Merge branch 'next' into for-linus

Prepare input updates for 4.17 merge window.

358 files changed, 25654 insertions, 16469 deletions

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 643cc4ba6872..3e5135dded16 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -31,5 +31,6 @@ config.mak.autogen
 .config-detected
 util/intel-pt-decoder/inat-tables.c
 arch/*/include/generated/
+trace/beauty/generated/
 pmu-events/pmu-events.c
 pmu-events/jevents
diff --git a/tools/perf/Build b/tools/perf/Build
index b48ca40fccf9..e5232d567611 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -25,7 +25,7 @@ perf-y += builtin-data.o
 perf-y += builtin-version.o
 perf-y += builtin-c2c.o
 
-perf-$(CONFIG_AUDIT) += builtin-trace.o
+perf-$(CONFIG_TRACE) += builtin-trace.o
 perf-$(CONFIG_LIBELF) += builtin-probe.o
 
 perf-y += bench/
@@ -50,6 +50,6 @@ libperf-y += util/
 libperf-y += arch/
 libperf-y += ui/
 libperf-y += scripts/
-libperf-$(CONFIG_AUDIT) += trace/beauty/
+libperf-$(CONFIG_TRACE) += trace/beauty/
 
 gtk-y += ui/gtk/
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 84681007f80f..73c2650bd0db 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -24,6 +24,9 @@ OPTIONS
 -a::
 --add=::
         Add specified file to the cache.
+-f::
+--force::
+        Don't complain, do it.
 -k::
 --kcore::
         Add specified kcore file to the cache. For the current host that is
diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
index f0796a47dfa3..90bb4aabe4f8 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -30,6 +30,10 @@ OPTIONS for 'convert'
 -i::
         Specify input perf data file path.
 
+-f::
+--force::
+        Don't complain, do it.
+
 -v::
 --verbose::
         Be more verbose (show counter open errors, etc).
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index 6f7200fb85cf..c0a66400a960 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -20,6 +20,10 @@ OPTIONS
 --input=::
         Input file name. (default: perf.data unless stdin is a fifo)
 
+-f::
+--force::
+        Don't complain, do it.
+
 -F::
 --freq=::
         Show just the sample frequency used for each event.
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index 87b2588d1cbd..a64d6588470e 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -60,6 +60,10 @@ include::itrace.txt[]
         found in the jitdumps files captured in the input perf.data file. Use this option
         if you are monitoring environment using JIT runtimes, such as Java, DART or V8.
 
+-f::
+--force::
+        Don't complain, do it.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index f709de54707b..e2a897ae3596 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,8 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
+'perf list' [--no-desc] [--long-desc]
+            [hw|sw|cache|tracepoint|pmu|sdt|metric|metricgroup|event_glob]
 
 DESCRIPTION
 -----------
@@ -47,6 +48,8 @@ counted. The following modifiers exist:
  P - use maximum detected precise level
  S - read sample value (PERF_SAMPLE_READ)
  D - pin the event to the PMU
+ W - group is weak and will fallback to non-group if not schedulable,
+     only supported in 'perf stat' for now.
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
@@ -201,7 +204,7 @@ For example Intel Core CPUs typically have four generic performance counters
 for the core, plus three fixed counters for instructions, cycles and
 ref-cycles. Some special events have restrictions on which counter they
 can schedule, and may not support multiple instances in a single group.
-When too many events are specified in the group none of them will not
+When too many events are specified in the group some of them will not
 be measured.
 
 Globally pinned events can limit the number of counters available for
@@ -246,6 +249,10 @@ To limit the list use:
 
 . 'sdt' to list all Statically Defined Tracepoint events.
 
+. 'metric' to list metrics
+
+. 'metricgroup' to list metricgroups with metrics.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index ab25be28c9dc..74d774592196 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -42,6 +42,10 @@ COMMON OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
+-f::
+--force::
+        Don't complan, do it.
+
 REPORT OPTIONS
 --------------
 
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index d7e4869905f1..b6866a05edd2 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -170,7 +170,7 @@ Probe points are defined by following syntax.
      or,
      sdt_PROVIDER:SDTEVENT
 
-'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
+'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function, and for return probes, a "\_\_return" suffix is automatically added to the function name. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
 Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
 modules.
 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.
@@ -182,6 +182,14 @@ Note that before using the SDT event, the target binary (on which SDT events are
 For details of the SDT, see below.
 https://sourceware.org/gdb/onlinedocs/gdb/Static-Probe-Points.html
 
+ESCAPED CHARACTER
+-----------------
+
+In the probe syntax, '=', '@', '+', ':' and ';' are treated as a special character. You can use a backslash ('\') to escape the special characters.
+This is useful if you need to probe on a specific versioned symbols, like @GLIBC_... suffixes, or also you need to specify a source file which includes the special characters.
+Note that usually single backslash is consumed by shell, so you might need to pass double backslash (\\) or wrapping with single quotes (\'AAA\@BBB').
+See EXAMPLES how it is used.
+
 PROBE ARGUMENT
 --------------
 Each probe argument follows below syntax.
@@ -277,6 +285,14 @@ Add a USDT probe to a target process running in a different mount namespace
 
  ./perf probe --target-ns <target pid> -x /usr/lib/jvm/java-1.8.0-openjdk-1.8.0.121-0.b13.el7_3.x86_64/jre/lib/amd64/server/libjvm.so %sdt_hotspot:thread__sleep__end
 
+Add a probe on specific versioned symbol by backslash escape
+
+ ./perf probe -x /lib64/libc-2.25.so 'malloc_get_state\@GLIBC_2.2.5'
+
+Add a probe in a source file using special characters by backslash escape
+
+ ./perf probe -x /opt/test/a.out 'foo\+bar.c:4'
+
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 63526f4416ea..3eea6de35a38 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -377,6 +377,8 @@ symbolic names, e.g. on x86, ax, si. To list the available registers use
 --intr-regs=\?. To name registers, pass a comma separated list such as
 --intr-regs=ax,bx. The list of register is architecture dependent.
 
+--user-regs::
+Capture user registers at sample time. Same arguments as -I.
 
 --running-time::
 Record running and enabled time for read events (:S)
@@ -428,6 +430,9 @@ Configure all used events to run in user space.
 --timestamp-filename
 Append timestamp to output file name.
 
+--timestamp-boundary::
+Record timestamp boundary (time of first/last samples).
+
 --switch-output[=mode]::
 Generate multiple perf.data files, timestamp prefixed, switching to a new one
 based on 'mode' value:
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 383a98d992ed..907e505b6309 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -402,6 +402,26 @@ OPTIONS
         stop time is not given (i.e, time string is 'x.y,') then analysis goes
         to end of file.
 
+        Also support time percent with multiple time range. Time string is
+        'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
+
+        For example:
+        Select the second 10% time slice:
+
+          perf report --time 10%/2
+
+        Select from 0% to 10% time slice:
+
+          perf report --time 0%-10%
+
+        Select the first and second 10% time slices:
+
+          perf report --time 10%/1,10%/2
+
+        Select from 0% to 10% and 30% to 40% slices:
+
+          perf report --time 0%-10%,30%-40%
+
 --itrace::
         Options for decoding instruction tracing data. The options are:
 
@@ -434,10 +454,26 @@ include::itrace.txt[]
 
 --inline::
         If a callgraph address belongs to an inlined function, the inline stack
-        will be printed. Each entry is function name or file/line.
+        will be printed. Each entry is function name or file/line. Enabled by
+        default, disable with --no-inline.
+
+--mmaps::
+        Show --tasks output plus mmap information in a format similar to
+        /proc/<PID>/maps.
+
+        Please note that not all mmaps are stored, options affecting which ones
+        are include 'perf record --data', for instance.
+
+--stats::
+        Display overall events statistics without any further processing.
+        (like the one at the end of the perf report -D command)
+
+--tasks::
+        Display monitored tasks stored in perf data. Displaying pid/tid/ppid
+        plus the command string aligned to distinguish parent and child tasks.
 
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-annotate[1]
+linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index a092a2499e8f..c7e50f263887 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -74,6 +74,10 @@ OPTIONS
 --dump-raw-trace=::
         Display verbose dump of the sched data.
 
+-f::
+--force::
+        Don't complain, do it.
+
 OPTIONS for 'perf sched map'
 ----------------------------
 
@@ -106,6 +110,14 @@ OPTIONS for 'perf sched timehist'
 --max-stack::
         Maximum number of functions to display in backtrace, default 5.
 
+-p=::
+--pid=::
+        Only show events for given process ID (comma separated list).
+
+-t=::
+--tid=::
+        Only show events for given thread ID (comma separated list).
+
 -s::
 --summary::
     Show only a summary of scheduling by thread with min, max, and average
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 18dfcfa38454..7730c1d2b5d3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,8 +116,8 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
-        callindent, insn, insnlen, synth, phys_addr.
+        srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
+        brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
@@ -217,6 +217,32 @@ OPTIONS
 
         The brstackoff field will print an offset into a specific dso/binary.
 
+        With the metric option perf script can compute metrics for
+        sampling periods, similar to perf stat. This requires
+        specifying a group with multiple metrics with the :S option
+        for perf record. perf will sample on the first event, and
+        compute metrics for all the events in the group. Please note
+        that the metric computed is averaged over the whole sampling
+        period, not just for the sample point.
+
+        For sample events it's possible to display misc field with -F +misc option,
+        following letters are displayed for each bit:
+
+          PERF_RECORD_MISC_KERNEL        K
+          PERF_RECORD_MISC_USER          U
+          PERF_RECORD_MISC_HYPERVISOR    H
+          PERF_RECORD_MISC_GUEST_KERNEL  G
+          PERF_RECORD_MISC_GUEST_USER    g
+          PERF_RECORD_MISC_MMAP_DATA*    M
+          PERF_RECORD_MISC_COMM_EXEC     E
+          PERF_RECORD_MISC_SWITCH_OUT    S
+
+          $ perf script -F +misc ...
+           sched-messaging  1414 K     28690.636582:       4590 cycles ...
+           sched-messaging  1407 U     28690.636600:     325620 cycles ...
+           sched-messaging  1414 K     28690.636608:      19473 cycles ...
+          misc field ___________/
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
@@ -274,6 +300,9 @@ OPTIONS
         Display context switch events i.e. events of type PERF_RECORD_SWITCH or
         PERF_RECORD_SWITCH_CPU_WIDE.
 
+--show-lost-events
+        Display lost events i.e. events of type PERF_RECORD_LOST.
+
 --demangle::
         Demangle symbol names to human readable form. It's enabled by default,
         disable with --no-demangle.
@@ -321,13 +350,34 @@ include::itrace.txt[]
         stop time is not given (i.e, time string is 'x.y,') then analysis goes
         to end of file.
 
+        Also support time percent with multipe time range. Time string is
+        'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
+
+        For example:
+        Select the second 10% time slice:
+        perf script --time 10%/2
+
+        Select from 0% to 10% time slice:
+        perf script --time 0%-10%
+
+        Select the first and second 10% time slices:
+        perf script --time 10%/1,10%/2
+
+        Select from 0% to 10% and 30% to 40% slices:
+        perf script --time 0%-10%,30%-40%
+
 --max-blocks::
         Set the maximum number of program blocks to print with brstackasm for
         each sample.
 
+--per-event-dump::
+        Create per event files with a "perf.data.EVENT.dump" name instead of
+        printing to stdout, useful, for instance, for generating flamegraphs.
+
 --inline::
         If a callgraph address belongs to an inlined function, the inline stack
-        will be printed. Each entry has function name and file/line.
+        will be printed. Each entry has function name and file/line. Enabled by
+        default, disable with --no-inline.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index c37d61682dfb..823fce7674bb 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -199,6 +199,13 @@ Aggregate counts per processor socket for system-wide mode measurements.
 --per-core::
 Aggregate counts per physical processor for system-wide mode measurements.
 
+-M::
+--metrics::
+Print metrics or metricgroups specified in a comma separated list.
+For a group all metrics from the group are added.
+The events from the metrics are automatically measured.
+See perf list output for the possble metrics and metricgroups.
+
 -A::
 --no-aggr::
 Do not aggregate counts across all monitored CPUs.
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index df98d1c82688..ef0c7565bd5c 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -50,7 +50,9 @@ TIMECHART OPTIONS
 -p::
 --process::
         Select the processes to display, by name or PID
-
+-f::
+--force::
+        Don't complain, do it.
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
 -n::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index d864ea6fd367..8a32cc77bead 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -240,6 +240,9 @@ Default is to monitor all CPUS.
 --force::
         Don't do ownership validation.
 
+--num-thread-synthesize::
+        The number of threads to run when synthesizing events for existing processes.
+        By default, the number of threads equals to the number of online CPUs.
 
 INTERACTIVE PROMPTING KEYS
 --------------------------
@@ -265,6 +268,12 @@ INTERACTIVE PROMPTING KEYS
 [S]::
         Stop annotation, return to full profile display.
 
+[K]::
+        Hide kernel symbols.
+
+[U]::
+        Hide user symbols.
+
 [z]::
         Toggle event count zeroing across display updates.
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index d53bea6bd571..33a88e984e66 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -86,18 +86,18 @@ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-
 In per-thread mode with inheritance mode on (default), Events are captured only when
 the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
---duration:
+--duration::
         Show only events that had a duration greater than N.M ms.
 
---sched:
+--sched::
         Accrue thread runtime and provide a summary at the end of the session.
 
--i
---input
+-i::
+--input::
         Process events from a given perf data file.
 
--T
---time
+-T::
+--time::
         Print full timestamp rather time relative to first sample.
 
 --comm::
@@ -117,6 +117,10 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
         Show tool stats such as number of times fd->pathname was discovered thru
         hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
 
+-f::
+--force::
+        Don't complain, do it.
+
 -F=[all|min|maj]::
 --pf=[all|min|maj]::
         Trace pagefaults. Optionally, you can specify whether you want minor,
@@ -159,6 +163,10 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
         Implies '--call-graph dwarf' when --call-graph not present on the
         command line, on systems where DWARF unwinding was built in.
 
+--print-sample::
+        Print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info for the
+        raw_syscalls:sys_{enter,exit} tracepoints, for debugging.
+
 --proc-map-timeout::
         When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
         because the file may be huge. A time out is needed in such cases.
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index e90c59c6d815..f7d85e89a98a 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -238,6 +238,33 @@ struct auxtrace_index {
         struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
 };
 
+        HEADER_STAT = 19,
+
+This is merely a flag signifying that the data section contains data
+recorded from perf stat record.
+
+        HEADER_CACHE = 20,
+
+Description of the cache hierarchy. Based on the Linux sysfs format
+in /sys/devices/system/cpu/cpu*/cache/
+
+        u32 version     Currently always 1
+        u32 number_of_cache_levels
+
+struct {
+        u32     level;
+        u32     line_size;
+        u32     sets;
+        u32     ways;
+        struct perf_header_string type;
+        struct perf_header_string size;
+        struct perf_header_string map;
+}[number_of_cache_levels];
+
+        HEADER_SAMPLE_TIME = 21,
+
+Two uint64_t for the time of first sample and the time of last sample.
+
         other bits are reserved and should ignored for now
         HEADER_FEAT_BITS        = 256,
 
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index db0ca3063eae..849599f39c5e 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -32,3 +32,5 @@ Order by the overhead of source file name and line number: perf report -s srclin
 System-wide collection from all CPUs: perf record -a
 Show current config key-value pairs: perf config --list
 Show user configuration overrides: perf config --user --list
+To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`
+To report cacheline events from previous recording: perf c2c report
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 63f534a0902f..0dfdaa9fa81e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -22,6 +22,7 @@ include $(srctree)/tools/scripts/Makefile.arch
 $(call detected_var,SRCARCH)
 
 NO_PERF_REGS := 1
+NO_SYSCALL_TABLE := 1
 
 # Additional ARCH settings for ppc
 ifeq ($(SRCARCH),powerpc)
@@ -33,7 +34,8 @@ endif
 ifeq ($(SRCARCH),x86)
   $(call detected,CONFIG_X86)
   ifeq (${IS_64_BIT}, 1)
-    CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated
+    NO_SYSCALL_TABLE := 0
+    CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -I$(OUTPUT)arch/x86/include/generated
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma
     $(call detected,CONFIG_X86_64)
@@ -53,15 +55,25 @@ ifeq ($(SRCARCH),arm64)
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
+ifeq ($(ARCH),s390)
+  NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -fPIC -I$(OUTPUT)arch/s390/include/generated
+endif
+
 ifeq ($(NO_PERF_REGS),0)
   $(call detected,CONFIG_PERF_REGS)
 endif
 
+ifneq ($(NO_SYSCALL_TABLE),1)
+  CFLAGS += -DHAVE_SYSCALL_TABLE
+endif
+
 # So far there's only x86 and arm libdw unwind support merged in perf.
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc s390))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
@@ -93,6 +105,16 @@ FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 
+ifdef CSINCLUDES
+  LIBOPENCSD_CFLAGS := -I$(CSINCLUDES)
+endif
+OPENCSDLIBS := -lopencsd_c_api -lopencsd
+ifdef CSLIBS
+  LIBOPENCSD_LDFLAGS := -L$(CSLIBS)
+endif
+FEATURE_CHECK_CFLAGS-libopencsd := $(LIBOPENCSD_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libopencsd := $(LIBOPENCSD_LDFLAGS) $(OPENCSDLIBS)
+
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
@@ -184,9 +206,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  ifeq ($(CC_NO_CLANG), 1)
-    PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
-  endif
+  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
@@ -263,6 +283,10 @@ ifeq ($(feature-pthread-attr-setaffinity-np), 1)
   CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP
 endif
 
+ifeq ($(feature-pthread-barrier), 1)
+  CFLAGS += -DHAVE_PTHREAD_BARRIER
+endif
+
 ifndef NO_BIONIC
   $(call feature_check,bionic)
   ifeq ($(feature-bionic), 1)
@@ -339,6 +363,21 @@ ifeq ($(feature-setns), 1)
   $(call detected,CONFIG_SETNS)
 endif
 
+ifndef NO_CORESIGHT
+  ifeq ($(feature-libopencsd), 1)
+    CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS)
+    LDFLAGS += $(LIBOPENCSD_LDFLAGS)
+    EXTLIBS += $(OPENCSDLIBS)
+    $(call detected,CONFIG_LIBOPENCSD)
+    ifdef CSTRACE_RAW
+      CFLAGS += -DCS_DEBUG_RAW
+      ifeq (${CSTRACE_RAW}, packed)
+        CFLAGS += -DCS_RAW_PACKED
+      endif
+    endif
+  endif
+endif
+
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
   EXTLIBS += -lelf
@@ -517,14 +556,18 @@ ifndef NO_LIBUNWIND
   EXTLIBS += $(EXTLIBS_LIBUNWIND)
 endif
 
-ifndef NO_LIBAUDIT
-  ifneq ($(feature-libaudit), 1)
-    msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
-    NO_LIBAUDIT := 1
-  else
-    CFLAGS += -DHAVE_LIBAUDIT_SUPPORT
-    EXTLIBS += -laudit
-    $(call detected,CONFIG_AUDIT)
+ifeq ($(NO_SYSCALL_TABLE),0)
+  $(call detected,CONFIG_TRACE)
+else
+  ifndef NO_LIBAUDIT
+    ifneq ($(feature-libaudit), 1)
+      msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
+      NO_LIBAUDIT := 1
+    else
+      CFLAGS += -DHAVE_LIBAUDIT_SUPPORT
+      EXTLIBS += -laudit
+      $(call detected,CONFIG_TRACE)
+    endif
   endif
 endif
 
@@ -572,14 +615,15 @@ ifndef NO_GTK2
   endif
 endif
 
-
 ifdef NO_LIBPERL
   CFLAGS += -DNO_LIBPERL
 else
   PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
   PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-  PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+  PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
+  PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
   ifneq ($(feature-libperl), 1)
@@ -765,7 +809,7 @@ else
   NO_PERF_READ_VDSOX32 := 1
 endif
 
-ifdef LIBBABELTRACE
+ifndef NO_LIBBABELTRACE
   $(call feature_check,libbabeltrace)
   ifeq ($(feature-libbabeltrace), 1)
     CFLAGS += -DHAVE_LIBBABELTRACE_SUPPORT $(LIBBABELTRACE_CFLAGS)
@@ -932,6 +976,10 @@ define print_var_code
 endef
 
 ifeq ($(VF),1)
+  # Display EXTRA features which are detected manualy
+  # from here with feature_check call and thus cannot
+  # be partof global state output.
+  $(foreach feat,$(FEATURE_TESTS_EXTRA),$(call feature_print_status,$(feat),))
   $(call print_var,prefix)
   $(call print_var,bindir)
   $(call print_var,libdir)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 91ef44bfaf3e..012328038594 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -77,7 +77,7 @@ include ../scripts/utilities.mak
 #
 # Define NO_ZLIB if you do not want to support compressed kernel modules
 #
-# Define LIBBABELTRACE if you DO want libbabeltrace support
+# Define NO_LIBBABELTRACE if you do not want libbabeltrace support
 # for CTF data format.
 #
 # Define NO_LZMA if you do not want to support compressed (xz) kernel modules
@@ -98,6 +98,8 @@ include ../scripts/utilities.mak
 # When selected, pass LLVM_CONFIG=/path/to/llvm-config to `make' if
 # llvm-config is not in $PATH.
 
+# Define NO_CORESIGHT if you do not want support for CoreSight trace decoding.
+
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
 LC_COLLATE=C
@@ -144,12 +146,6 @@ define allow-override
     $(eval $(1) = $(2)))
 endef
 
-# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
-$(call allow-override,CC,$(CROSS_COMPILE)gcc)
-$(call allow-override,AR,$(CROSS_COMPILE)ar)
-$(call allow-override,LD,$(CROSS_COMPILE)ld)
-$(call allow-override,CXX,$(CROSS_COMPILE)g++)
-
 LD += $(EXTRA_LDFLAGS)
 
 HOSTCC  ?= gcc
@@ -173,7 +169,7 @@ AWK     = awk
 # non-config cases
 config := 1
 
-NON_CONFIG_TARGETS := clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
+NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
 
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -420,6 +416,13 @@ sndrv_pcm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
 $(sndrv_pcm_ioctl_array): $(sndrv_pcm_hdr_dir)/asound.h $(sndrv_pcm_ioctl_tbl)
         $(Q)$(SHELL) '$(sndrv_pcm_ioctl_tbl)' $(sndrv_pcm_hdr_dir) > $@
 
+kcmp_type_array := $(beauty_outdir)/kcmp_type_array.c
+kcmp_hdr_dir := $(srctree)/tools/include/uapi/linux/
+kcmp_type_tbl := $(srctree)/tools/perf/trace/beauty/kcmp_type.sh
+
+$(kcmp_type_array): $(kcmp_hdr_dir)/kcmp.h $(kcmp_type_tbl)
+        $(Q)$(SHELL) '$(kcmp_type_tbl)' $(kcmp_hdr_dir) > $@
+
 kvm_ioctl_array := $(beauty_ioctl_outdir)/kvm_ioctl_array.c
 kvm_hdr_dir := $(srctree)/tools/include/uapi/linux
 kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -441,6 +444,27 @@ perf_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/perf_ioctl.sh
 $(perf_ioctl_array): $(perf_hdr_dir)/perf_event.h $(perf_ioctl_tbl)
         $(Q)$(SHELL) '$(perf_ioctl_tbl)' $(perf_hdr_dir) > $@
 
+madvise_behavior_array := $(beauty_outdir)/madvise_behavior_array.c
+madvise_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
+madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
+
+$(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
+        $(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
+
+prctl_option_array := $(beauty_outdir)/prctl_option_array.c
+prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
+prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
+
+$(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl)
+        $(Q)$(SHELL) '$(prctl_option_tbl)' $(prctl_hdr_dir) > $@
+
+arch_errno_name_array := $(beauty_outdir)/arch_errno_name_array.c
+arch_errno_hdr_dir := $(srctree)/tools
+arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
+
+$(arch_errno_name_array): $(arch_errno_tbl)
+        $(Q)$(SHELL) '$(arch_errno_tbl)' $(CC) $(arch_errno_hdr_dir) > $@
+
 all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
@@ -539,9 +563,13 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
         $(pkey_alloc_access_rights_array) \
         $(sndrv_pcm_ioctl_array) \
         $(sndrv_ctl_ioctl_array) \
+        $(kcmp_type_array) \
         $(kvm_ioctl_array) \
         $(vhost_virtio_ioctl_array) \
-        $(perf_ioctl_array)
+        $(madvise_behavior_array) \
+        $(perf_ioctl_array) \
+        $(prctl_option_array) \
+        $(arch_errno_name_array)
 
 $(OUTPUT)%.o: %.c prepare FORCE
         $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
@@ -802,7 +830,10 @@ config-clean:
         $(call QUIET_CLEAN, config)
         $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
 
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean
+python-clean:
+        $(python-clean)
+
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean python-clean
         $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
         $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
         $(Q)$(RM) $(OUTPUT).config-detected
@@ -811,15 +842,18 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
                 $(OUTPUT)util/intel-pt-decoder/inat-tables.c \
                 $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
                 $(OUTPUT)pmu-events/pmu-events.c \
+                $(OUTPUT)$(madvise_behavior_array) \
                 $(OUTPUT)$(drm_ioctl_array) \
                 $(OUTPUT)$(pkey_alloc_access_rights_array) \
                 $(OUTPUT)$(sndrv_ctl_ioctl_array) \
                 $(OUTPUT)$(sndrv_pcm_ioctl_array) \
                 $(OUTPUT)$(kvm_ioctl_array) \
+                $(OUTPUT)$(kcmp_type_array) \
                 $(OUTPUT)$(vhost_virtio_ioctl_array) \
-                $(OUTPUT)$(perf_ioctl_array)
+                $(OUTPUT)$(perf_ioctl_array) \
+                $(OUTPUT)$(prctl_option_array) \
+                $(OUTPUT)$(arch_errno_name_array)
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
-        $(python-clean)
 
 #
 # To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index b39b16395aac..f64516d5b23e 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -24,7 +25,7 @@ static struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const c
         return ops;
 }
 
-static int arm__annotate_init(struct arch *arch)
+static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         struct arm_annotate *arm;
         int err;
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 8edf2cb71564..2323581b157d 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -22,6 +22,42 @@
 #include "../../util/evlist.h"
 #include "../../util/pmu.h"
 #include "cs-etm.h"
+#include "arm-spe.h"
+
+static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err)
+{
+        struct perf_pmu **arm_spe_pmus = NULL;
+        int ret, i, nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+        /* arm_spe_xxxxxxxxx\0 */
+        char arm_spe_pmu_name[sizeof(ARM_SPE_PMU_NAME) + 10];
+
+        arm_spe_pmus = zalloc(sizeof(struct perf_pmu *) * nr_cpus);
+        if (!arm_spe_pmus) {
+                pr_err("spes alloc failed\n");
+                *err = -ENOMEM;
+                return NULL;
+        }
+
+        for (i = 0; i < nr_cpus; i++) {
+                ret = sprintf(arm_spe_pmu_name, "%s%d", ARM_SPE_PMU_NAME, i);
+                if (ret < 0) {
+                        pr_err("sprintf failed\n");
+                        *err = -ENOMEM;
+                        return NULL;
+                }
+
+                arm_spe_pmus[*nr_spes] = perf_pmu__find(arm_spe_pmu_name);
+                if (arm_spe_pmus[*nr_spes]) {
+                        pr_debug2("%s %d: arm_spe_pmu %d type %d name %s\n",
+                                 __func__, __LINE__, *nr_spes,
+                                 arm_spe_pmus[*nr_spes]->type,
+                                 arm_spe_pmus[*nr_spes]->name);
+                        (*nr_spes)++;
+                }
+        }
+
+        return arm_spe_pmus;
+}
 
 struct auxtrace_record
 *auxtrace_record__init(struct perf_evlist *evlist, int *err)
@@ -29,22 +65,51 @@ struct auxtrace_record
         struct perf_pmu *cs_etm_pmu;
         struct perf_evsel *evsel;
         bool found_etm = false;
+        bool found_spe = false;
+        static struct perf_pmu **arm_spe_pmus = NULL;
+        static int nr_spes = 0;
+        int i;
+
+        if (!evlist)
+                return NULL;
 
         cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
 
-        if (evlist) {
-                evlist__for_each_entry(evlist, evsel) {
-                        if (cs_etm_pmu &&
-                            evsel->attr.type == cs_etm_pmu->type)
-                                found_etm = true;
+        if (!arm_spe_pmus)
+                arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err);
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (cs_etm_pmu &&
+                    evsel->attr.type == cs_etm_pmu->type)
+                        found_etm = true;
+
+                if (!nr_spes)
+                        continue;
+
+                for (i = 0; i < nr_spes; i++) {
+                        if (evsel->attr.type == arm_spe_pmus[i]->type) {
+                                found_spe = true;
+                                break;
+                        }
                 }
         }
 
+        if (found_etm && found_spe) {
+                pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n");
+                *err = -EOPNOTSUPP;
+                return NULL;
+        }
+
         if (found_etm)
                 return cs_etm_record_init(err);
 
+#if defined(__aarch64__)
+        if (found_spe)
+                return arm_spe_recording_init(err, arm_spe_pmus[i]);
+#endif
+
         /*
-         * Clear 'err' even if we haven't found a cs_etm event - that way perf
+         * Clear 'err' even if we haven't found an event - that way perf
          * record can still be used even if tracers aren't present.  The NULL
          * return value will take care of telling the infrastructure HW tracing
          * isn't available.
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index 98d67399a0d6..ac4dffc807b8 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -20,6 +20,7 @@
 #include <linux/perf_event.h>
 
 #include "cs-etm.h"
+#include "arm-spe.h"
 #include "../../util/pmu.h"
 
 struct perf_event_attr
@@ -30,7 +31,12 @@ struct perf_event_attr
                 /* add ETM default config here */
                 pmu->selectable = true;
                 pmu->set_drv_config = cs_etm_set_drv_config;
+#if defined(__aarch64__)
+        } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) {
+                return arm_spe_pmu_default_config(pmu);
+#endif
         }
+
 #endif
         return NULL;
 }
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 9a3e0523e2c9..6688977e4ac7 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -26,7 +27,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
         return ops;
 }
 
-static int arm64__annotate_init(struct arch *arch)
+static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         struct arm64_annotate *arm;
         int err;
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index cef6fb38d17e..c0b8dfef98ba 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,6 +1,9 @@
+libperf-y += header.o
+libperf-y += sym-handling.o
 libperf-$(CONFIG_DWARF)     += dwarf-regs.o
 libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 
 libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
                               ../../arm/util/auxtrace.o \
-                              ../../arm/util/cs-etm.o
+                              ../../arm/util/cs-etm.o \
+                              arm-spe.o
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
new file mode 100644
index 000000000000..1120e39c1b00
--- /dev/null
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <time.h>
+
+#include "../../util/cpumap.h"
+#include "../../util/evsel.h"
+#include "../../util/evlist.h"
+#include "../../util/session.h"
+#include "../../util/util.h"
+#include "../../util/pmu.h"
+#include "../../util/debug.h"
+#include "../../util/auxtrace.h"
+#include "../../util/arm-spe.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+
+struct arm_spe_recording {
+        struct auxtrace_record          itr;
+        struct perf_pmu                 *arm_spe_pmu;
+        struct perf_evlist              *evlist;
+};
+
+static size_t
+arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+                       struct perf_evlist *evlist __maybe_unused)
+{
+        return ARM_SPE_AUXTRACE_PRIV_SIZE;
+}
+
+static int arm_spe_info_fill(struct auxtrace_record *itr,
+                             struct perf_session *session,
+                             struct auxtrace_info_event *auxtrace_info,
+                             size_t priv_size)
+{
+        struct arm_spe_recording *sper =
+                        container_of(itr, struct arm_spe_recording, itr);
+        struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+
+        if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE)
+                return -EINVAL;
+
+        if (!session->evlist->nr_mmaps)
+                return -EINVAL;
+
+        auxtrace_info->type = PERF_AUXTRACE_ARM_SPE;
+        auxtrace_info->priv[ARM_SPE_PMU_TYPE] = arm_spe_pmu->type;
+
+        return 0;
+}
+
+static int arm_spe_recording_options(struct auxtrace_record *itr,
+                                     struct perf_evlist *evlist,
+                                     struct record_opts *opts)
+{
+        struct arm_spe_recording *sper =
+                        container_of(itr, struct arm_spe_recording, itr);
+        struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
+        struct perf_evsel *evsel, *arm_spe_evsel = NULL;
+        bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+        struct perf_evsel *tracking_evsel;
+        int err;
+
+        sper->evlist = evlist;
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (evsel->attr.type == arm_spe_pmu->type) {
+                        if (arm_spe_evsel) {
+                                pr_err("There may be only one " ARM_SPE_PMU_NAME "x event\n");
+                                return -EINVAL;
+                        }
+                        evsel->attr.freq = 0;
+                        evsel->attr.sample_period = 1;
+                        arm_spe_evsel = evsel;
+                        opts->full_auxtrace = true;
+                }
+        }
+
+        if (!opts->full_auxtrace)
+                return 0;
+
+        /* We are in full trace mode but '-m,xyz' wasn't specified */
+        if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+                if (privileged) {
+                        opts->auxtrace_mmap_pages = MiB(4) / page_size;
+                } else {
+                        opts->auxtrace_mmap_pages = KiB(128) / page_size;
+                        if (opts->mmap_pages == UINT_MAX)
+                                opts->mmap_pages = KiB(256) / page_size;
+                }
+        }
+
+        /* Validate auxtrace_mmap_pages */
+        if (opts->auxtrace_mmap_pages) {
+                size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+                size_t min_sz = KiB(8);
+
+                if (sz < min_sz || !is_power_of_2(sz)) {
+                        pr_err("Invalid mmap size for ARM SPE: must be at least %zuKiB and a power of 2\n",
+                               min_sz / 1024);
+                        return -EINVAL;
+                }
+        }
+
+
+        /*
+         * To obtain the auxtrace buffer file descriptor, the auxtrace event
+         * must come first.
+         */
+        perf_evlist__to_front(evlist, arm_spe_evsel);
+
+        perf_evsel__set_sample_bit(arm_spe_evsel, CPU);
+        perf_evsel__set_sample_bit(arm_spe_evsel, TIME);
+        perf_evsel__set_sample_bit(arm_spe_evsel, TID);
+
+        /* Add dummy event to keep tracking */
+        err = parse_events(evlist, "dummy:u", NULL);
+        if (err)
+                return err;
+
+        tracking_evsel = perf_evlist__last(evlist);
+        perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+        tracking_evsel->attr.freq = 0;
+        tracking_evsel->attr.sample_period = 1;
+        perf_evsel__set_sample_bit(tracking_evsel, TIME);
+        perf_evsel__set_sample_bit(tracking_evsel, CPU);
+        perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+
+        return 0;
+}
+
+static u64 arm_spe_reference(struct auxtrace_record *itr __maybe_unused)
+{
+        struct timespec ts;
+
+        clock_gettime(CLOCK_MONOTONIC_RAW, &ts);
+
+        return ts.tv_sec ^ ts.tv_nsec;
+}
+
+static void arm_spe_recording_free(struct auxtrace_record *itr)
+{
+        struct arm_spe_recording *sper =
+                        container_of(itr, struct arm_spe_recording, itr);
+
+        free(sper);
+}
+
+static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
+{
+        struct arm_spe_recording *sper =
+                        container_of(itr, struct arm_spe_recording, itr);
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(sper->evlist, evsel) {
+                if (evsel->attr.type == sper->arm_spe_pmu->type)
+                        return perf_evlist__enable_event_idx(sper->evlist,
+                                                             evsel, idx);
+        }
+        return -EINVAL;
+}
+
+struct auxtrace_record *arm_spe_recording_init(int *err,
+                                               struct perf_pmu *arm_spe_pmu)
+{
+        struct arm_spe_recording *sper;
+
+        if (!arm_spe_pmu) {
+                *err = -ENODEV;
+                return NULL;
+        }
+
+        sper = zalloc(sizeof(struct arm_spe_recording));
+        if (!sper) {
+                *err = -ENOMEM;
+                return NULL;
+        }
+
+        sper->arm_spe_pmu = arm_spe_pmu;
+        sper->itr.recording_options = arm_spe_recording_options;
+        sper->itr.info_priv_size = arm_spe_info_priv_size;
+        sper->itr.info_fill = arm_spe_info_fill;
+        sper->itr.free = arm_spe_recording_free;
+        sper->itr.reference = arm_spe_reference;
+        sper->itr.read_finish = arm_spe_read_finish;
+        sper->itr.alignment = 0;
+
+        return &sper->itr;
+}
+
+struct perf_event_attr
+*arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu)
+{
+        struct perf_event_attr *attr;
+
+        attr = zalloc(sizeof(struct perf_event_attr));
+        if (!attr) {
+                pr_err("arm_spe default config cannot allocate a perf_event_attr\n");
+                return NULL;
+        }
+
+        /*
+         * If kernel driver doesn't advertise a minimum,
+         * use max allowable by PMSIDR_EL1.INTERVAL
+         */
+        if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu",
+                                  &attr->sample_period) != 1) {
+                pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n");
+                attr->sample_period = 4096;
+        }
+
+        arm_spe_pmu->selectable = true;
+        arm_spe_pmu->is_uncore = false;
+
+        return attr;
+}
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
new file mode 100644
index 000000000000..534cd2507d83
--- /dev/null
+++ b/tools/perf/arch/arm64/util/header.c
@@ -0,0 +1,65 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <api/fs/fs.h>
+#include "header.h"
+
+#define MIDR "/regs/identification/midr_el1"
+#define MIDR_SIZE 19
+#define MIDR_REVISION_MASK      0xf
+#define MIDR_VARIANT_SHIFT      20
+#define MIDR_VARIANT_MASK       (0xf << MIDR_VARIANT_SHIFT)
+
+char *get_cpuid_str(struct perf_pmu *pmu)
+{
+        char *buf = NULL;
+        char path[PATH_MAX];
+        const char *sysfs = sysfs__mountpoint();
+        int cpu;
+        u64 midr = 0;
+        struct cpu_map *cpus;
+        FILE *file;
+
+        if (!sysfs || !pmu || !pmu->cpus)
+                return NULL;
+
+        buf = malloc(MIDR_SIZE);
+        if (!buf)
+                return NULL;
+
+        /* read midr from list of cpus mapped to this pmu */
+        cpus = cpu_map__get(pmu->cpus);
+        for (cpu = 0; cpu < cpus->nr; cpu++) {
+                scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
+                                sysfs, cpus->map[cpu]);
+
+                file = fopen(path, "r");
+                if (!file) {
+                        pr_debug("fopen failed for file %s\n", path);
+                        continue;
+                }
+
+                if (!fgets(buf, MIDR_SIZE, file)) {
+                        fclose(file);
+                        continue;
+                }
+                fclose(file);
+
+                /* Ignore/clear Variant[23:20] and
+                 * Revision[3:0] of MIDR
+                 */
+                midr = strtoul(buf, NULL, 16);
+                midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK));
+                scnprintf(buf, MIDR_SIZE, "0x%016lx", midr);
+                /* got midr break loop */
+                break;
+        }
+
+        if (!midr) {
+                pr_err("failed to get cpuid string for PMU %s\n", pmu->name);
+                free(buf);
+                buf = NULL;
+        }
+
+        cpu_map__put(cpus);
+        return buf;
+}
diff --git a/tools/perf/arch/arm64/util/sym-handling.c b/tools/perf/arch/arm64/util/sym-handling.c
new file mode 100644
index 000000000000..0051b1ee8450
--- /dev/null
+++ b/tools/perf/arch/arm64/util/sym-handling.c
@@ -0,0 +1,22 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "debug.h"
+#include "symbol.h"
+#include "map.h"
+#include "probe-event.h"
+#include "probe-file.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+        return ehdr.e_type == ET_EXEC ||
+               ehdr.e_type == ET_REL ||
+               ehdr.e_type == ET_DYN;
+}
+#endif
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 8c0cfeb55f8e..c6f373508a4f 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -1,12 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
-#include <sys/utsname.h>
 #include "common.h"
+#include "../util/env.h"
 #include "../util/util.h"
 #include "../util/debug.h"
 
-#include "sane_ctype.h"
-
 const char *const arm_triplets[] = {
         "arm-eabi-",
         "arm-linux-androideabi-",
@@ -120,55 +118,19 @@ static int lookup_triplets(const char *const *triplets, const char *name)
         return -1;
 }
 
-/*
- * Return architecture name in a normalized form.
- * The conversion logic comes from the Makefile.
- */
-const char *normalize_arch(char *arch)
-{
-        if (!strcmp(arch, "x86_64"))
-                return "x86";
-        if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
-                return "x86";
-        if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
-                return "sparc";
-        if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
-                return "arm64";
-        if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
-                return "arm";
-        if (!strncmp(arch, "s390", 4))
-                return "s390";
-        if (!strncmp(arch, "parisc", 6))
-                return "parisc";
-        if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
-                return "powerpc";
-        if (!strncmp(arch, "mips", 4))
-                return "mips";
-        if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
-                return "sh";
-
-        return arch;
-}
-
 static int perf_env__lookup_binutils_path(struct perf_env *env,
                                           const char *name, const char **path)
 {
         int idx;
-        const char *arch, *cross_env;
-        struct utsname uts;
+        const char *arch = perf_env__arch(env), *cross_env;
         const char *const *path_list;
         char *buf = NULL;
 
-        arch = normalize_arch(env->arch);
-
-        if (uname(&uts) < 0)
-                goto out;
-
         /*
          * We don't need to try to find objdump path for native system.
          * Just use default binutils path (e.g.: "objdump").
          */
-        if (!strcmp(normalize_arch(uts.machine), arch))
+        if (!strcmp(perf_env__arch(NULL), arch))
                 goto out;
 
         cross_env = getenv("CROSS_COMPILE");
diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h
index a1546509ad24..2d875baa92e6 100644
--- a/tools/perf/arch/common.h
+++ b/tools/perf/arch/common.h
@@ -7,6 +7,5 @@
 extern const char *objdump_path;
 
 int perf_env__lookup_objdump(struct perf_env *env);
-const char *normalize_arch(char *arch);
 
 #endif /* ARCH_PERF_COMMON_H */
diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
index b7bc04980fe8..a3f423c27cae 100644
--- a/tools/perf/arch/powerpc/annotate/instructions.c
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+
 static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, const char *name)
 {
         int i;
@@ -47,7 +49,7 @@ static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, con
         return ops;
 }
 
-static int powerpc__annotate_init(struct arch *arch)
+static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         if (!arch->initialized) {
                 arch->initialized = true;
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 7a4cf80c207a..0b242664f5ea 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -35,7 +35,7 @@ get_cpuid(char *buffer, size_t sz)
 }
 
 char *
-get_cpuid_str(void)
+get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
         char *bufp;
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 9c4e23d8c8ce..53d83d7e6a09 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -64,6 +64,14 @@ int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 
         return strncmp(namea, nameb, n);
 }
+
+const char *arch__normalize_symbol_name(const char *name)
+{
+        /* Skip over initial dot */
+        if (name && *name == '.')
+                name++;
+        return name;
+}
 #endif
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 21322e0385b8..dfa6e3103437 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -2,3 +2,29 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/s390/include/generated/asm
+header := $(out)/syscalls_64.c
+syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl
+sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls
+sysdef := $(sysprf)/syscall.tbl
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+        @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+        (diff -B $(sysdef) $(syskrn) >/dev/null) \
+        || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+        $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@
+
+clean::
+        $(call QUIET_CLEAN, s390) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index c9a81673e8aa..8c72b44444cb 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+
 static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
 {
         struct ins_ops *ops = NULL;
@@ -16,11 +18,12 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
         if (!strcmp(name, "br"))
                 ops = &ret_ops;
 
-        arch__associate_ins_ops(arch, name, ops);
+        if (ops)
+                arch__associate_ins_ops(arch, name, ops);
         return ops;
 }
 
-static int s390__annotate_init(struct arch *arch)
+static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
         if (!arch->initialized) {
                 arch->initialized = true;
diff --git a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..72ecbb676370
--- /dev/null
+++ b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf
+#
+# Copyright IBM Corp. 2017, 2018
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+#
+
+SYSCALL_TBL=$1
+
+if ! test -r $SYSCALL_TBL; then
+        echo "Could not read input file" >&2
+        exit 1
+fi
+
+create_table()
+{
+        local max_nr nr abi sc discard
+
+        echo 'static const char *syscalltbl_s390_64[] = {'
+        while read nr abi sc discard; do
+                printf '\t[%d] = "%s",\n' $nr $sc
+                max_nr=$nr
+        done
+        echo '};'
+        echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr"
+}
+
+grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL     \
+        |sort -k1 -n                                    \
+        |create_table
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
new file mode 100644
index 000000000000..b38d48464368
--- /dev/null
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -0,0 +1,390 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# System call table for s390
+#
+# Format:
+#
+# <nr> <abi> <syscall> <entry-64bit> <compat-entry>
+#
+# where <abi> can be common, 64, or 32
+
+1    common     exit                    sys_exit                        sys_exit
+2    common     fork                    sys_fork                        sys_fork
+3    common     read                    sys_read                        compat_sys_s390_read
+4    common     write                   sys_write                       compat_sys_s390_write
+5    common     open                    sys_open                        compat_sys_open
+6    common     close                   sys_close                       sys_close
+7    common     restart_syscall         sys_restart_syscall             sys_restart_syscall
+8    common     creat                   sys_creat                       compat_sys_creat
+9    common     link                    sys_link                        compat_sys_link
+10   common     unlink                  sys_unlink                      compat_sys_unlink
+11   common     execve                  sys_execve                      compat_sys_execve
+12   common     chdir                   sys_chdir                       compat_sys_chdir
+13   32         time                    -                               compat_sys_time
+14   common     mknod                   sys_mknod                       compat_sys_mknod
+15   common     chmod                   sys_chmod                       compat_sys_chmod
+16   32         lchown                  -                               compat_sys_s390_lchown16
+19   common     lseek                   sys_lseek                       compat_sys_lseek
+20   common     getpid                  sys_getpid                      sys_getpid
+21   common     mount                   sys_mount                       compat_sys_mount
+22   common     umount                  sys_oldumount                   compat_sys_oldumount
+23   32         setuid                  -                               compat_sys_s390_setuid16
+24   32         getuid                  -                               compat_sys_s390_getuid16
+25   32         stime                   -                               compat_sys_stime
+26   common     ptrace                  sys_ptrace                      compat_sys_ptrace
+27   common     alarm                   sys_alarm                       sys_alarm
+29   common     pause                   sys_pause                       sys_pause
+30   common     utime                   sys_utime                       compat_sys_utime
+33   common     access                  sys_access                      compat_sys_access
+34   common     nice                    sys_nice                        sys_nice
+36   common     sync                    sys_sync                        sys_sync
+37   common     kill                    sys_kill                        sys_kill
+38   common     rename                  sys_rename                      compat_sys_rename
+39   common     mkdir                   sys_mkdir                       compat_sys_mkdir
+40   common     rmdir                   sys_rmdir                       compat_sys_rmdir
+41   common     dup                     sys_dup                         sys_dup
+42   common     pipe                    sys_pipe                        compat_sys_pipe
+43   common     times                   sys_times                       compat_sys_times
+45   common     brk                     sys_brk                         compat_sys_brk
+46   32         setgid                  -                               compat_sys_s390_setgid16
+47   32         getgid                  -                               compat_sys_s390_getgid16
+48   common     signal                  sys_signal                      compat_sys_signal
+49   32         geteuid                 -                               compat_sys_s390_geteuid16
+50   32         getegid                 -                               compat_sys_s390_getegid16
+51   common     acct                    sys_acct                        compat_sys_acct
+52   common     umount2                 sys_umount                      compat_sys_umount
+54   common     ioctl                   sys_ioctl                       compat_sys_ioctl
+55   common     fcntl                   sys_fcntl                       compat_sys_fcntl
+57   common     setpgid                 sys_setpgid                     sys_setpgid
+60   common     umask                   sys_umask                       sys_umask
+61   common     chroot                  sys_chroot                      compat_sys_chroot
+62   common     ustat                   sys_ustat                       compat_sys_ustat
+63   common     dup2                    sys_dup2                        sys_dup2
+64   common     getppid                 sys_getppid                     sys_getppid
+65   common     getpgrp                 sys_getpgrp                     sys_getpgrp
+66   common     setsid                  sys_setsid                      sys_setsid
+67   common     sigaction               sys_sigaction                   compat_sys_sigaction
+70   32         setreuid                -                               compat_sys_s390_setreuid16
+71   32         setregid                -                               compat_sys_s390_setregid16
+72   common     sigsuspend              sys_sigsuspend                  compat_sys_sigsuspend
+73   common     sigpending              sys_sigpending                  compat_sys_sigpending
+74   common     sethostname             sys_sethostname                 compat_sys_sethostname
+75   common     setrlimit               sys_setrlimit                   compat_sys_setrlimit
+76   32         getrlimit               -                               compat_sys_old_getrlimit
+77   common     getrusage               sys_getrusage                   compat_sys_getrusage
+78   common     gettimeofday            sys_gettimeofday                compat_sys_gettimeofday
+79   common     settimeofday            sys_settimeofday                compat_sys_settimeofday
+80   32         getgroups               -                               compat_sys_s390_getgroups16
+81   32         setgroups               -                               compat_sys_s390_setgroups16
+83   common     symlink                 sys_symlink                     compat_sys_symlink
+85   common     readlink                sys_readlink                    compat_sys_readlink
+86   common     uselib                  sys_uselib                      compat_sys_uselib
+87   common     swapon                  sys_swapon                      compat_sys_swapon
+88   common     reboot                  sys_reboot                      compat_sys_reboot
+89   common     readdir                 -                               compat_sys_old_readdir
+90   common     mmap                    sys_old_mmap                    compat_sys_s390_old_mmap
+91   common     munmap                  sys_munmap                      compat_sys_munmap
+92   common     truncate                sys_truncate                    compat_sys_truncate
+93   common     ftruncate               sys_ftruncate                   compat_sys_ftruncate
+94   common     fchmod                  sys_fchmod                      sys_fchmod
+95   32         fchown                  -                               compat_sys_s390_fchown16
+96   common     getpriority             sys_getpriority                 sys_getpriority
+97   common     setpriority             sys_setpriority                 sys_setpriority
+99   common     statfs                  sys_statfs                      compat_sys_statfs
+100  common     fstatfs                 sys_fstatfs                     compat_sys_fstatfs
+101  32         ioperm                  -                               -
+102  common     socketcall              sys_socketcall                  compat_sys_socketcall
+103  common     syslog                  sys_syslog                      compat_sys_syslog
+104  common     setitimer               sys_setitimer                   compat_sys_setitimer
+105  common     getitimer               sys_getitimer                   compat_sys_getitimer
+106  common     stat                    sys_newstat                     compat_sys_newstat
+107  common     lstat                   sys_newlstat                    compat_sys_newlstat
+108  common     fstat                   sys_newfstat                    compat_sys_newfstat
+110  common     lookup_dcookie          sys_lookup_dcookie              compat_sys_lookup_dcookie
+111  common     vhangup                 sys_vhangup                     sys_vhangup
+112  common     idle                    -                               -
+114  common     wait4                   sys_wait4                       compat_sys_wait4
+115  common     swapoff                 sys_swapoff                     compat_sys_swapoff
+116  common     sysinfo                 sys_sysinfo                     compat_sys_sysinfo
+117  common     ipc                     sys_s390_ipc                    compat_sys_s390_ipc
+118  common     fsync                   sys_fsync                       sys_fsync
+119  common     sigreturn               sys_sigreturn                   compat_sys_sigreturn
+120  common     clone                   sys_clone                       compat_sys_clone
+121  common     setdomainname           sys_setdomainname               compat_sys_setdomainname
+122  common     uname                   sys_newuname                    compat_sys_newuname
+124  common     adjtimex                sys_adjtimex                    compat_sys_adjtimex
+125  common     mprotect                sys_mprotect                    compat_sys_mprotect
+126  common     sigprocmask             sys_sigprocmask                 compat_sys_sigprocmask
+127  common     create_module           -                               -
+128  common     init_module             sys_init_module                 compat_sys_init_module
+129  common     delete_module           sys_delete_module               compat_sys_delete_module
+130  common     get_kernel_syms         -                               -
+131  common     quotactl                sys_quotactl                    compat_sys_quotactl
+132  common     getpgid                 sys_getpgid                     sys_getpgid
+133  common     fchdir                  sys_fchdir                      sys_fchdir
+134  common     bdflush                 sys_bdflush                     compat_sys_bdflush
+135  common     sysfs                   sys_sysfs                       compat_sys_sysfs
+136  common     personality             sys_s390_personality            sys_s390_personality
+137  common     afs_syscall             -                               -
+138  32         setfsuid                -                               compat_sys_s390_setfsuid16
+139  32         setfsgid                -                               compat_sys_s390_setfsgid16
+140  32         _llseek                 -                               compat_sys_llseek
+141  common     getdents                sys_getdents                    compat_sys_getdents
+142  32         _newselect              -                               compat_sys_select
+142  64         select                  sys_select                      -
+143  common     flock                   sys_flock                       sys_flock
+144  common     msync                   sys_msync                       compat_sys_msync
+145  common     readv                   sys_readv                       compat_sys_readv
+146  common     writev                  sys_writev                      compat_sys_writev
+147  common     getsid                  sys_getsid                      sys_getsid
+148  common     fdatasync               sys_fdatasync                   sys_fdatasync
+149  common     _sysctl                 sys_sysctl                      compat_sys_sysctl
+150  common     mlock                   sys_mlock                       compat_sys_mlock
+151  common     munlock                 sys_munlock                     compat_sys_munlock
+152  common     mlockall                sys_mlockall                    sys_mlockall
+153  common     munlockall              sys_munlockall                  sys_munlockall
+154  common     sched_setparam          sys_sched_setparam              compat_sys_sched_setparam
+155  common     sched_getparam          sys_sched_getparam              compat_sys_sched_getparam
+156  common     sched_setscheduler      sys_sched_setscheduler          compat_sys_sched_setscheduler
+157  common     sched_getscheduler      sys_sched_getscheduler          sys_sched_getscheduler
+158  common     sched_yield             sys_sched_yield                 sys_sched_yield
+159  common     sched_get_priority_max  sys_sched_get_priority_max      sys_sched_get_priority_max
+160  common     sched_get_priority_min  sys_sched_get_priority_min      sys_sched_get_priority_min
+161  common     sched_rr_get_interval   sys_sched_rr_get_interval       compat_sys_sched_rr_get_interval
+162  common     nanosleep               sys_nanosleep                   compat_sys_nanosleep
+163  common     mremap                  sys_mremap                      compat_sys_mremap
+164  32         setresuid               -                               compat_sys_s390_setresuid16
+165  32         getresuid               -                               compat_sys_s390_getresuid16
+167  common     query_module            -                               -
+168  common     poll                    sys_poll                        compat_sys_poll
+169  common     nfsservctl              -                               -
+170  32         setresgid               -                               compat_sys_s390_setresgid16
+171  32         getresgid               -                               compat_sys_s390_getresgid16
+172  common     prctl                   sys_prctl                       compat_sys_prctl
+173  common     rt_sigreturn            sys_rt_sigreturn                compat_sys_rt_sigreturn
+174  common     rt_sigaction            sys_rt_sigaction                compat_sys_rt_sigaction
+175  common     rt_sigprocmask          sys_rt_sigprocmask              compat_sys_rt_sigprocmask
+176  common     rt_sigpending           sys_rt_sigpending               compat_sys_rt_sigpending
+177  common     rt_sigtimedwait         sys_rt_sigtimedwait             compat_sys_rt_sigtimedwait
+178  common     rt_sigqueueinfo         sys_rt_sigqueueinfo             compat_sys_rt_sigqueueinfo
+179  common     rt_sigsuspend           sys_rt_sigsuspend               compat_sys_rt_sigsuspend
+180  common     pread64                 sys_pread64                     compat_sys_s390_pread64
+181  common     pwrite64                sys_pwrite64                    compat_sys_s390_pwrite64
+182  32         chown                   -                               compat_sys_s390_chown16
+183  common     getcwd                  sys_getcwd                      compat_sys_getcwd
+184  common     capget                  sys_capget                      compat_sys_capget
+185  common     capset                  sys_capset                      compat_sys_capset
+186  common     sigaltstack             sys_sigaltstack                 compat_sys_sigaltstack
+187  common     sendfile                sys_sendfile64                  compat_sys_sendfile
+188  common     getpmsg                 -                               -
+189  common     putpmsg                 -                               -
+190  common     vfork                   sys_vfork                       sys_vfork
+191  32         ugetrlimit              -                               compat_sys_getrlimit
+191  64         getrlimit               sys_getrlimit                   -
+192  32         mmap2                   -                               compat_sys_s390_mmap2
+193  32         truncate64              -                               compat_sys_s390_truncate64
+194  32         ftruncate64             -                               compat_sys_s390_ftruncate64
+195  32         stat64                  -                               compat_sys_s390_stat64
+196  32         lstat64                 -                               compat_sys_s390_lstat64
+197  32         fstat64                 -                               compat_sys_s390_fstat64
+198  32         lchown32                -                               compat_sys_lchown
+198  64         lchown                  sys_lchown                      -
+199  32         getuid32                -                               sys_getuid
+199  64         getuid                  sys_getuid                      -
+200  32         getgid32                -                               sys_getgid
+200  64         getgid                  sys_getgid                      -
+201  32         geteuid32               -                               sys_geteuid
+201  64         geteuid                 sys_geteuid                     -
+202  32         getegid32               -                               sys_getegid
+202  64         getegid                 sys_getegid                     -
+203  32         setreuid32              -                               sys_setreuid
+203  64         setreuid                sys_setreuid                    -
+204  32         setregid32              -                               sys_setregid
+204  64         setregid                sys_setregid                    -
+205  32         getgroups32             -                               compat_sys_getgroups
+205  64         getgroups               sys_getgroups                   -
+206  32         setgroups32             -                               compat_sys_setgroups
+206  64         setgroups               sys_setgroups                   -
+207  32         fchown32                -                               sys_fchown
+207  64         fchown                  sys_fchown                      -
+208  32         setresuid32             -                               sys_setresuid
+208  64         setresuid               sys_setresuid                   -
+209  32         getresuid32             -                               compat_sys_getresuid
+209  64         getresuid               sys_getresuid                   -
+210  32         setresgid32             -                               sys_setresgid
+210  64         setresgid               sys_setresgid                   -
+211  32         getresgid32             -                               compat_sys_getresgid
+211  64         getresgid               sys_getresgid                   -
+212  32         chown32                 -                               compat_sys_chown
+212  64         chown                   sys_chown                       -
+213  32         setuid32                -                               sys_setuid
+213  64         setuid                  sys_setuid                      -
+214  32         setgid32                -                               sys_setgid
+214  64         setgid                  sys_setgid                      -
+215  32         setfsuid32              -                               sys_setfsuid
+215  64         setfsuid                sys_setfsuid                    -
+216  32         setfsgid32              -                               sys_setfsgid
+216  64         setfsgid                sys_setfsgid                    -
+217  common     pivot_root              sys_pivot_root                  compat_sys_pivot_root
+218  common     mincore                 sys_mincore                     compat_sys_mincore
+219  common     madvise                 sys_madvise                     compat_sys_madvise
+220  common     getdents64              sys_getdents64                  compat_sys_getdents64
+221  32         fcntl64                 -                               compat_sys_fcntl64
+222  common     readahead               sys_readahead                   compat_sys_s390_readahead
+223  32         sendfile64              -                               compat_sys_sendfile64
+224  common     setxattr                sys_setxattr                    compat_sys_setxattr
+225  common     lsetxattr               sys_lsetxattr                   compat_sys_lsetxattr
+226  common     fsetxattr               sys_fsetxattr                   compat_sys_fsetxattr
+227  common     getxattr                sys_getxattr                    compat_sys_getxattr
+228  common     lgetxattr               sys_lgetxattr                   compat_sys_lgetxattr
+229  common     fgetxattr               sys_fgetxattr                   compat_sys_fgetxattr
+230  common     listxattr               sys_listxattr                   compat_sys_listxattr
+231  common     llistxattr              sys_llistxattr                  compat_sys_llistxattr
+232  common     flistxattr              sys_flistxattr                  compat_sys_flistxattr
+233  common     removexattr             sys_removexattr                 compat_sys_removexattr
+234  common     lremovexattr            sys_lremovexattr                compat_sys_lremovexattr
+235  common     fremovexattr            sys_fremovexattr                compat_sys_fremovexattr
+236  common     gettid                  sys_gettid                      sys_gettid
+237  common     tkill                   sys_tkill                       sys_tkill
+238  common     futex                   sys_futex                       compat_sys_futex
+239  common     sched_setaffinity       sys_sched_setaffinity           compat_sys_sched_setaffinity
+240  common     sched_getaffinity       sys_sched_getaffinity           compat_sys_sched_getaffinity
+241  common     tgkill                  sys_tgkill                      sys_tgkill
+243  common     io_setup                sys_io_setup                    compat_sys_io_setup
+244  common     io_destroy              sys_io_destroy                  compat_sys_io_destroy
+245  common     io_getevents            sys_io_getevents                compat_sys_io_getevents
+246  common     io_submit               sys_io_submit                   compat_sys_io_submit
+247  common     io_cancel               sys_io_cancel                   compat_sys_io_cancel
+248  common     exit_group              sys_exit_group                  sys_exit_group
+249  common     epoll_create            sys_epoll_create                sys_epoll_create
+250  common     epoll_ctl               sys_epoll_ctl                   compat_sys_epoll_ctl
+251  common     epoll_wait              sys_epoll_wait                  compat_sys_epoll_wait
+252  common     set_tid_address         sys_set_tid_address             compat_sys_set_tid_address
+253  common     fadvise64               sys_fadvise64_64                compat_sys_s390_fadvise64
+254  common     timer_create            sys_timer_create                compat_sys_timer_create
+255  common     timer_settime           sys_timer_settime               compat_sys_timer_settime
+256  common     timer_gettime           sys_timer_gettime               compat_sys_timer_gettime
+257  common     timer_getoverrun        sys_timer_getoverrun            sys_timer_getoverrun
+258  common     timer_delete            sys_timer_delete                sys_timer_delete
+259  common     clock_settime           sys_clock_settime               compat_sys_clock_settime
+260  common     clock_gettime           sys_clock_gettime               compat_sys_clock_gettime
+261  common     clock_getres            sys_clock_getres                compat_sys_clock_getres
+262  common     clock_nanosleep         sys_clock_nanosleep             compat_sys_clock_nanosleep
+264  32         fadvise64_64            -                               compat_sys_s390_fadvise64_64
+265  common     statfs64                sys_statfs64                    compat_sys_statfs64
+266  common     fstatfs64               sys_fstatfs64                   compat_sys_fstatfs64
+267  common     remap_file_pages        sys_remap_file_pages            compat_sys_remap_file_pages
+268  common     mbind                   sys_mbind                       compat_sys_mbind
+269  common     get_mempolicy           sys_get_mempolicy               compat_sys_get_mempolicy
+270  common     set_mempolicy           sys_set_mempolicy               compat_sys_set_mempolicy
+271  common     mq_open                 sys_mq_open                     compat_sys_mq_open
+272  common     mq_unlink               sys_mq_unlink                   compat_sys_mq_unlink
+273  common     mq_timedsend            sys_mq_timedsend                compat_sys_mq_timedsend
+274  common     mq_timedreceive         sys_mq_timedreceive             compat_sys_mq_timedreceive
+275  common     mq_notify               sys_mq_notify                   compat_sys_mq_notify
+276  common     mq_getsetattr           sys_mq_getsetattr               compat_sys_mq_getsetattr
+277  common     kexec_load              sys_kexec_load                  compat_sys_kexec_load
+278  common     add_key                 sys_add_key                     compat_sys_add_key
+279  common     request_key             sys_request_key                 compat_sys_request_key
+280  common     keyctl                  sys_keyctl                      compat_sys_keyctl
+281  common     waitid                  sys_waitid                      compat_sys_waitid
+282  common     ioprio_set              sys_ioprio_set                  sys_ioprio_set
+283  common     ioprio_get              sys_ioprio_get                  sys_ioprio_get
+284  common     inotify_init            sys_inotify_init                sys_inotify_init
+285  common     inotify_add_watch       sys_inotify_add_watch           compat_sys_inotify_add_watch
+286  common     inotify_rm_watch        sys_inotify_rm_watch            sys_inotify_rm_watch
+287  common     migrate_pages           sys_migrate_pages               compat_sys_migrate_pages
+288  common     openat                  sys_openat                      compat_sys_openat
+289  common     mkdirat                 sys_mkdirat                     compat_sys_mkdirat
+290  common     mknodat                 sys_mknodat                     compat_sys_mknodat
+291  common     fchownat                sys_fchownat                    compat_sys_fchownat
+292  common     futimesat               sys_futimesat                   compat_sys_futimesat
+293  32         fstatat64               -                               compat_sys_s390_fstatat64
+293  64         newfstatat              sys_newfstatat                  -
+294  common     unlinkat                sys_unlinkat                    compat_sys_unlinkat
+295  common     renameat                sys_renameat                    compat_sys_renameat
+296  common     linkat                  sys_linkat                      compat_sys_linkat
+297  common     symlinkat               sys_symlinkat                   compat_sys_symlinkat
+298  common     readlinkat              sys_readlinkat                  compat_sys_readlinkat
+299  common     fchmodat                sys_fchmodat                    compat_sys_fchmodat
+300  common     faccessat               sys_faccessat                   compat_sys_faccessat
+301  common     pselect6                sys_pselect6                    compat_sys_pselect6
+302  common     ppoll                   sys_ppoll                       compat_sys_ppoll
+303  common     unshare                 sys_unshare                     compat_sys_unshare
+304  common     set_robust_list         sys_set_robust_list             compat_sys_set_robust_list
+305  common     get_robust_list         sys_get_robust_list             compat_sys_get_robust_list
+306  common     splice                  sys_splice                      compat_sys_splice
+307  common     sync_file_range         sys_sync_file_range             compat_sys_s390_sync_file_range
+308  common     tee                     sys_tee                         compat_sys_tee
+309  common     vmsplice                sys_vmsplice                    compat_sys_vmsplice
+310  common     move_pages              sys_move_pages                  compat_sys_move_pages
+311  common     getcpu                  sys_getcpu                      compat_sys_getcpu
+312  common     epoll_pwait             sys_epoll_pwait                 compat_sys_epoll_pwait
+313  common     utimes                  sys_utimes                      compat_sys_utimes
+314  common     fallocate               sys_fallocate                   compat_sys_s390_fallocate
+315  common     utimensat               sys_utimensat                   compat_sys_utimensat
+316  common     signalfd                sys_signalfd                    compat_sys_signalfd
+317  common     timerfd                 -                               -
+318  common     eventfd                 sys_eventfd                     sys_eventfd
+319  common     timerfd_create          sys_timerfd_create              sys_timerfd_create
+320  common     timerfd_settime         sys_timerfd_settime             compat_sys_timerfd_settime
+321  common     timerfd_gettime         sys_timerfd_gettime             compat_sys_timerfd_gettime
+322  common     signalfd4               sys_signalfd4                   compat_sys_signalfd4
+323  common     eventfd2                sys_eventfd2                    sys_eventfd2
+324  common     inotify_init1           sys_inotify_init1               sys_inotify_init1
+325  common     pipe2                   sys_pipe2                       compat_sys_pipe2
+326  common     dup3                    sys_dup3                        sys_dup3
+327  common     epoll_create1           sys_epoll_create1               sys_epoll_create1
+328  common     preadv                  sys_preadv                      compat_sys_preadv
+329  common     pwritev                 sys_pwritev                     compat_sys_pwritev
+330  common     rt_tgsigqueueinfo       sys_rt_tgsigqueueinfo           compat_sys_rt_tgsigqueueinfo
+331  common     perf_event_open         sys_perf_event_open             compat_sys_perf_event_open
+332  common     fanotify_init           sys_fanotify_init               sys_fanotify_init
+333  common     fanotify_mark           sys_fanotify_mark               compat_sys_fanotify_mark
+334  common     prlimit64               sys_prlimit64                   compat_sys_prlimit64
+335  common     name_to_handle_at       sys_name_to_handle_at           compat_sys_name_to_handle_at
+336  common     open_by_handle_at       sys_open_by_handle_at           compat_sys_open_by_handle_at
+337  common     clock_adjtime           sys_clock_adjtime               compat_sys_clock_adjtime
+338  common     syncfs                  sys_syncfs                      sys_syncfs
+339  common     setns                   sys_setns                       sys_setns
+340  common     process_vm_readv        sys_process_vm_readv            compat_sys_process_vm_readv
+341  common     process_vm_writev       sys_process_vm_writev           compat_sys_process_vm_writev
+342  common     s390_runtime_instr      sys_s390_runtime_instr          sys_s390_runtime_instr
+343  common     kcmp                    sys_kcmp                        compat_sys_kcmp
+344  common     finit_module            sys_finit_module                compat_sys_finit_module
+345  common     sched_setattr           sys_sched_setattr               compat_sys_sched_setattr
+346  common     sched_getattr           sys_sched_getattr               compat_sys_sched_getattr
+347  common     renameat2               sys_renameat2                   compat_sys_renameat2
+348  common     seccomp                 sys_seccomp                     compat_sys_seccomp
+349  common     getrandom               sys_getrandom                   compat_sys_getrandom
+350  common     memfd_create            sys_memfd_create                compat_sys_memfd_create
+351  common     bpf                     sys_bpf                         compat_sys_bpf
+352  common     s390_pci_mmio_write     sys_s390_pci_mmio_write         compat_sys_s390_pci_mmio_write
+353  common     s390_pci_mmio_read      sys_s390_pci_mmio_read          compat_sys_s390_pci_mmio_read
+354  common     execveat                sys_execveat                    compat_sys_execveat
+355  common     userfaultfd             sys_userfaultfd                 sys_userfaultfd
+356  common     membarrier              sys_membarrier                  sys_membarrier
+357  common     recvmmsg                sys_recvmmsg                    compat_sys_recvmmsg
+358  common     sendmmsg                sys_sendmmsg                    compat_sys_sendmmsg
+359  common     socket                  sys_socket                      sys_socket
+360  common     socketpair              sys_socketpair                  compat_sys_socketpair
+361  common     bind                    sys_bind                        compat_sys_bind
+362  common     connect                 sys_connect                     compat_sys_connect
+363  common     listen                  sys_listen                      sys_listen
+364  common     accept4                 sys_accept4                     compat_sys_accept4
+365  common     getsockopt              sys_getsockopt                  compat_sys_getsockopt
+366  common     setsockopt              sys_setsockopt                  compat_sys_setsockopt
+367  common     getsockname             sys_getsockname                 compat_sys_getsockname
+368  common     getpeername             sys_getpeername                 compat_sys_getpeername
+369  common     sendto                  sys_sendto                      compat_sys_sendto
+370  common     sendmsg                 sys_sendmsg                     compat_sys_sendmsg
+371  common     recvfrom                sys_recvfrom                    compat_sys_recvfrom
+372  common     recvmsg                 sys_recvmsg                     compat_sys_recvmsg
+373  common     shutdown                sys_shutdown                    sys_shutdown
+374  common     mlock2                  sys_mlock2                      compat_sys_mlock2
+375  common     copy_file_range         sys_copy_file_range             compat_sys_copy_file_range
+376  common     preadv2                 sys_preadv2                     compat_sys_preadv2
+377  common     pwritev2                sys_pwritev2                    compat_sys_pwritev2
+378  common     s390_guarded_storage    sys_s390_guarded_storage        compat_sys_s390_guarded_storage
+379  common     statx                   sys_statx                       compat_sys_statx
+380  common     s390_sthyi              sys_s390_sthyi                  compat_sys_s390_sthyi
diff --git a/tools/perf/arch/s390/include/dwarf-regs-table.h b/tools/perf/arch/s390/include/dwarf-regs-table.h
index 792d4c277225..671553525f41 100644
--- a/tools/perf/arch/s390/include/dwarf-regs-table.h
+++ b/tools/perf/arch/s390/include/dwarf-regs-table.h
@@ -1,9 +1,72 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifdef DEFINE_DWARF_REGSTR_TABLE
-/* This is included in perf/util/dwarf-regs.c */
+#ifndef S390_DWARF_REGS_TABLE_H
+#define S390_DWARF_REGS_TABLE_H
 
-static const char * const s390_regstr_tbl[] = {
+#define REG_DWARFNUM_NAME(reg, idx)     [idx] = "%" #reg
+
+/*
+ * For reference, see DWARF register mapping:
+ * http://refspecs.linuxfoundation.org/ELF/zSeries/lzsabi0_s390/x1542.html
+ */
+static const char * const s390_dwarf_regs[] = {
         "%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
         "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+        REG_DWARFNUM_NAME(f0, 16),
+        REG_DWARFNUM_NAME(f1, 20),
+        REG_DWARFNUM_NAME(f2, 17),
+        REG_DWARFNUM_NAME(f3, 21),
+        REG_DWARFNUM_NAME(f4, 18),
+        REG_DWARFNUM_NAME(f5, 22),
+        REG_DWARFNUM_NAME(f6, 19),
+        REG_DWARFNUM_NAME(f7, 23),
+        REG_DWARFNUM_NAME(f8, 24),
+        REG_DWARFNUM_NAME(f9, 28),
+        REG_DWARFNUM_NAME(f10, 25),
+        REG_DWARFNUM_NAME(f11, 29),
+        REG_DWARFNUM_NAME(f12, 26),
+        REG_DWARFNUM_NAME(f13, 30),
+        REG_DWARFNUM_NAME(f14, 27),
+        REG_DWARFNUM_NAME(f15, 31),
+        REG_DWARFNUM_NAME(c0, 32),
+        REG_DWARFNUM_NAME(c1, 33),
+        REG_DWARFNUM_NAME(c2, 34),
+        REG_DWARFNUM_NAME(c3, 35),
+        REG_DWARFNUM_NAME(c4, 36),
+        REG_DWARFNUM_NAME(c5, 37),
+        REG_DWARFNUM_NAME(c6, 38),
+        REG_DWARFNUM_NAME(c7, 39),
+        REG_DWARFNUM_NAME(c8, 40),
+        REG_DWARFNUM_NAME(c9, 41),
+        REG_DWARFNUM_NAME(c10, 42),
+        REG_DWARFNUM_NAME(c11, 43),
+        REG_DWARFNUM_NAME(c12, 44),
+        REG_DWARFNUM_NAME(c13, 45),
+        REG_DWARFNUM_NAME(c14, 46),
+        REG_DWARFNUM_NAME(c15, 47),
+        REG_DWARFNUM_NAME(a0, 48),
+        REG_DWARFNUM_NAME(a1, 49),
+        REG_DWARFNUM_NAME(a2, 50),
+        REG_DWARFNUM_NAME(a3, 51),
+        REG_DWARFNUM_NAME(a4, 52),
+        REG_DWARFNUM_NAME(a5, 53),
+        REG_DWARFNUM_NAME(a6, 54),
+        REG_DWARFNUM_NAME(a7, 55),
+        REG_DWARFNUM_NAME(a8, 56),
+        REG_DWARFNUM_NAME(a9, 57),
+        REG_DWARFNUM_NAME(a10, 58),
+        REG_DWARFNUM_NAME(a11, 59),
+        REG_DWARFNUM_NAME(a12, 60),
+        REG_DWARFNUM_NAME(a13, 61),
+        REG_DWARFNUM_NAME(a14, 62),
+        REG_DWARFNUM_NAME(a15, 63),
+        REG_DWARFNUM_NAME(pswm, 64),
+        REG_DWARFNUM_NAME(pswa, 65),
 };
-#endif
+
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+#define s390_regstr_tbl s390_dwarf_regs
+
+#endif  /* DEFINE_DWARF_REGSTR_TABLE */
+#endif  /* S390_DWARF_REGS_TABLE_H */
diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
new file mode 100644
index 000000000000..bcfbaed78cc2
--- /dev/null
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -0,0 +1,95 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MASK ((1ULL << PERF_REG_S390_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_S390_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
+
+#define PERF_REG_IP PERF_REG_S390_PC
+#define PERF_REG_SP PERF_REG_S390_R15
+
+static inline const char *perf_reg_name(int id)
+{
+        switch (id) {
+        case PERF_REG_S390_R0:
+                return "R0";
+        case PERF_REG_S390_R1:
+                return "R1";
+        case PERF_REG_S390_R2:
+                return "R2";
+        case PERF_REG_S390_R3:
+                return "R3";
+        case PERF_REG_S390_R4:
+                return "R4";
+        case PERF_REG_S390_R5:
+                return "R5";
+        case PERF_REG_S390_R6:
+                return "R6";
+        case PERF_REG_S390_R7:
+                return "R7";
+        case PERF_REG_S390_R8:
+                return "R8";
+        case PERF_REG_S390_R9:
+                return "R9";
+        case PERF_REG_S390_R10:
+                return "R10";
+        case PERF_REG_S390_R11:
+                return "R11";
+        case PERF_REG_S390_R12:
+                return "R12";
+        case PERF_REG_S390_R13:
+                return "R13";
+        case PERF_REG_S390_R14:
+                return "R14";
+        case PERF_REG_S390_R15:
+                return "R15";
+        case PERF_REG_S390_FP0:
+                return "FP0";
+        case PERF_REG_S390_FP1:
+                return "FP1";
+        case PERF_REG_S390_FP2:
+                return "FP2";
+        case PERF_REG_S390_FP3:
+                return "FP3";
+        case PERF_REG_S390_FP4:
+                return "FP4";
+        case PERF_REG_S390_FP5:
+                return "FP5";
+        case PERF_REG_S390_FP6:
+                return "FP6";
+        case PERF_REG_S390_FP7:
+                return "FP7";
+        case PERF_REG_S390_FP8:
+                return "FP8";
+        case PERF_REG_S390_FP9:
+                return "FP9";
+        case PERF_REG_S390_FP10:
+                return "FP10";
+        case PERF_REG_S390_FP11:
+                return "FP11";
+        case PERF_REG_S390_FP12:
+                return "FP12";
+        case PERF_REG_S390_FP13:
+                return "FP13";
+        case PERF_REG_S390_FP14:
+                return "FP14";
+        case PERF_REG_S390_FP15:
+                return "FP15";
+        case PERF_REG_S390_MASK:
+                return "MASK";
+        case PERF_REG_S390_PC:
+                return "PC";
+        default:
+                return NULL;
+        }
+
+        return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 5bd7b9260cc0..4a233683c684 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,5 +2,8 @@ libperf-y += header.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
+libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-y += machine.o
+
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
new file mode 100644
index 000000000000..6cb48e4cffd9
--- /dev/null
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -0,0 +1,118 @@
+#include <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../../util/evlist.h"
+#include "../../util/auxtrace.h"
+#include "../../util/evsel.h"
+
+#define PERF_EVENT_CPUM_SF              0xB0000 /* Event: Basic-sampling */
+#define PERF_EVENT_CPUM_SF_DIAG         0xBD000 /* Event: Combined-sampling */
+#define DEFAULT_AUX_PAGES               128
+#define DEFAULT_FREQ                    4000
+
+static void cpumsf_free(struct auxtrace_record *itr)
+{
+        free(itr);
+}
+
+static size_t cpumsf_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+                                    struct perf_evlist *evlist __maybe_unused)
+{
+        return 0;
+}
+
+static int
+cpumsf_info_fill(struct auxtrace_record *itr __maybe_unused,
+                 struct perf_session *session __maybe_unused,
+                 struct auxtrace_info_event *auxtrace_info __maybe_unused,
+                 size_t priv_size __maybe_unused)
+{
+        return 0;
+}
+
+static unsigned long
+cpumsf_reference(struct auxtrace_record *itr __maybe_unused)
+{
+        return 0;
+}
+
+static int
+cpumsf_recording_options(struct auxtrace_record *ar __maybe_unused,
+                         struct perf_evlist *evlist __maybe_unused,
+                         struct record_opts *opts)
+{
+        unsigned int factor = 1;
+        unsigned int pages;
+
+        opts->full_auxtrace = true;
+
+        /*
+         * The AUX buffer size should be set properly to avoid
+         * overflow of samples if it is not set explicitly.
+         * DEFAULT_AUX_PAGES is an proper size when sampling frequency
+         * is DEFAULT_FREQ. It is expected to hold about 1/2 second
+         * of sampling data. The size used for AUX buffer will scale
+         * according to the specified frequency and DEFAULT_FREQ.
+         */
+        if (!opts->auxtrace_mmap_pages) {
+                if (opts->user_freq != UINT_MAX)
+                        factor = (opts->user_freq + DEFAULT_FREQ
+                                  - 1) / DEFAULT_FREQ;
+                pages = DEFAULT_AUX_PAGES * factor;
+                opts->auxtrace_mmap_pages = roundup_pow_of_two(pages);
+        }
+
+        return 0;
+}
+
+static int
+cpumsf_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+                              struct record_opts *opts __maybe_unused,
+                              const char *str __maybe_unused)
+{
+        return 0;
+}
+
+/*
+ * auxtrace_record__init is called when perf record
+ * check if the event really need auxtrace
+ */
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+                                              int *err)
+{
+        struct auxtrace_record *aux;
+        struct perf_evsel *pos;
+        int diagnose = 0;
+
+        if (evlist->nr_entries == 0)
+                return NULL;
+
+        evlist__for_each_entry(evlist, pos) {
+                if (pos->attr.config == PERF_EVENT_CPUM_SF_DIAG) {
+                        diagnose = 1;
+                        break;
+                }
+        }
+
+        if (!diagnose)
+                return NULL;
+
+        /* sampling in diagnose mode. alloc aux buffer */
+        aux = zalloc(sizeof(*aux));
+        if (aux == NULL) {
+                *err = -ENOMEM;
+                return NULL;
+        }
+
+        aux->parse_snapshot_options = cpumsf_parse_snapshot_options;
+        aux->recording_options = cpumsf_recording_options;
+        aux->info_priv_size = cpumsf_info_priv_size;
+        aux->info_fill = cpumsf_info_fill;
+        aux->free = cpumsf_free;
+        aux->reference = cpumsf_reference;
+
+        return aux;
+}
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
index 0dff5b2ed1e5..a8ace5cc6301 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -2,22 +2,43 @@
 /*
  * Mapping of DWARF debug register numbers into register names.
  *
- *    Copyright IBM Corp. 2010
- *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ * Copyright IBM Corp. 2010, 2017
+ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *            Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *
  */
 
+#include <errno.h>
 #include <stddef.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+#include <asm/ptrace.h>
+#include <string.h>
 #include <dwarf-regs.h>
-
-#define NUM_GPRS 16
-
-static const char *gpr_names[NUM_GPRS] = {
-        "%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
-        "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
-};
+#include "dwarf-regs-table.h"
 
 const char *get_arch_regstr(unsigned int n)
 {
-        return (n >= NUM_GPRS) ? NULL : gpr_names[n];
+        return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
+}
+
+/*
+ * Convert the register name into an offset to struct pt_regs (kernel).
+ * This is required by the BPF prologue generator.  The BPF
+ * program is called in the BPF overflow handler in the perf
+ * core.
+ */
+int regs_query_register_offset(const char *name)
+{
+        unsigned long gpr;
+
+        if (!name || strncmp(name, "%r", 2))
+                return -EINVAL;
+
+        errno = 0;
+        gpr = strtoul(name + 2, NULL, 10);
+        if (errno || gpr >= 16)
+                return -EINVAL;
+
+        return offsetof(user_pt_regs, gprs) + 8 * gpr;
 }
diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c
new file mode 100644
index 000000000000..387c698cdd1b
--- /dev/null
+++ b/tools/perf/arch/s390/util/unwind-libdw.c
@@ -0,0 +1,63 @@
+#include <linux/kernel.h>
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+#include "dwarf-regs-table.h"
+
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+        struct unwind_info *ui = arg;
+        struct regs_dump *user_regs = &ui->sample->user_regs;
+        Dwarf_Word dwarf_regs[ARRAY_SIZE(s390_dwarf_regs)];
+
+#define REG(r) ({                                               \
+        Dwarf_Word val = 0;                                     \
+        perf_reg_value(&val, user_regs, PERF_REG_S390_##r);     \
+        val;                                                    \
+})
+        /*
+         * For DWARF register mapping details,
+         * see also perf/arch/s390/include/dwarf-regs-table.h
+         */
+        dwarf_regs[0]  = REG(R0);
+        dwarf_regs[1]  = REG(R1);
+        dwarf_regs[2]  = REG(R2);
+        dwarf_regs[3]  = REG(R3);
+        dwarf_regs[4]  = REG(R4);
+        dwarf_regs[5]  = REG(R5);
+        dwarf_regs[6]  = REG(R6);
+        dwarf_regs[7]  = REG(R7);
+        dwarf_regs[8]  = REG(R8);
+        dwarf_regs[9]  = REG(R9);
+        dwarf_regs[10] = REG(R10);
+        dwarf_regs[11] = REG(R11);
+        dwarf_regs[12] = REG(R12);
+        dwarf_regs[13] = REG(R13);
+        dwarf_regs[14] = REG(R14);
+        dwarf_regs[15] = REG(R15);
+
+        dwarf_regs[16] = REG(FP0);
+        dwarf_regs[17] = REG(FP2);
+        dwarf_regs[18] = REG(FP4);
+        dwarf_regs[19] = REG(FP6);
+        dwarf_regs[20] = REG(FP1);
+        dwarf_regs[21] = REG(FP3);
+        dwarf_regs[22] = REG(FP5);
+        dwarf_regs[23] = REG(FP7);
+        dwarf_regs[24] = REG(FP8);
+        dwarf_regs[25] = REG(FP10);
+        dwarf_regs[26] = REG(FP12);
+        dwarf_regs[27] = REG(FP14);
+        dwarf_regs[28] = REG(FP9);
+        dwarf_regs[29] = REG(FP11);
+        dwarf_regs[30] = REG(FP13);
+        dwarf_regs[31] = REG(FP15);
+
+        dwarf_regs[64] = REG(MASK);
+        dwarf_regs[65] = REG(PC);
+
+        dwfl_thread_state_register_pc(thread, dwarf_regs[65]);
+        return dwfl_thread_state_registers(thread, 0, 32, dwarf_regs);
+}
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 4adfb4ce2864..5bd1ba8c0282 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -123,3 +123,17 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid)
 
         return -1;
 }
+
+static int x86__annotate_init(struct arch *arch, char *cpuid)
+{
+        int err = 0;
+
+        if (arch->initialized)
+                return 0;
+
+        if (cpuid)
+                err = x86__cpuid_parse(arch, cpuid);
+
+        arch->initialized = true;
+        return err;
+}
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 9834fdc7c59e..c1bd979b957b 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -9,7 +9,6 @@ struct test;
 int test__rdpmc(struct test *test __maybe_unused, int subtest);
 int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
-int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index cbb7e978166b..8e2c5a38c3b9 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -5,4 +5,3 @@ libperf-y += arch-tests.o
 libperf-y += rdpmc.o
 libperf-y += perf-time-to-tsc.o
 libperf-$(CONFIG_AUXTRACE) += insn-x86.o
-libperf-y += intel-cqm.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index 34a078136a47..cc1802ff5410 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -25,10 +25,6 @@ struct test arch_tests[] = {
         },
 #endif
         {
-                .desc = "Intel cqm nmi context read",
-                .func = test__intel_cqm_count_nmi_context,
-        },
-        {
                 .func = NULL,
         },
 
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index b59678e8c1e2..06abe8108b33 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -84,7 +84,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
         CHECK__(perf_evlist__open(evlist));
 
-        CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+        CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
         pc = evlist->mmap[0].base;
         ret = perf_read_tsc_conversion(pc, &tc);
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 33027c5e6f92..fb0d71afee8b 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -66,11 +66,11 @@ get_cpuid(char *buffer, size_t sz)
 }
 
 char *
-get_cpuid_str(void)
+get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
         char *buf = malloc(128);
 
-        if (__get_cpuid(buf, 128, "%s-%u-%X$") < 0) {
+        if (buf && __get_cpuid(buf, 128, "%s-%u-%X$") < 0) {
                 free(buf);
                 return NULL;
         }
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 9c917f80c906..05920e3edf7a 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#ifndef REMOTE_UNWIND_LIBUNWIND
 #include <errno.h>
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 58ae6ed8f38b..9aa3a674829b 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -24,9 +24,9 @@
 #include <subcmd/parse-options.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
-#include <sys/time.h>
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 10;
@@ -118,11 +118,12 @@ static void print_summary(void)
 int bench_futex_hash(int argc, const char **argv)
 {
         int ret = 0;
-        cpu_set_t cpu;
+        cpu_set_t cpuset;
         struct sigaction act;
-        unsigned int i, ncpus;
+        unsigned int i;
         pthread_attr_t thread_attr;
         struct worker *worker = NULL;
+        struct cpu_map *cpu;
 
         argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
         if (argc) {
@@ -130,14 +131,16 @@ int bench_futex_hash(int argc, const char **argv)
                 exit(EXIT_FAILURE);
         }
 
-        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+        cpu = cpu_map__new(NULL);
+        if (!cpu)
+                goto errmem;
 
         sigfillset(&act.sa_mask);
         act.sa_sigaction = toggle_done;
         sigaction(SIGINT, &act, NULL);
 
         if (!nthreads) /* default to the number of CPUs */
-                nthreads = ncpus;
+                nthreads = cpu->nr;
 
         worker = calloc(nthreads, sizeof(*worker));
         if (!worker)
@@ -163,10 +166,10 @@ int bench_futex_hash(int argc, const char **argv)
                 if (!worker[i].futex)
                         goto errmem;
 
-                CPU_ZERO(&cpu);
-                CPU_SET(i % ncpus, &cpu);
+                CPU_ZERO(&cpuset);
+                CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-                ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
+                ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
                 if (ret)
                         err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
@@ -217,6 +220,7 @@ int bench_futex_hash(int argc, const char **argv)
         print_summary();
 
         free(worker);
+        free(cpu);
         return ret;
 errmem:
         err(EXIT_FAILURE, "calloc");
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 08653ae8a8c4..8e9c4753e304 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -15,6 +15,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -32,7 +33,7 @@ static struct worker *worker;
 static unsigned int nsecs = 10;
 static bool silent = false, multi = false;
 static bool done = false, fshared = false;
-static unsigned int ncpus, nthreads = 0;
+static unsigned int nthreads = 0;
 static int futex_flag = 0;
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -113,9 +114,10 @@ static void *workerfn(void *arg)
         return NULL;
 }
 
-static void create_threads(struct worker *w, pthread_attr_t thread_attr)
+static void create_threads(struct worker *w, pthread_attr_t thread_attr,
+                           struct cpu_map *cpu)
 {
-        cpu_set_t cpu;
+        cpu_set_t cpuset;
         unsigned int i;
 
         threads_starting = nthreads;
@@ -130,10 +132,10 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr)
                 } else
                         worker[i].futex = &global_futex;
 
-                CPU_ZERO(&cpu);
-                CPU_SET(i % ncpus, &cpu);
+                CPU_ZERO(&cpuset);
+                CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
                         err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
                 if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i]))
@@ -147,19 +149,22 @@ int bench_futex_lock_pi(int argc, const char **argv)
         unsigned int i;
         struct sigaction act;
         pthread_attr_t thread_attr;
+        struct cpu_map *cpu;
 
         argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0);
         if (argc)
                 goto err;
 
-        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+        cpu = cpu_map__new(NULL);
+        if (!cpu)
+                err(EXIT_FAILURE, "calloc");
 
         sigfillset(&act.sa_mask);
         act.sa_sigaction = toggle_done;
         sigaction(SIGINT, &act, NULL);
 
         if (!nthreads)
-                nthreads = ncpus;
+                nthreads = cpu->nr;
 
         worker = calloc(nthreads, sizeof(*worker));
         if (!worker)
@@ -180,7 +185,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
         pthread_attr_init(&thread_attr);
         gettimeofday(&start, NULL);
 
-        create_threads(worker, thread_attr);
+        create_threads(worker, thread_attr, cpu);
         pthread_attr_destroy(&thread_attr);
 
         pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 1058c194608a..fc692efa0c05 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -40,7 +41,7 @@ static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats requeuetime_stats, requeued_stats;
-static unsigned int ncpus, threads_starting, nthreads = 0;
+static unsigned int threads_starting, nthreads = 0;
 static int futex_flag = 0;
 
 static const struct option options[] = {
@@ -83,19 +84,19 @@ static void *workerfn(void *arg __maybe_unused)
 }
 
 static void block_threads(pthread_t *w,
-                          pthread_attr_t thread_attr)
+                          pthread_attr_t thread_attr, struct cpu_map *cpu)
 {
-        cpu_set_t cpu;
+        cpu_set_t cpuset;
         unsigned int i;
 
         threads_starting = nthreads;
 
         /* create and block all threads */
         for (i = 0; i < nthreads; i++) {
-                CPU_ZERO(&cpu);
-                CPU_SET(i % ncpus, &cpu);
+                CPU_ZERO(&cpuset);
+                CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
                         err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
                 if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
@@ -116,19 +117,22 @@ int bench_futex_requeue(int argc, const char **argv)
         unsigned int i, j;
         struct sigaction act;
         pthread_attr_t thread_attr;
+        struct cpu_map *cpu;
 
         argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
         if (argc)
                 goto err;
 
-        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+        cpu = cpu_map__new(NULL);
+        if (!cpu)
+                err(EXIT_FAILURE, "cpu_map__new");
 
         sigfillset(&act.sa_mask);
         act.sa_sigaction = toggle_done;
         sigaction(SIGINT, &act, NULL);
 
         if (!nthreads)
-                nthreads = ncpus;
+                nthreads = cpu->nr;
 
         worker = calloc(nthreads, sizeof(*worker));
         if (!worker)
@@ -156,7 +160,7 @@ int bench_futex_requeue(int argc, const char **argv)
                 struct timeval start, end, runtime;
 
                 /* create, launch & block all threads */
-                block_threads(worker, thread_attr);
+                block_threads(worker, thread_attr, cpu);
 
                 /* make sure all threads are already blocked */
                 pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index b4732dad9f89..69d8fdc87315 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,7 +7,17 @@
  * for each individual thread to service its share of work. Ultimately
  * it can be used to measure futex_wake() changes.
  */
+#include "bench.h"
+#include <linux/compiler.h>
+#include "../util/debug.h"
 
+#ifndef HAVE_PTHREAD_BARRIER
+int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe_unused)
+{
+        pr_err("%s: pthread_barrier_t unavailable, disabling this test...\n", __func__);
+        return 0;
+}
+#else /* HAVE_PTHREAD_BARRIER */
 /* For the CLR_() macros */
 #include <string.h>
 #include <pthread.h>
@@ -15,12 +25,11 @@
 #include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
-#include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -42,8 +51,9 @@ static bool done = false, silent = false, fshared = false;
 static unsigned int nblocked_threads = 0, nwaking_threads = 0;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
+static pthread_barrier_t barrier;
 static struct stats waketime_stats, wakeup_stats;
-static unsigned int ncpus, threads_starting;
+static unsigned int threads_starting;
 static int futex_flag = 0;
 
 static const struct option options[] = {
@@ -64,6 +74,8 @@ static void *waking_workerfn(void *arg)
         struct thread_data *waker = (struct thread_data *) arg;
         struct timeval start, end;
 
+        pthread_barrier_wait(&barrier);
+
         gettimeofday(&start, NULL);
 
         waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
@@ -84,6 +96,8 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 
         pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
 
+        pthread_barrier_init(&barrier, NULL, nwaking_threads + 1);
+
         /* create and block all threads */
         for (i = 0; i < nwaking_threads; i++) {
                 /*
@@ -96,9 +110,13 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
                         err(EXIT_FAILURE, "pthread_create");
         }
 
+        pthread_barrier_wait(&barrier);
+
         for (i = 0; i < nwaking_threads; i++)
                 if (pthread_join(td[i].worker, NULL))
                         err(EXIT_FAILURE, "pthread_join");
+
+        pthread_barrier_destroy(&barrier);
 }
 
 static void *blocked_workerfn(void *arg __maybe_unused)
@@ -119,19 +137,20 @@ static void *blocked_workerfn(void *arg __maybe_unused)
         return NULL;
 }
 
-static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
+                          struct cpu_map *cpu)
 {
-        cpu_set_t cpu;
+        cpu_set_t cpuset;
         unsigned int i;
 
         threads_starting = nblocked_threads;
 
         /* create and block all threads */
         for (i = 0; i < nblocked_threads; i++) {
-                CPU_ZERO(&cpu);
-                CPU_SET(i % ncpus, &cpu);
+                CPU_ZERO(&cpuset);
+                CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
                         err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
                 if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
@@ -205,6 +224,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
         struct sigaction act;
         pthread_attr_t thread_attr;
         struct thread_data *waking_worker;
+        struct cpu_map *cpu;
 
         argc = parse_options(argc, argv, options,
                              bench_futex_wake_parallel_usage, 0);
@@ -217,9 +237,12 @@ int bench_futex_wake_parallel(int argc, const char **argv)
         act.sa_sigaction = toggle_done;
         sigaction(SIGINT, &act, NULL);
 
-        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+        cpu = cpu_map__new(NULL);
+        if (!cpu)
+                err(EXIT_FAILURE, "calloc");
+
         if (!nblocked_threads)
-                nblocked_threads = ncpus;
+                nblocked_threads = cpu->nr;
 
         /* some sanity checks */
         if (nwaking_threads > nblocked_threads || !nwaking_threads)
@@ -259,7 +282,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
                         err(EXIT_FAILURE, "calloc");
 
                 /* create, launch & block all threads */
-                block_threads(blocked_worker, thread_attr);
+                block_threads(blocked_worker, thread_attr, cpu);
 
                 /* make sure all threads are already blocked */
                 pthread_mutex_lock(&thread_lock);
@@ -297,3 +320,4 @@ int bench_futex_wake_parallel(int argc, const char **argv)
         free(blocked_worker);
         return ret;
 }
+#endif /* HAVE_PTHREAD_BARRIER */
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 8c5c0b6b5c97..e8181ad7d088 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -89,19 +90,19 @@ static void print_summary(void)
 }
 
 static void block_threads(pthread_t *w,
-                          pthread_attr_t thread_attr)
+                          pthread_attr_t thread_attr, struct cpu_map *cpu)
 {
-        cpu_set_t cpu;
+        cpu_set_t cpuset;
         unsigned int i;
 
         threads_starting = nthreads;
 
         /* create and block all threads */
         for (i = 0; i < nthreads; i++) {
-                CPU_ZERO(&cpu);
-                CPU_SET(i % ncpus, &cpu);
+                CPU_ZERO(&cpuset);
+                CPU_SET(cpu->map[i % cpu->nr], &cpuset);
 
-                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+                if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
                         err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
 
                 if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
@@ -122,6 +123,7 @@ int bench_futex_wake(int argc, const char **argv)
         unsigned int i, j;
         struct sigaction act;
         pthread_attr_t thread_attr;
+        struct cpu_map *cpu;
 
         argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
         if (argc) {
@@ -129,7 +131,9 @@ int bench_futex_wake(int argc, const char **argv)
                 exit(EXIT_FAILURE);
         }
 
-        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+        cpu = cpu_map__new(NULL);
+        if (!cpu)
+                err(EXIT_FAILURE, "calloc");
 
         sigfillset(&act.sa_mask);
         act.sa_sigaction = toggle_done;
@@ -161,7 +165,7 @@ int bench_futex_wake(int argc, const char **argv)
                 struct timeval start, end, runtime;
 
                 /* create, launch & block all threads */
-                block_threads(worker, thread_attr);
+                block_threads(worker, thread_attr, cpu);
 
                 /* make sure all threads are already blocked */
                 pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d95fdcc26f4b..944070e98a2c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = {
         NULL
 };
 
+/*
+ * To get number of numa nodes present.
+ */
+static int nr_numa_nodes(void)
+{
+        int i, nr_nodes = 0;
+
+        for (i = 0; i < g->p.nr_nodes; i++) {
+                if (numa_bitmask_isbitset(numa_nodes_ptr, i))
+                        nr_nodes++;
+        }
+
+        return nr_nodes;
+}
+
+/*
+ * To check if given numa node is present.
+ */
+static int is_node_present(int node)
+{
+        return numa_bitmask_isbitset(numa_nodes_ptr, node);
+}
+
+/*
+ * To check given numa node has cpus.
+ */
+static bool node_has_cpus(int node)
+{
+        struct bitmask *cpu = numa_allocate_cpumask();
+        unsigned int i;
+
+        if (cpu && !numa_node_to_cpus(node, cpu)) {
+                for (i = 0; i < cpu->size; i++) {
+                        if (numa_bitmask_isbitset(cpu, i))
+                                return true;
+                }
+        }
+
+        return false; /* lets fall back to nocpus safely */
+}
+
 static cpu_set_t bind_to_cpu(int target_cpu)
 {
         cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)
 
 static cpu_set_t bind_to_node(int target_node)
 {
-        int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+        int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
         cpu_set_t orig_mask, mask;
         int cpu;
         int ret;
 
-        BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+        BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
         BUG_ON(!cpus_per_node);
 
         ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)
                         int i;
 
                         for (i = 0; i < mul; i++) {
-                                if (t >= g->p.nr_tasks) {
+                                if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) {
                                         printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
                                         goto out;
                                 }
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
         sum = 0;
 
         for (node = 0; node < g->p.nr_nodes; node++) {
+                if (!is_node_present(node))
+                        continue;
                 nr = nodes[node];
                 nr_min = min(nr, nr_min);
                 nr_max = max(nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
         process_groups = 0;
 
         for (node = 0; node < g->p.nr_nodes; node++) {
-                int processes = count_node_processes(node);
+                int processes;
 
+                if (!is_node_present(node))
+                        continue;
+                processes = count_node_processes(node);
                 nr = nodes[node];
                 tprintf(" %2d/%-2d", nr, processes);
 
@@ -1291,7 +1337,7 @@ static void print_summary(void)
 
         printf("\n ###\n");
         printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
-                g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+                g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus);
         printf(" #      %5dx %5ldMB global  shared mem operations\n",
                         g->p.nr_loops, g->p.bytes_global/1024/1024);
         printf(" #      %5dx %5ldMB process shared mem operations\n",
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 3d32aa45016d..f15731a3d438 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -357,7 +357,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
         }
 
         if (total_nr_samples == 0) {
-                ui__error("The %s file has no samples!\n", session->file->path);
+                ui__error("The %s file has no samples!\n", session->data->file.path);
                 goto out;
         }
 
@@ -401,7 +401,7 @@ int cmd_annotate(int argc, const char **argv)
                         .ordering_requires_timestamps = true,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode  = PERF_DATA_MODE_READ,
         };
         struct option options[] = {
@@ -411,7 +411,7 @@ int cmd_annotate(int argc, const char **argv)
                    "only consider symbols in these dsos"),
         OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
                     "symbol to annotate"),
-        OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+        OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
         OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
@@ -483,9 +483,9 @@ int cmd_annotate(int argc, const char **argv)
         if (quiet)
                 perf_quiet_option();
 
-        file.path  = input_name;
+        data.file.path = input_name;
 
-        annotate.session = perf_session__new(&file, false, &annotate.tool);
+        annotate.session = perf_session__new(&data, false, &annotate.tool);
         if (annotate.session == NULL)
                 return -1;
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 5f53a7ad5ef3..41db2cba77eb 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -312,7 +312,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                    *kcore_filename = NULL;
         char sbuf[STRERR_BUFSIZE];
 
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode  = PERF_DATA_MODE_READ,
         };
         struct perf_session *session = NULL;
@@ -325,8 +325,8 @@ int cmd_buildid_cache(int argc, const char **argv)
                    "file", "kcore file to add"),
         OPT_STRING('r', "remove", &remove_name_list_str, "file list",
                     "file(s) to remove"),
-        OPT_STRING('p', "purge", &purge_name_list_str, "path list",
-                    "path(s) to remove (remove old caches too)"),
+        OPT_STRING('p', "purge", &purge_name_list_str, "file list",
+                    "file(s) to remove (remove old caches too)"),
         OPT_STRING('M', "missing", &missing_filename, "file",
                    "to find missing build ids in the cache"),
         OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -353,10 +353,10 @@ int cmd_buildid_cache(int argc, const char **argv)
                 nsi = nsinfo__new(ns_id);
 
         if (missing_filename) {
-                file.path = missing_filename;
-                file.force = force;
+                data.file.path = missing_filename;
+                data.force     = force;
 
-                session = perf_session__new(&file, false, NULL);
+                session = perf_session__new(&data, false, NULL);
                 if (session == NULL)
                         return -1;
         }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index ec2f327cd79d..78abbe8d9d5f 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -51,10 +51,12 @@ static bool dso__skip_buildid(struct dso *dso, int with_hits)
 static int perf_session__list_build_ids(bool force, bool with_hits)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path  = input_name,
-                .mode  = PERF_DATA_MODE_READ,
-                .force = force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = force,
         };
 
         symbol__elf_init();
@@ -64,7 +66,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
         if (filename__fprintf_build_id(input_name, stdout) > 0)
                 goto out;
 
-        session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
+        session = perf_session__new(&data, false, &build_id__mark_dso_hit_ops);
         if (session == NULL)
                 return -1;
 
@@ -72,7 +74,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
          * We take all buildids when the file contains AUX area tracing data
          * because we do not decode the trace because it would take too long.
          */
-        if (!perf_data_file__is_pipe(&file) &&
+        if (!perf_data__is_pipe(&data) &&
             perf_header__has_feat(&session->header, HEADER_AUXTRACE))
                 with_hits = false;
 
@@ -80,7 +82,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
          * in pipe-mode, the only way to get the buildids is to parse
          * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
          */
-        if (with_hits || perf_data_file__is_pipe(&file))
+        if (with_hits || perf_data__is_pipe(&data))
                 perf_session__process_events(session);
 
         perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index fd32ad08c6d4..539c3d460158 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -27,13 +27,10 @@
 #include "sort.h"
 #include "tool.h"
 #include "data.h"
-#include "sort.h"
 #include "event.h"
 #include "evlist.h"
 #include "evsel.h"
-#include <asm/bug.h>
 #include "ui/browsers/hists.h"
-#include "evlist.h"
 #include "thread.h"
 
 struct c2c_hists {
@@ -2224,9 +2221,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
         struct hist_browser *browser;
         int key = -1;
         const char help[] =
-        " ENTER         Togle callchains (if present) \n"
-        " n             Togle Node details info \n"
-        " s             Togle full lenght of symbol and source line columns \n"
+        " ENTER         Toggle callchains (if present) \n"
+        " n             Toggle Node details info \n"
+        " s             Toggle full length of symbol and source line columns \n"
         " q             Return back to cacheline list \n";
 
         /* Display compact version first. */
@@ -2248,7 +2245,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
         c2c_browser__update_nr_entries(browser);
 
         while (1) {
-                key = hist_browser__run(browser, "? - help");
+                key = hist_browser__run(browser, "? - help", true);
 
                 switch (key) {
                 case 's':
@@ -2303,7 +2300,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
         int key = -1;
         const char help[] =
         " d             Display cacheline details \n"
-        " ENTER         Togle callchains (if present) \n"
+        " ENTER         Toggle callchains (if present) \n"
         " q             Quit \n";
 
         browser = perf_c2c_browser__new(hists);
@@ -2317,7 +2314,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
         c2c_browser__update_nr_entries(browser);
 
         while (1) {
-                key = hist_browser__run(browser, "? - help");
+                key = hist_browser__run(browser, "? - help", true);
 
                 switch (key) {
                 case 'q':
@@ -2393,9 +2390,10 @@ static int setup_callchain(struct perf_evlist *evlist)
         enum perf_call_graph_mode mode = CALLCHAIN_NONE;
 
         if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-            (sample_type & PERF_SAMPLE_STACK_USER))
+            (sample_type & PERF_SAMPLE_STACK_USER)) {
                 mode = CALLCHAIN_DWARF;
-        else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+                dwarf_callchain_users = true;
+        } else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
                 mode = CALLCHAIN_LBR;
         else if (sample_type & PERF_SAMPLE_CALLCHAIN)
                 mode = CALLCHAIN_FP;
@@ -2524,7 +2522,7 @@ static int perf_c2c__report(int argc, const char **argv)
 {
         struct perf_session *session;
         struct ui_progress prog;
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT;
@@ -2573,8 +2571,8 @@ static int perf_c2c__report(int argc, const char **argv)
         if (!input_name || !strlen(input_name))
                 input_name = "perf.data";
 
-        file.path  = input_name;
-        file.force = symbol_conf.force;
+        data.file.path = input_name;
+        data.force     = symbol_conf.force;
 
         err = setup_display(display);
         if (err)
@@ -2592,7 +2590,7 @@ static int perf_c2c__report(int argc, const char **argv)
                 goto out;
         }
 
-        session = perf_session__new(&file, 0, &c2c.tool);
+        session = perf_session__new(&data, 0, &c2c.tool);
         if (session == NULL) {
                 pr_debug("No memory for session\n");
                 goto out;
@@ -2612,7 +2610,7 @@ static int perf_c2c__report(int argc, const char **argv)
                 goto out_session;
 
         /* No pipe support at the moment. */
-        if (perf_data_file__is_pipe(session->file)) {
+        if (perf_data__is_pipe(session->data)) {
                 pr_debug("No pipe support at the moment.\n");
                 goto out_session;
         }
@@ -2733,6 +2731,7 @@ static int perf_c2c__record(int argc, const char **argv)
                 if (!perf_mem_events[j].supported) {
                         pr_err("failed: event '%s' not supported\n",
                                perf_mem_events[j].name);
+                        free(rec_argv);
                         return -1;
                 }
 
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index abfa49eaf7fd..514f70f95b57 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -35,8 +35,7 @@ static struct option config_options[] = {
         OPT_END()
 };
 
-static int set_config(struct perf_config_set *set, const char *file_name,
-                      const char *var, const char *value)
+static int set_config(struct perf_config_set *set, const char *file_name)
 {
         struct perf_config_section *section = NULL;
         struct perf_config_item *item = NULL;
@@ -50,7 +49,6 @@ static int set_config(struct perf_config_set *set, const char *file_name,
         if (!fp)
                 return -1;
 
-        perf_config_set__collect(set, file_name, var, value);
         fprintf(fp, "%s\n", first_line);
 
         /* overwrite configvariables */
@@ -162,6 +160,7 @@ int cmd_config(int argc, const char **argv)
         struct perf_config_set *set;
         char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
         const char *config_filename;
+        bool changed = false;
 
         argc = parse_options(argc, argv, config_options, config_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
@@ -232,15 +231,26 @@ int cmd_config(int argc, const char **argv)
                                         goto out_err;
                                 }
                         } else {
-                                if (set_config(set, config_filename, var, value) < 0) {
-                                        pr_err("Failed to set '%s=%s' on %s\n",
-                                               var, value, config_filename);
+                                if (perf_config_set__collect(set, config_filename,
+                                                             var, value) < 0) {
+                                        pr_err("Failed to add '%s=%s'\n",
+                                               var, value);
                                         free(arg);
                                         goto out_err;
                                 }
+                                changed = true;
                         }
                         free(arg);
                 }
+
+                if (!changed)
+                        break;
+
+                if (set_config(set, config_filename) < 0) {
+                        pr_err("Failed to set the configs on %s\n",
+                               config_filename);
+                        goto out_err;
+                }
         }
 
         ret = 0;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 56223bdfa205..d660cb7b222b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -48,7 +48,7 @@ struct diff_hpp_fmt {
 
 struct data__file {
         struct perf_session     *session;
-        struct perf_data_file   file;
+        struct perf_data         data;
         int                      idx;
         struct hists            *hists;
         struct diff_hpp_fmt      fmt[PERF_HPP_DIFF__MAX_INDEX];
@@ -708,7 +708,7 @@ static void data__fprintf(void)
 
         data__for_each_file(i, d)
                 fprintf(stdout, "#  [%d] %s %s\n",
-                        d->idx, d->file.path,
+                        d->idx, d->data.file.path,
                         !d->idx ? "(Baseline)" : "");
 
         fprintf(stdout, "#\n");
@@ -777,16 +777,16 @@ static int __cmd_diff(void)
         int ret = -EINVAL, i;
 
         data__for_each_file(i, d) {
-                d->session = perf_session__new(&d->file, false, &tool);
+                d->session = perf_session__new(&d->data, false, &tool);
                 if (!d->session) {
-                        pr_err("Failed to open %s\n", d->file.path);
+                        pr_err("Failed to open %s\n", d->data.file.path);
                         ret = -1;
                         goto out_delete;
                 }
 
                 ret = perf_session__process_events(d->session);
                 if (ret) {
-                        pr_err("Failed to process %s\n", d->file.path);
+                        pr_err("Failed to process %s\n", d->data.file.path);
                         goto out_delete;
                 }
 
@@ -1287,11 +1287,11 @@ static int data_init(int argc, const char **argv)
                 return -ENOMEM;
 
         data__for_each_file(i, d) {
-                struct perf_data_file *file = &d->file;
+                struct perf_data *data = &d->data;
 
-                file->path  = use_default ? defaults[i] : argv[i];
-                file->mode  = PERF_DATA_MODE_READ,
-                file->force = force,
+                data->file.path = use_default ? defaults[i] : argv[i];
+                data->mode      = PERF_DATA_MODE_READ,
+                data->force     = force,
 
                 d->idx  = i;
         }
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index cdd145613f60..e06e822ce634 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -22,14 +22,16 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 {
         struct perf_session *session;
         struct perf_evsel *pos;
-        struct perf_data_file file = {
-                .path = file_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = details->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = file_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = details->force,
         };
         bool has_tracepoint = false;
 
-        session = perf_session__new(&file, 0, NULL);
+        session = perf_session__new(&data, 0, NULL);
         if (session == NULL)
                 return -1;
 
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index bd1fedef3d1c..4aca13f23b9d 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -284,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
                 add_man_viewer(value);
                 return 0;
         }
-        if (!strstarts(var, "man."))
+        if (strstarts(var, "man."))
                 return add_man_viewer_info(var, value);
 
         return 0;
@@ -314,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
         if (!perf_cmd)
                 return "perf";
-        else if (!strstarts(perf_cmd, "perf"))
+        else if (strstarts(perf_cmd, "perf"))
                 return perf_cmd;
 
         return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
@@ -439,7 +439,7 @@ int cmd_help(int argc, const char **argv)
 #ifdef HAVE_LIBELF_SUPPORT
                 "probe",
 #endif
-#ifdef HAVE_LIBAUDIT_SUPPORT
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
                 "trace",
 #endif
         NULL };
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 3e0e73b0dc67..40fe919bbcf3 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -36,7 +36,7 @@ struct perf_inject {
         bool                    strip;
         bool                    jit_mode;
         const char              *input_name;
-        struct perf_data_file   output;
+        struct perf_data        output;
         u64                     bytes_written;
         u64                     aux_id;
         struct list_head        samples;
@@ -53,7 +53,7 @@ static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
 {
         ssize_t size;
 
-        size = perf_data_file__write(&inject->output, buf, sz);
+        size = perf_data__write(&inject->output, buf, sz);
         if (size < 0)
                 return -errno;
 
@@ -146,7 +146,7 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
         if (!inject->output.is_pipe) {
                 off_t offset;
 
-                offset = lseek(inject->output.fd, 0, SEEK_CUR);
+                offset = lseek(inject->output.file.fd, 0, SEEK_CUR);
                 if (offset == -1)
                         return -errno;
                 ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
@@ -155,11 +155,11 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
                         return ret;
         }
 
-        if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+        if (perf_data__is_pipe(session->data) || !session->one_mmap) {
                 ret = output_bytes(inject, event, event->header.size);
                 if (ret < 0)
                         return ret;
-                ret = copy_bytes(inject, perf_data_file__fd(session->file),
+                ret = copy_bytes(inject, perf_data__fd(session->data),
                                  event->auxtrace.size);
         } else {
                 ret = output_bytes(inject, event,
@@ -536,8 +536,7 @@ found:
         sample_sw.period = sample->period;
         sample_sw.time   = sample->time;
         perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
-                                      evsel->attr.read_format, &sample_sw,
-                                      false);
+                                      evsel->attr.read_format, &sample_sw);
         build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
         return perf_event__repipe(tool, event_sw, &sample_sw, machine);
 }
@@ -638,8 +637,8 @@ static int __cmd_inject(struct perf_inject *inject)
 {
         int ret = -EINVAL;
         struct perf_session *session = inject->session;
-        struct perf_data_file *file_out = &inject->output;
-        int fd = perf_data_file__fd(file_out);
+        struct perf_data *data_out = &inject->output;
+        int fd = perf_data__fd(data_out);
         u64 output_data_offset;
 
         signal(SIGINT, sig_handler);
@@ -694,14 +693,14 @@ static int __cmd_inject(struct perf_inject *inject)
         if (!inject->itrace_synth_opts.set)
                 auxtrace_index__free(&session->auxtrace_index);
 
-        if (!file_out->is_pipe)
+        if (!data_out->is_pipe)
                 lseek(fd, output_data_offset, SEEK_SET);
 
         ret = perf_session__process_events(session);
         if (ret)
                 return ret;
 
-        if (!file_out->is_pipe) {
+        if (!data_out->is_pipe) {
                 if (inject->build_ids)
                         perf_header__set_feat(&session->header,
                                               HEADER_BUILD_ID);
@@ -776,11 +775,13 @@ int cmd_inject(int argc, const char **argv)
                 .input_name  = "-",
                 .samples = LIST_HEAD_INIT(inject.samples),
                 .output = {
-                        .path = "-",
-                        .mode = PERF_DATA_MODE_WRITE,
+                        .file      = {
+                                .path = "-",
+                        },
+                        .mode      = PERF_DATA_MODE_WRITE,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         int ret;
@@ -790,7 +791,7 @@ int cmd_inject(int argc, const char **argv)
                             "Inject build-ids into the output stream"),
                 OPT_STRING('i', "input", &inject.input_name, "file",
                            "input file name"),
-                OPT_STRING('o', "output", &inject.output.path, "file",
+                OPT_STRING('o', "output", &inject.output.file.path, "file",
                            "output file name"),
                 OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
                             "Merge sched-stat and sched-switch for getting events "
@@ -802,7 +803,7 @@ int cmd_inject(int argc, const char **argv)
                          "be more verbose (show build ids, etc)"),
                 OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
                            "kallsyms pathname"),
-                OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+                OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
                 OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
                                     NULL, "opts", "Instruction Tracing options",
                                     itrace_parse_synth_opts),
@@ -830,15 +831,15 @@ int cmd_inject(int argc, const char **argv)
                 return -1;
         }
 
-        if (perf_data_file__open(&inject.output)) {
+        if (perf_data__open(&inject.output)) {
                 perror("failed to create output file");
                 return -1;
         }
 
         inject.tool.ordered_events = inject.sched_stat;
 
-        file.path = inject.input_name;
-        inject.session = perf_session__new(&file, true, &inject.tool);
+        data.file.path = inject.input_name;
+        inject.session = perf_session__new(&data, true, &inject.tool);
         if (inject.session == NULL)
                 return -1;
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 35d4b9c9a9e8..ae11e4c3516a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -641,7 +641,6 @@ static const struct {
         { "__GFP_ATOMIC",               "_A" },
         { "__GFP_IO",                   "I" },
         { "__GFP_FS",                   "F" },
-        { "__GFP_COLD",                 "CO" },
         { "__GFP_NOWARN",               "NWR" },
         { "__GFP_RETRY_MAYFAIL",        "R" },
         { "__GFP_NOFAIL",               "NF" },
@@ -655,7 +654,6 @@ static const struct {
         { "__GFP_RECLAIMABLE",          "RC" },
         { "__GFP_MOVABLE",              "M" },
         { "__GFP_ACCOUNT",              "AC" },
-        { "__GFP_NOTRACK",              "NT" },
         { "__GFP_WRITE",                "WR" },
         { "__GFP_RECLAIM",              "R" },
         { "__GFP_DIRECT_RECLAIM",       "DR" },
@@ -1894,7 +1892,7 @@ int cmd_kmem(int argc, const char **argv)
 {
         const char * const default_slab_sort = "frag,hit,bytes";
         const char * const default_page_sort = "bytes,hit";
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         const struct option kmem_options[] = {
@@ -1910,7 +1908,7 @@ int cmd_kmem(int argc, const char **argv)
                      "page, order, migtype, gfp", parse_sort_opt),
         OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
         OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
-        OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+        OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
         OPT_CALLBACK_NOOPT(0, "slab", NULL, NULL, "Analyze slab allocator",
                            parse_slab_opt),
         OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
@@ -1950,9 +1948,9 @@ int cmd_kmem(int argc, const char **argv)
                 return __cmd_record(argc, argv);
         }
 
-        file.path = input_name;
+        data.file.path = input_name;
 
-        kmem_session = session = perf_session__new(&file, false, &perf_kmem);
+        kmem_session = session = perf_session__new(&data, false, &perf_kmem);
         if (session == NULL)
                 return -1;
 
@@ -1984,7 +1982,8 @@ int cmd_kmem(int argc, const char **argv)
 
         if (perf_time__parse_str(&ptime, time_str) != 0) {
                 pr_err("Invalid time string\n");
-                return -EINVAL;
+                ret = -EINVAL;
+                goto out_delete;
         }
 
         if (!strcmp(argv[0], "stat")) {
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 5fb40368d5d1..55d919dc5bc6 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -26,6 +26,9 @@
 #include <sys/timerfd.h>
 #endif
 #include <sys/time.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 #include <linux/kernel.h>
 #include <linux/time64.h>
@@ -35,7 +38,6 @@
 #include <termios.h>
 #include <semaphore.h>
 #include <signal.h>
-#include <pthread.h>
 #include <math.h>
 
 static const char *get_filename_for_perf_kvm(void)
@@ -742,20 +744,20 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
                                    u64 *mmap_time)
 {
         union perf_event *event;
-        struct perf_sample sample;
+        u64 timestamp;
         s64 n = 0;
         int err;
 
         *mmap_time = ULLONG_MAX;
         while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
-                err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
+                err = perf_evlist__parse_sample_timestamp(kvm->evlist, event, &timestamp);
                 if (err) {
                         perf_evlist__mmap_consume(kvm->evlist, idx);
                         pr_err("Failed to parse sample\n");
                         return -1;
                 }
 
-                err = perf_session__queue_event(kvm->session, event, &sample, 0);
+                err = perf_session__queue_event(kvm->session, event, timestamp, 0);
                 /*
                  * FIXME: Here we can't consume the event, as perf_session__queue_event will
                  *        point to it, and it'll get possibly overwritten by the kernel.
@@ -769,7 +771,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 
                 /* save time stamp of our first sample for this mmap */
                 if (n == 0)
-                        *mmap_time = sample.time;
+                        *mmap_time = timestamp;
 
                 /* limit events per mmap handled all at once */
                 n++;
@@ -1045,7 +1047,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
                 goto out;
         }
 
-        if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+        if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
                 ui__error("Failed to mmap the events: %s\n",
                           str_error_r(errno, sbuf, sizeof(sbuf)));
                 perf_evlist__close(evlist);
@@ -1069,10 +1071,12 @@ static int read_events(struct perf_kvm_stat *kvm)
                 .namespaces             = perf_event__process_namespaces,
                 .ordered_events         = true,
         };
-        struct perf_data_file file = {
-                .path = kvm->file_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = kvm->force,
+        struct perf_data file = {
+                .file      = {
+                        .path = kvm->file_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = kvm->force,
         };
 
         kvm->tool = eops;
@@ -1360,7 +1364,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
                 "perf kvm stat live [<options>]",
                 NULL
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_WRITE,
         };
 
@@ -1434,7 +1438,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         /*
          * perf session
          */
-        kvm->session = perf_session__new(&file, false, &kvm->tool);
+        kvm->session = perf_session__new(&data, false, &kvm->tool);
         if (kvm->session == NULL) {
                 err = -1;
                 goto out;
@@ -1443,7 +1447,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         perf_session__set_id_hdr_size(kvm->session);
         ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
         machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
-                                    kvm->evlist->threads, false, kvm->opts.proc_map_timeout);
+                                    kvm->evlist->threads, false,
+                                    kvm->opts.proc_map_timeout, 1);
         err = kvm_live_open_events(kvm);
         if (err)
                 goto out;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index eeedbe433776..ead221e49f00 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -16,6 +16,7 @@
 #include "util/cache.h"
 #include "util/pmu.h"
 #include "util/debug.h"
+#include "util/metricgroup.h"
 #include <subcmd/parse-options.h>
 
 static bool desc_flag = true;
@@ -80,6 +81,10 @@ int cmd_list(int argc, const char **argv)
                                                 long_desc_flag, details_flag);
                 else if (strcmp(argv[i], "sdt") == 0)
                         print_sdt_events(NULL, NULL, raw_dump);
+                else if (strcmp(argv[i], "metric") == 0)
+                        metricgroup__print(true, false, NULL, raw_dump);
+                else if (strcmp(argv[i], "metricgroup") == 0)
+                        metricgroup__print(false, true, NULL, raw_dump);
                 else if ((sep = strchr(argv[i], ':')) != NULL) {
                         int sep_idx;
 
@@ -97,6 +102,7 @@ int cmd_list(int argc, const char **argv)
                         s[sep_idx] = '\0';
                         print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
                         print_sdt_events(s, s + sep_idx + 1, raw_dump);
+                        metricgroup__print(true, true, s, raw_dump);
                         free(s);
                 } else {
                         if (asprintf(&s, "*%s*", argv[i]) < 0) {
@@ -113,6 +119,7 @@ int cmd_list(int argc, const char **argv)
                                                 details_flag);
                         print_tracepoint_events(NULL, s, raw_dump);
                         print_sdt_events(NULL, s, raw_dump);
+                        metricgroup__print(true, true, NULL, raw_dump);
                         free(s);
                 }
         }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index fe69cd6b89e1..6e0189df2b3b 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -865,13 +865,15 @@ static int __cmd_report(bool display_info)
                 .namespaces      = perf_event__process_namespaces,
                 .ordered_events  = true,
         };
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = force,
         };
 
-        session = perf_session__new(&file, false, &eops);
+        session = perf_session__new(&data, false, &eops);
         if (!session) {
                 pr_err("Initializing perf session failed\n");
                 return -1;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 4db960085273..506564651cda 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -113,6 +113,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
                 if (!perf_mem_events[j].supported) {
                         pr_err("failed: event '%s' not supported\n",
                                perf_mem_events__name(j));
+                        free(rec_argv);
                         return -1;
                 }
 
@@ -236,13 +237,15 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int report_raw_events(struct perf_mem *mem)
 {
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = mem->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = mem->force,
         };
         int ret;
-        struct perf_session *session = perf_session__new(&file, false,
+        struct perf_session *session = perf_session__new(&data, false,
                                                          &mem->tool);
 
         if (session == NULL)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0c95ffefb6cc..bf4ca749d1ac 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -51,7 +51,6 @@
 #include <signal.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
-#include <asm/bug.h>
 #include <linux/time64.h>
 
 struct switch_output {
@@ -67,7 +66,7 @@ struct record {
         struct perf_tool        tool;
         struct record_opts      opts;
         u64                     bytes_written;
-        struct perf_data_file   file;
+        struct perf_data        data;
         struct auxtrace_record  *itr;
         struct perf_evlist      *evlist;
         struct perf_session     *session;
@@ -79,6 +78,7 @@ struct record {
         bool                    no_buildid_cache_set;
         bool                    buildid_all;
         bool                    timestamp_filename;
+        bool                    timestamp_boundary;
         struct switch_output    switch_output;
         unsigned long long      samples;
 };
@@ -108,7 +108,7 @@ static bool switch_output_time(struct record *rec)
 
 static int record__write(struct record *rec, void *bf, size_t size)
 {
-        if (perf_data_file__write(rec->session->file, bf, size) < 0) {
+        if (perf_data__write(rec->session->data, bf, size) < 0) {
                 pr_err("failed to write perf data, error: %m\n");
                 return -1;
         }
@@ -130,107 +130,12 @@ static int process_synthesized_event(struct perf_tool *tool,
         return record__write(rec, event, event->header.size);
 }
 
-static int
-backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
-{
-        struct perf_event_header *pheader;
-        u64 evt_head = head;
-        int size = mask + 1;
-
-        pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
-        pheader = (struct perf_event_header *)(buf + (head & mask));
-        *start = head;
-        while (true) {
-                if (evt_head - head >= (unsigned int)size) {
-                        pr_debug("Finished reading backward ring buffer: rewind\n");
-                        if (evt_head - head > (unsigned int)size)
-                                evt_head -= pheader->size;
-                        *end = evt_head;
-                        return 0;
-                }
-
-                pheader = (struct perf_event_header *)(buf + (evt_head & mask));
-
-                if (pheader->size == 0) {
-                        pr_debug("Finished reading backward ring buffer: get start\n");
-                        *end = evt_head;
-                        return 0;
-                }
-
-                evt_head += pheader->size;
-                pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
-        }
-        WARN_ONCE(1, "Shouldn't get here\n");
-        return -1;
-}
-
-static int
-rb_find_range(void *data, int mask, u64 head, u64 old,
-              u64 *start, u64 *end, bool backward)
-{
-        if (!backward) {
-                *start = old;
-                *end = head;
-                return 0;
-        }
-
-        return backward_rb_find_range(data, mask, head, start, end);
-}
-
-static int
-record__mmap_read(struct record *rec, struct perf_mmap *md,
-                  bool overwrite, bool backward)
+static int record__pushfn(void *to, void *bf, size_t size)
 {
-        u64 head = perf_mmap__read_head(md);
-        u64 old = md->prev;
-        u64 end = head, start = old;
-        unsigned char *data = md->base + page_size;
-        unsigned long size;
-        void *buf;
-        int rc = 0;
-
-        if (rb_find_range(data, md->mask, head,
-                          old, &start, &end, backward))
-                return -1;
-
-        if (start == end)
-                return 0;
+        struct record *rec = to;
 
         rec->samples++;
-
-        size = end - start;
-        if (size > (unsigned long)(md->mask) + 1) {
-                WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
-
-                md->prev = head;
-                perf_mmap__consume(md, overwrite || backward);
-                return 0;
-        }
-
-        if ((start & md->mask) + size != (end & md->mask)) {
-                buf = &data[start & md->mask];
-                size = md->mask + 1 - (start & md->mask);
-                start += size;
-
-                if (record__write(rec, buf, size) < 0) {
-                        rc = -1;
-                        goto out;
-                }
-        }
-
-        buf = &data[start & md->mask];
-        size = end - start;
-        start += size;
-
-        if (record__write(rec, buf, size) < 0) {
-                rc = -1;
-                goto out;
-        }
-
-        md->prev = head;
-        perf_mmap__consume(md, overwrite || backward);
-out:
-        return rc;
+        return record__write(rec, bf, size);
 }
 
 static volatile int done;
@@ -269,13 +174,13 @@ static int record__process_auxtrace(struct perf_tool *tool,
                                     size_t len1, void *data2, size_t len2)
 {
         struct record *rec = container_of(tool, struct record, tool);
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         size_t padding;
         u8 pad[8] = {0};
 
-        if (!perf_data_file__is_pipe(file)) {
+        if (!perf_data__is_pipe(data)) {
                 off_t file_offset;
-                int fd = perf_data_file__fd(file);
+                int fd = perf_data__fd(data);
                 int err;
 
                 file_offset = lseek(fd, 0, SEEK_CUR);
@@ -396,7 +301,7 @@ static int record__mmap_evlist(struct record *rec,
         struct record_opts *opts = &rec->opts;
         char msg[512];
 
-        if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+        if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
                                  opts->auxtrace_mmap_pages,
                                  opts->auxtrace_snapshot_mode) < 0) {
                 if (errno == EPERM) {
@@ -434,6 +339,22 @@ static int record__open(struct record *rec)
         struct perf_evsel_config_term *err_term;
         int rc = 0;
 
+        /*
+         * For initial_delay we need to add a dummy event so that we can track
+         * PERF_RECORD_MMAP while we wait for the initial delay to enable the
+         * real events, the ones asked by the user.
+         */
+        if (opts->initial_delay) {
+                if (perf_evlist__add_dummy(evlist))
+                        return -ENOMEM;
+
+                pos = perf_evlist__first(evlist);
+                pos->tracking = 0;
+                pos = perf_evlist__last(evlist);
+                pos->tracking = 1;
+                pos->attr.enable_on_exec = 1;
+        }
+
         perf_evlist__config(evlist, opts, &callchain_param);
 
         evlist__for_each_entry(evlist, pos) {
@@ -451,6 +372,8 @@ try_again:
                         ui__error("%s\n", msg);
                         goto out;
                 }
+
+                pos->supported = true;
         }
 
         if (perf_evlist__apply_filters(evlist, &pos)) {
@@ -487,17 +410,24 @@ static int process_sample_event(struct perf_tool *tool,
 {
         struct record *rec = container_of(tool, struct record, tool);
 
-        rec->samples++;
+        if (rec->evlist->first_sample_time == 0)
+                rec->evlist->first_sample_time = sample->time;
 
+        rec->evlist->last_sample_time = sample->time;
+
+        if (rec->buildid_all)
+                return 0;
+
+        rec->samples++;
         return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 }
 
 static int process_buildids(struct record *rec)
 {
-        struct perf_data_file *file  = &rec->file;
+        struct perf_data *data = &rec->data;
         struct perf_session *session = rec->session;
 
-        if (file->size == 0)
+        if (data->size == 0)
                 return 0;
 
         /*
@@ -513,9 +443,11 @@ static int process_buildids(struct record *rec)
 
         /*
          * If --buildid-all is given, it marks all DSO regardless of hits,
-         * so no need to process samples.
+         * so no need to process samples. But if timestamp_boundary is enabled,
+         * it still needs to walk on all samples to get the timestamps of
+         * first/last samples.
          */
-        if (rec->buildid_all)
+        if (rec->buildid_all && !rec->timestamp_boundary)
                 rec->tool.sample = NULL;
 
         return perf_session__process_events(session);
@@ -556,7 +488,7 @@ static struct perf_event_header finished_round_event = {
 };
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
-                                    bool backward)
+                                    bool overwrite)
 {
         u64 bytes_written = rec->bytes_written;
         int i;
@@ -566,19 +498,18 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
         if (!evlist)
                 return 0;
 
-        maps = backward ? evlist->backward_mmap : evlist->mmap;
+        maps = overwrite ? evlist->overwrite_mmap : evlist->mmap;
         if (!maps)
                 return 0;
 
-        if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+        if (overwrite && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
                 return 0;
 
         for (i = 0; i < evlist->nr_mmaps; i++) {
                 struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
                 if (maps[i].base) {
-                        if (record__mmap_read(rec, &maps[i],
-                                              evlist->overwrite, backward) != 0) {
+                        if (perf_mmap__push(&maps[i], overwrite, rec, record__pushfn) != 0) {
                                 rc = -1;
                                 goto out;
                         }
@@ -598,7 +529,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
         if (bytes_written != rec->bytes_written)
                 rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
-        if (backward)
+        if (overwrite)
                 perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
         return rc;
@@ -641,14 +572,14 @@ static void record__init_features(struct record *rec)
 static void
 record__finish_output(struct record *rec)
 {
-        struct perf_data_file *file = &rec->file;
-        int fd = perf_data_file__fd(file);
+        struct perf_data *data = &rec->data;
+        int fd = perf_data__fd(data);
 
-        if (file->is_pipe)
+        if (data->is_pipe)
                 return;
 
         rec->session->header.data_size += rec->bytes_written;
-        file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
+        data->size = lseek(perf_data__fd(data), 0, SEEK_CUR);
 
         if (!rec->no_buildid) {
                 process_buildids(rec);
@@ -687,7 +618,7 @@ static int record__synthesize(struct record *rec, bool tail);
 static int
 record__switch_output(struct record *rec, bool at_exit)
 {
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         int fd, err;
 
         /* Same Size:      "2015122520103046"*/
@@ -705,7 +636,7 @@ record__switch_output(struct record *rec, bool at_exit)
                 return -EINVAL;
         }
 
-        fd = perf_data_file__switch(file, timestamp,
+        fd = perf_data__switch(data, timestamp,
                                     rec->session->header.data_offset,
                                     at_exit);
         if (fd >= 0 && !at_exit) {
@@ -715,7 +646,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
         if (!quiet)
                 fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
-                        file->path, timestamp);
+                        data->file.path, timestamp);
 
         /* Output tracking events */
         if (!at_exit) {
@@ -770,8 +701,8 @@ perf_evlist__pick_pc(struct perf_evlist *evlist)
         if (evlist) {
                 if (evlist->mmap && evlist->mmap[0].base)
                         return evlist->mmap[0].base;
-                if (evlist->backward_mmap && evlist->backward_mmap[0].base)
-                        return evlist->backward_mmap[0].base;
+                if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+                        return evlist->overwrite_mmap[0].base;
         }
         return NULL;
 }
@@ -790,16 +721,16 @@ static int record__synthesize(struct record *rec, bool tail)
 {
         struct perf_session *session = rec->session;
         struct machine *machine = &session->machines.host;
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         struct record_opts *opts = &rec->opts;
         struct perf_tool *tool = &rec->tool;
-        int fd = perf_data_file__fd(file);
+        int fd = perf_data__fd(data);
         int err = 0;
 
         if (rec->opts.tail_synthesize != tail)
                 return 0;
 
-        if (file->is_pipe) {
+        if (data->is_pipe) {
                 err = perf_event__synthesize_features(
                         tool, session, rec->evlist, process_synthesized_event);
                 if (err < 0) {
@@ -845,26 +776,50 @@ static int record__synthesize(struct record *rec, bool tail)
                         goto out;
         }
 
-        err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-                                                 machine);
-        WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
-                           "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-                           "Check /proc/kallsyms permission or run as root.\n");
-
-        err = perf_event__synthesize_modules(tool, process_synthesized_event,
-                                             machine);
-        WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
-                           "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-                           "Check /proc/modules permission or run as root.\n");
+        if (!perf_evlist__exclude_kernel(rec->evlist)) {
+                err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+                                                         machine);
+                WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+                                   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                                   "Check /proc/kallsyms permission or run as root.\n");
+
+                err = perf_event__synthesize_modules(tool, process_synthesized_event,
+                                                     machine);
+                WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+                                   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                                   "Check /proc/modules permission or run as root.\n");
+        }
 
         if (perf_guest) {
                 machines__process_guests(&session->machines,
                                          perf_event__synthesize_guest_os, tool);
         }
 
+        err = perf_event__synthesize_extra_attr(&rec->tool,
+                                                rec->evlist,
+                                                process_synthesized_event,
+                                                data->is_pipe);
+        if (err)
+                goto out;
+
+        err = perf_event__synthesize_thread_map2(&rec->tool, rec->evlist->threads,
+                                                 process_synthesized_event,
+                                                NULL);
+        if (err < 0) {
+                pr_err("Couldn't synthesize thread map.\n");
+                return err;
+        }
+
+        err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->cpus,
+                                             process_synthesized_event, NULL);
+        if (err < 0) {
+                pr_err("Couldn't synthesize cpu map.\n");
+                return err;
+        }
+
         err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
                                             process_synthesized_event, opts->sample_address,
-                                            opts->proc_map_timeout);
+                                            opts->proc_map_timeout, 1);
 out:
         return err;
 }
@@ -878,7 +833,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         struct machine *machine;
         struct perf_tool *tool = &rec->tool;
         struct record_opts *opts = &rec->opts;
-        struct perf_data_file *file = &rec->file;
+        struct perf_data *data = &rec->data;
         struct perf_session *session;
         bool disabled = false, draining = false;
         int fd;
@@ -904,20 +859,20 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 signal(SIGUSR2, SIG_IGN);
         }
 
-        session = perf_session__new(file, false, tool);
+        session = perf_session__new(data, false, tool);
         if (session == NULL) {
                 pr_err("Perf session creation failed.\n");
                 return -1;
         }
 
-        fd = perf_data_file__fd(file);
+        fd = perf_data__fd(data);
         rec->session = session;
 
         record__init_features(rec);
 
         if (forks) {
                 err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
-                                                    argv, file->is_pipe,
+                                                    argv, data->is_pipe,
                                                     workload_exec_failed_signal);
                 if (err < 0) {
                         pr_err("Couldn't run the workload!\n");
@@ -953,7 +908,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         if (!rec->evlist->nr_groups)
                 perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
-        if (file->is_pipe) {
+        if (data->is_pipe) {
                 err = perf_header__write_pipe(fd);
                 if (err < 0)
                         goto out_child;
@@ -1214,8 +1169,8 @@ out_child:
                         samples[0] = '\0';
 
                 fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n",
-                        perf_data_file__size(file) / 1024.0 / 1024.0,
-                        file->path, postfix, samples);
+                        perf_data__size(data) / 1024.0 / 1024.0,
+                        data->file.path, postfix, samples);
         }
 
 out_delete_session:
@@ -1579,7 +1534,7 @@ static struct option __record_options[] = {
         OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
                     "list of cpus to monitor"),
         OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
-        OPT_STRING('o', "output", &record.file.path, "file",
+        OPT_STRING('o', "output", &record.data.file.path, "file",
                     "output file name"),
         OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
                         &record.opts.no_inherit_set,
@@ -1611,7 +1566,8 @@ static struct option __record_options[] = {
         OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
                         &record.opts.sample_time_set,
                         "Record the sample timestamps"),
-        OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
+        OPT_BOOLEAN_SET('P', "period", &record.opts.period, &record.opts.period_set,
+                        "Record the sample period"),
         OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
                     "don't sample"),
         OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
@@ -1644,6 +1600,9 @@ static struct option __record_options[] = {
         OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register",
                     "sample selected machine registers on interrupt,"
                     " use -I ? to list register names", parse_regs),
+        OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
+                    "sample selected machine registers on interrupt,"
+                    " use -I ? to list register names", parse_regs),
         OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
                     "Record running/enabled time of read (:S) events"),
         OPT_CALLBACK('k', "clockid", &record.opts,
@@ -1673,6 +1632,8 @@ static struct option __record_options[] = {
                     "Record build-id of all DSOs regardless of hits"),
         OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
                     "append timestamp to output filename"),
+        OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary,
+                    "Record timestamp boundary (time of first/last samples)"),
         OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
                           &record.switch_output.set, "signal,size,time",
                           "Switch output when receive SIGUSR2 or cross size,time threshold",
@@ -1786,7 +1747,7 @@ int cmd_record(int argc, const char **argv)
 
         err = -ENOMEM;
 
-        if (symbol_conf.kptr_restrict)
+        if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
                 pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict.\n\n"
@@ -1856,8 +1817,8 @@ int cmd_record(int argc, const char **argv)
                 goto out;
         }
 
-        /* Enable ignoring missing threads when -u option is defined. */
-        rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+        /* Enable ignoring missing threads when -u/-p option is defined. */
+        rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid;
 
         err = -ENOMEM;
         if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index fae4b0340750..4ad5dc649716 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -15,6 +15,7 @@
 #include "util/color.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <linux/err.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
 #include "util/values.h"
@@ -51,6 +52,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
+#include <linux/mman.h>
 
 struct report {
         struct perf_tool        tool;
@@ -60,6 +62,9 @@ struct report {
         bool                    show_threads;
         bool                    inverted_callchain;
         bool                    mem_mode;
+        bool                    stats_mode;
+        bool                    tasks_mode;
+        bool                    mmaps_mode;
         bool                    header;
         bool                    header_only;
         bool                    nonany_branch_mode;
@@ -69,7 +74,9 @@ struct report {
         const char              *cpu_list;
         const char              *symbol_filter_str;
         const char              *time_str;
-        struct perf_time_interval ptime;
+        struct perf_time_interval *ptime_range;
+        int                     range_size;
+        int                     range_num;
         float                   min_percent;
         u64                     nr_entries;
         u64                     queue_size;
@@ -162,12 +169,28 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
         struct hist_entry *he = iter->he;
         struct report *rep = arg;
         struct branch_info *bi;
+        struct perf_sample *sample = iter->sample;
+        struct perf_evsel *evsel = iter->evsel;
+        int err;
+
+        if (!ui__has_annotation())
+                return 0;
+
+        hist__account_cycles(sample->branch_stack, al, sample,
+                             rep->nonany_branch_mode);
 
         bi = he->branch_info;
+        err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx);
+        if (err)
+                goto out;
+
+        err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx);
+
         branch_type_count(&rep->brtype_stat, &bi->flags,
                           bi->from.addr, bi->to.addr);
 
-        return 0;
+out:
+        return err;
 }
 
 static int process_sample_event(struct perf_tool *tool,
@@ -186,8 +209,10 @@ static int process_sample_event(struct perf_tool *tool,
         };
         int ret = 0;
 
-        if (perf_time__skip_sample(&rep->ptime, sample->time))
+        if (perf_time__ranges_skip_sample(rep->ptime_range, rep->range_num,
+                                          sample->time)) {
                 return 0;
+        }
 
         if (machine__resolve(machine, &al, sample) < 0) {
                 pr_debug("problem processing %d event, skipping it.\n",
@@ -258,7 +283,7 @@ static int report__setup_sample_type(struct report *rep)
 {
         struct perf_session *session = rep->session;
         u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
-        bool is_pipe = perf_data_file__is_pipe(session->file);
+        bool is_pipe = perf_data__is_pipe(session->data);
 
         if (session->itrace_synth_opts->callchain ||
             (!is_pipe &&
@@ -312,9 +337,10 @@ static int report__setup_sample_type(struct report *rep)
 
         if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
                 if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-                    (sample_type & PERF_SAMPLE_STACK_USER))
+                    (sample_type & PERF_SAMPLE_STACK_USER)) {
                         callchain_param.record_mode = CALLCHAIN_DWARF;
-                else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+                        dwarf_callchain_users = true;
+                } else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
                         callchain_param.record_mode = CALLCHAIN_LBR;
                 else
                         callchain_param.record_mode = CALLCHAIN_FP;
@@ -377,6 +403,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
         if (evname != NULL)
                 ret += fprintf(fp, " of event '%s'", evname);
 
+        if (rep->time_str)
+                ret += fprintf(fp, " (time slices: %s)", rep->time_str);
+
         if (symbol_conf.show_ref_callgraph &&
             strstr(evname, "call-graph=no")) {
                 ret += fprintf(fp, ", show reference callgraph");
@@ -441,6 +470,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
         struct map *kernel_map = machine__kernel_map(&rep->session->machines.host);
         struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL;
 
+        if (perf_evlist__exclude_kernel(rep->session->evlist))
+                return;
+
         if (kernel_map == NULL ||
             (kernel_map->dso->hit &&
              (kernel_kmap->ref_reloc_sym == NULL ||
@@ -498,7 +530,8 @@ static int report__browse_hists(struct report *rep)
         case 1:
                 ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
                                                     rep->min_percent,
-                                                    &session->header.env);
+                                                    &session->header.env,
+                                                    true);
                 /*
                  * Usually "ret" is the last pressed key, and we only
                  * care if the key notifies us to switch data file.
@@ -564,12 +597,180 @@ static void report__output_resort(struct report *rep)
         ui_progress__finish();
 }
 
+static void stats_setup(struct report *rep)
+{
+        memset(&rep->tool, 0, sizeof(rep->tool));
+        rep->tool.no_warn = true;
+}
+
+static int stats_print(struct report *rep)
+{
+        struct perf_session *session = rep->session;
+
+        perf_session__fprintf_nr_events(session, stdout);
+        return 0;
+}
+
+static void tasks_setup(struct report *rep)
+{
+        memset(&rep->tool, 0, sizeof(rep->tool));
+        if (rep->mmaps_mode) {
+                rep->tool.mmap = perf_event__process_mmap;
+                rep->tool.mmap2 = perf_event__process_mmap2;
+        }
+        rep->tool.comm = perf_event__process_comm;
+        rep->tool.exit = perf_event__process_exit;
+        rep->tool.fork = perf_event__process_fork;
+        rep->tool.no_warn = true;
+}
+
+struct task {
+        struct thread           *thread;
+        struct list_head         list;
+        struct list_head         children;
+};
+
+static struct task *tasks_list(struct task *task, struct machine *machine)
+{
+        struct thread *parent_thread, *thread = task->thread;
+        struct task   *parent_task;
+
+        /* Already listed. */
+        if (!list_empty(&task->list))
+                return NULL;
+
+        /* Last one in the chain. */
+        if (thread->ppid == -1)
+                return task;
+
+        parent_thread = machine__find_thread(machine, -1, thread->ppid);
+        if (!parent_thread)
+                return ERR_PTR(-ENOENT);
+
+        parent_task = thread__priv(parent_thread);
+        list_add_tail(&task->list, &parent_task->children);
+        return tasks_list(parent_task, machine);
+}
+
+static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
+{
+        size_t printed = 0;
+        struct rb_node *nd;
+
+        for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
+                struct map *map = rb_entry(nd, struct map, rb_node);
+
+                printed += fprintf(fp, "%*s  %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n",
+                                   indent, "", map->start, map->end,
+                                   map->prot & PROT_READ ? 'r' : '-',
+                                   map->prot & PROT_WRITE ? 'w' : '-',
+                                   map->prot & PROT_EXEC ? 'x' : '-',
+                                   map->flags & MAP_SHARED ? 's' : 'p',
+                                   map->pgoff,
+                                   map->ino, map->dso->name);
+        }
+
+        return printed;
+}
+
+static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp)
+{
+        int printed = 0, i;
+        for (i = 0; i < MAP__NR_TYPES; ++i)
+                printed += maps__fprintf_task(&mg->maps[i], indent, fp);
+        return printed;
+}
+
+static void task__print_level(struct task *task, FILE *fp, int level)
+{
+        struct thread *thread = task->thread;
+        struct task *child;
+        int comm_indent = fprintf(fp, "  %8d %8d %8d |%*s",
+                                  thread->pid_, thread->tid, thread->ppid,
+                                  level, "");
+
+        fprintf(fp, "%s\n", thread__comm_str(thread));
+
+        map_groups__fprintf_task(thread->mg, comm_indent, fp);
+
+        if (!list_empty(&task->children)) {
+                list_for_each_entry(child, &task->children, list)
+                        task__print_level(child, fp, level + 1);
+        }
+}
+
+static int tasks_print(struct report *rep, FILE *fp)
+{
+        struct perf_session *session = rep->session;
+        struct machine      *machine = &session->machines.host;
+        struct task *tasks, *task;
+        unsigned int nr = 0, itask = 0, i;
+        struct rb_node *nd;
+        LIST_HEAD(list);
+
+        /*
+         * No locking needed while accessing machine->threads,
+         * because --tasks is single threaded command.
+         */
+
+        /* Count all the threads. */
+        for (i = 0; i < THREADS__TABLE_SIZE; i++)
+                nr += machine->threads[i].nr;
+
+        tasks = malloc(sizeof(*tasks) * nr);
+        if (!tasks)
+                return -ENOMEM;
+
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+
+                for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+                        task = tasks + itask++;
+
+                        task->thread = rb_entry(nd, struct thread, rb_node);
+                        INIT_LIST_HEAD(&task->children);
+                        INIT_LIST_HEAD(&task->list);
+                        thread__set_priv(task->thread, task);
+                }
+        }
+
+        /*
+         * Iterate every task down to the unprocessed parent
+         * and link all in task children list. Task with no
+         * parent is added into 'list'.
+         */
+        for (itask = 0; itask < nr; itask++) {
+                task = tasks + itask;
+
+                if (!list_empty(&task->list))
+                        continue;
+
+                task = tasks_list(task, machine);
+                if (IS_ERR(task)) {
+                        pr_err("Error: failed to process tasks\n");
+                        free(tasks);
+                        return PTR_ERR(task);
+                }
+
+                if (task)
+                        list_add_tail(&task->list, &list);
+        }
+
+        fprintf(fp, "# %8s %8s %8s  %s\n", "pid", "tid", "ppid", "comm");
+
+        list_for_each_entry(task, &list, list)
+                task__print_level(task, fp, 0);
+
+        free(tasks);
+        return 0;
+}
+
 static int __cmd_report(struct report *rep)
 {
         int ret;
         struct perf_session *session = rep->session;
         struct perf_evsel *pos;
-        struct perf_data_file *file = session->file;
+        struct perf_data *data = session->data;
 
         signal(SIGINT, sig_handler);
 
@@ -595,12 +796,24 @@ static int __cmd_report(struct report *rep)
                 return ret;
         }
 
+        if (rep->stats_mode)
+                stats_setup(rep);
+
+        if (rep->tasks_mode)
+                tasks_setup(rep);
+
         ret = perf_session__process_events(session);
         if (ret) {
                 ui__error("failed to process sample\n");
                 return ret;
         }
 
+        if (rep->stats_mode)
+                return stats_print(rep);
+
+        if (rep->tasks_mode)
+                return tasks_print(rep, stdout);
+
         report__warn_kptr_restrict(rep);
 
         evlist__for_each_entry(session->evlist, pos)
@@ -638,7 +851,7 @@ static int __cmd_report(struct report *rep)
                 rep->nr_entries += evsel__hists(pos)->nr_entries;
 
         if (rep->nr_entries == 0) {
-                ui__error("The %s file has no samples!\n", file->path);
+                ui__error("The %s file has no samples!\n", data->file.path);
                 return 0;
         }
 
@@ -757,6 +970,9 @@ int cmd_report(int argc, const char **argv)
         OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                     "dump raw trace in ASCII"),
+        OPT_BOOLEAN(0, "stats", &report.stats_mode, "Display event stats"),
+        OPT_BOOLEAN(0, "tasks", &report.tasks_mode, "Display recorded tasks"),
+        OPT_BOOLEAN(0, "mmaps", &report.mmaps_mode, "Display recorded tasks memory maps"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
         OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
@@ -880,7 +1096,7 @@ int cmd_report(int argc, const char **argv)
                     "Show inline function"),
         OPT_END()
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode  = PERF_DATA_MODE_READ,
         };
         int ret = hists__init();
@@ -904,6 +1120,9 @@ int cmd_report(int argc, const char **argv)
                 report.symbol_filter_str = argv[0];
         }
 
+        if (report.mmaps_mode)
+                report.tasks_mode = true;
+
         if (quiet)
                 perf_quiet_option();
 
@@ -918,13 +1137,6 @@ int cmd_report(int argc, const char **argv)
                 return -EINVAL;
         }
 
-        if (report.use_stdio)
-                use_browser = 0;
-        else if (report.use_tui)
-                use_browser = 1;
-        else if (report.use_gtk)
-                use_browser = 2;
-
         if (report.inverted_callchain)
                 callchain_param.order = ORDER_CALLER;
         if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
@@ -941,11 +1153,11 @@ int cmd_report(int argc, const char **argv)
                         input_name = "perf.data";
         }
 
-        file.path  = input_name;
-        file.force = symbol_conf.force;
+        data.file.path = input_name;
+        data.force     = symbol_conf.force;
 
 repeat:
-        session = perf_session__new(&file, false, &report.tool);
+        session = perf_session__new(&data, false, &report.tool);
         if (session == NULL)
                 return -1;
 
@@ -1011,6 +1223,13 @@ repeat:
                 perf_hpp_list.need_collapse = true;
         }
 
+        if (report.use_stdio)
+                use_browser = 0;
+        else if (report.use_tui)
+                use_browser = 1;
+        else if (report.use_gtk)
+                use_browser = 2;
+
         /* Force tty output for header output and per-thread stat. */
         if (report.header || report.header_only || report.show_threads)
                 use_browser = 0;
@@ -1018,6 +1237,12 @@ repeat:
                 report.tool.show_feat_hdr = SHOW_FEAT_HEADER;
         if (report.show_full_info)
                 report.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO;
+        if (report.stats_mode || report.tasks_mode)
+                use_browser = 0;
+        if (report.stats_mode && report.tasks_mode) {
+                pr_err("Error: --tasks and --mmaps can't be used together with --stats\n");
+                goto error;
+        }
 
         if (strcmp(input_name, "-") != 0)
                 setup_browser(true);
@@ -1040,7 +1265,8 @@ repeat:
                         ret = 0;
                         goto error;
                 }
-        } else if (use_browser == 0 && !quiet) {
+        } else if (use_browser == 0 && !quiet &&
+                   !report.stats_mode && !report.tasks_mode) {
                 fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
                       stdout);
         }
@@ -1074,9 +1300,36 @@ repeat:
         if (symbol__init(&session->header.env) < 0)
                 goto error;
 
-        if (perf_time__parse_str(&report.ptime, report.time_str) != 0) {
-                pr_err("Invalid time string\n");
-                return -EINVAL;
+        report.ptime_range = perf_time__range_alloc(report.time_str,
+                                                    &report.range_size);
+        if (!report.ptime_range) {
+                ret = -ENOMEM;
+                goto error;
+        }
+
+        if (perf_time__parse_str(report.ptime_range, report.time_str) != 0) {
+                if (session->evlist->first_sample_time == 0 &&
+                    session->evlist->last_sample_time == 0) {
+                        pr_err("HINT: no first/last sample time found in perf data.\n"
+                               "Please use latest perf binary to execute 'perf record'\n"
+                               "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
+                        ret = -EINVAL;
+                        goto error;
+                }
+
+                report.range_num = perf_time__percent_parse_str(
+                                        report.ptime_range, report.range_size,
+                                        report.time_str,
+                                        session->evlist->first_sample_time,
+                                        session->evlist->last_sample_time);
+
+                if (report.range_num < 0) {
+                        pr_err("Invalid time string\n");
+                        ret = -EINVAL;
+                        goto error;
+                }
+        } else {
+                report.range_num = 1;
         }
 
         sort__setup_elide(stdout);
@@ -1089,6 +1342,8 @@ repeat:
                 ret = 0;
 
 error:
+        zfree(&report.ptime_range);
+
         perf_session__delete(session);
         return ret;
 }
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f380d91ee609..83283fedb00f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1701,14 +1701,16 @@ static int perf_sched__read_events(struct perf_sched *sched)
                 { "sched:sched_migrate_task", process_sched_migrate_task_event, },
         };
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = sched->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = sched->force,
         };
         int rc = -1;
 
-        session = perf_session__new(&file, false, &sched->tool);
+        session = perf_session__new(&data, false, &sched->tool);
         if (session == NULL) {
                 pr_debug("No Memory for session\n");
                 return -1;
@@ -2903,10 +2905,12 @@ static int perf_sched__timehist(struct perf_sched *sched)
         const struct perf_evsel_str_handler migrate_handlers[] = {
                 { "sched:sched_migrate_task", timehist_migrate_task_event, },
         };
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = sched->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = sched->force,
         };
 
         struct perf_session *session;
@@ -2931,7 +2935,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
 
         symbol_conf.use_callchain = sched->show_callchain;
 
-        session = perf_session__new(&file, false, &sched->tool);
+        session = perf_session__new(&data, false, &sched->tool);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -3364,6 +3368,10 @@ int cmd_sched(int argc, const char **argv)
         OPT_STRING(0, "time", &sched.time_str, "str",
                    "Time span for analysis (start,stop)"),
         OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
+        OPT_STRING('p', "pid", &symbol_conf.pid_list_str, "pid[,pid...]",
+                   "analyze events only for given process id(s)"),
+        OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
+                   "analyze events only for given thread id(s)"),
         OPT_PARENT(sched_options)
         };
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 0fe02758de7d..ab19a6ee4093 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -22,9 +22,11 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/color.h"
 #include "util/string2.h"
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
+#include "util/path.h"
 #include "print_binary.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
@@ -40,6 +42,7 @@
 #include <sys/param.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <unistd.h>
 
 #include "sane_ctype.h"
@@ -89,6 +92,9 @@ enum perf_output_field {
         PERF_OUTPUT_BRSTACKOFF      = 1U << 24,
         PERF_OUTPUT_SYNTH           = 1U << 25,
         PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
+        PERF_OUTPUT_UREGS           = 1U << 27,
+        PERF_OUTPUT_METRIC          = 1U << 28,
+        PERF_OUTPUT_MISC            = 1U << 29,
 };
 
 struct output_option {
@@ -110,6 +116,7 @@ struct output_option {
         {.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
         {.str = "period", .field = PERF_OUTPUT_PERIOD},
         {.str = "iregs", .field = PERF_OUTPUT_IREGS},
+        {.str = "uregs", .field = PERF_OUTPUT_UREGS},
         {.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
         {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
         {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
@@ -122,6 +129,8 @@ struct output_option {
         {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
         {.str = "synth", .field = PERF_OUTPUT_SYNTH},
         {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
+        {.str = "metric", .field = PERF_OUTPUT_METRIC},
+        {.str = "misc", .field = PERF_OUTPUT_MISC},
 };
 
 enum {
@@ -209,6 +218,58 @@ static struct {
         },
 };
 
+struct perf_evsel_script {
+       char *filename;
+       FILE *fp;
+       u64  samples;
+       /* For metric output */
+       u64  val;
+       int  gnum;
+};
+
+static inline struct perf_evsel_script *evsel_script(struct perf_evsel *evsel)
+{
+        return (struct perf_evsel_script *)evsel->priv;
+}
+
+static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel,
+                                                        struct perf_data *data)
+{
+        struct perf_evsel_script *es = zalloc(sizeof(*es));
+
+        if (es != NULL) {
+                if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0)
+                        goto out_free;
+                es->fp = fopen(es->filename, "w");
+                if (es->fp == NULL)
+                        goto out_free_filename;
+        }
+
+        return es;
+out_free_filename:
+        zfree(&es->filename);
+out_free:
+        free(es);
+        return NULL;
+}
+
+static void perf_evsel_script__delete(struct perf_evsel_script *es)
+{
+        zfree(&es->filename);
+        fclose(es->fp);
+        es->fp = NULL;
+        free(es);
+}
+
+static int perf_evsel_script__fprintf(struct perf_evsel_script *es, FILE *fp)
+{
+        struct stat st;
+
+        fstat(fileno(es->fp), &st);
+        return fprintf(fp, "[ perf script: Wrote %.3f MB %s (%" PRIu64 " samples) ]\n",
+                       st.st_size / 1024.0 / 1024.0, es->filename, es->samples);
+}
+
 static inline int output_type(unsigned int type)
 {
         switch (type) {
@@ -376,16 +437,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                            PERF_OUTPUT_CPU, allow_user_set))
                 return -EINVAL;
 
-        if (PRINT_FIELD(PERIOD) &&
-                perf_evsel__check_stype(evsel, PERF_SAMPLE_PERIOD, "PERIOD",
-                                        PERF_OUTPUT_PERIOD))
-                return -EINVAL;
-
         if (PRINT_FIELD(IREGS) &&
                 perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS",
                                         PERF_OUTPUT_IREGS))
                 return -EINVAL;
 
+        if (PRINT_FIELD(UREGS) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS",
+                                        PERF_OUTPUT_UREGS))
+                return -EINVAL;
+
         if (PRINT_FIELD(PHYS_ADDR) &&
                 perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
                                         PERF_OUTPUT_PHYS_ADDR))
@@ -494,51 +555,118 @@ out:
         return 0;
 }
 
-static void print_sample_iregs(struct perf_sample *sample,
-                          struct perf_event_attr *attr)
+static int perf_sample__fprintf_iregs(struct perf_sample *sample,
+                                      struct perf_event_attr *attr, FILE *fp)
 {
         struct regs_dump *regs = &sample->intr_regs;
         uint64_t mask = attr->sample_regs_intr;
         unsigned i = 0, r;
+        int printed = 0;
 
         if (!regs)
-                return;
+                return 0;
 
         for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
                 u64 val = regs->regs[i++];
-                printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+                printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
         }
+
+        return printed;
 }
 
-static void print_sample_start(struct perf_sample *sample,
-                               struct thread *thread,
-                               struct perf_evsel *evsel)
+static int perf_sample__fprintf_uregs(struct perf_sample *sample,
+                                      struct perf_event_attr *attr, FILE *fp)
+{
+        struct regs_dump *regs = &sample->user_regs;
+        uint64_t mask = attr->sample_regs_user;
+        unsigned i = 0, r;
+        int printed = 0;
+
+        if (!regs || !regs->regs)
+                return 0;
+
+        printed += fprintf(fp, " ABI:%" PRIu64 " ", regs->abi);
+
+        for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+                u64 val = regs->regs[i++];
+                printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+        }
+
+        return printed;
+}
+
+static int perf_sample__fprintf_start(struct perf_sample *sample,
+                                      struct thread *thread,
+                                      struct perf_evsel *evsel,
+                                      u32 type, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         unsigned long secs;
         unsigned long long nsecs;
+        int printed = 0;
 
         if (PRINT_FIELD(COMM)) {
                 if (latency_format)
-                        printf("%8.8s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%8.8s ", thread__comm_str(thread));
                 else if (PRINT_FIELD(IP) && symbol_conf.use_callchain)
-                        printf("%s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%s ", thread__comm_str(thread));
                 else
-                        printf("%16s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%16s ", thread__comm_str(thread));
         }
 
         if (PRINT_FIELD(PID) && PRINT_FIELD(TID))
-                printf("%5d/%-5d ", sample->pid, sample->tid);
+                printed += fprintf(fp, "%5d/%-5d ", sample->pid, sample->tid);
         else if (PRINT_FIELD(PID))
-                printf("%5d ", sample->pid);
+                printed += fprintf(fp, "%5d ", sample->pid);
         else if (PRINT_FIELD(TID))
-                printf("%5d ", sample->tid);
+                printed += fprintf(fp, "%5d ", sample->tid);
 
         if (PRINT_FIELD(CPU)) {
                 if (latency_format)
-                        printf("%3d ", sample->cpu);
+                        printed += fprintf(fp, "%3d ", sample->cpu);
                 else
-                        printf("[%03d] ", sample->cpu);
+                        printed += fprintf(fp, "[%03d] ", sample->cpu);
+        }
+
+        if (PRINT_FIELD(MISC)) {
+                int ret = 0;
+
+                #define has(m) \
+                        (sample->misc & PERF_RECORD_MISC_##m) == PERF_RECORD_MISC_##m
+
+                if (has(KERNEL))
+                        ret += fprintf(fp, "K");
+                if (has(USER))
+                        ret += fprintf(fp, "U");
+                if (has(HYPERVISOR))
+                        ret += fprintf(fp, "H");
+                if (has(GUEST_KERNEL))
+                        ret += fprintf(fp, "G");
+                if (has(GUEST_USER))
+                        ret += fprintf(fp, "g");
+
+                switch (type) {
+                case PERF_RECORD_MMAP:
+                case PERF_RECORD_MMAP2:
+                        if (has(MMAP_DATA))
+                                ret += fprintf(fp, "M");
+                        break;
+                case PERF_RECORD_COMM:
+                        if (has(COMM_EXEC))
+                                ret += fprintf(fp, "E");
+                        break;
+                case PERF_RECORD_SWITCH:
+                case PERF_RECORD_SWITCH_CPU_WIDE:
+                        if (has(SWITCH_OUT))
+                                ret += fprintf(fp, "S");
+                default:
+                        break;
+                }
+
+                #undef has
+
+                ret += fprintf(fp, "%*s", 6 - ret, " ");
+                printed += ret;
         }
 
         if (PRINT_FIELD(TIME)) {
@@ -547,13 +675,15 @@ static void print_sample_start(struct perf_sample *sample,
                 nsecs -= secs * NSEC_PER_SEC;
 
                 if (nanosecs)
-                        printf("%5lu.%09llu: ", secs, nsecs);
+                        printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs);
                 else {
                         char sample_time[32];
                         timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time));
-                        printf("%12s: ", sample_time);
+                        printed += fprintf(fp, "%12s: ", sample_time);
                 }
         }
+
+        return printed;
 }
 
 static inline char
@@ -565,16 +695,17 @@ mispred_str(struct branch_entry *br)
         return br->flags.predicted ? 'P' : 'M';
 }
 
-static void print_sample_brstack(struct perf_sample *sample,
-                                 struct thread *thread,
-                                 struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstack(struct perf_sample *sample,
+                                        struct thread *thread,
+                                        struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
                 from = br->entries[i].from;
@@ -587,38 +718,41 @@ static void print_sample_brstack(struct perf_sample *sample,
                         thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
                 }
 
-                printf(" 0x%"PRIx64, from);
+                printed += fprintf(fp, " 0x%"PRIx64, from);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
 
-                printf("/0x%"PRIx64, to);
+                printed += fprintf(fp, "/0x%"PRIx64, to);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
 
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str( br->entries + i),
                         br->entries[i].flags.in_tx? 'X' : '-',
                         br->entries[i].flags.abort? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 
-static void print_sample_brstacksym(struct perf_sample *sample,
-                                    struct thread *thread,
-                                    struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
+                                           struct thread *thread,
+                                           struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
 
@@ -635,37 +769,40 @@ static void print_sample_brstacksym(struct perf_sample *sample,
                 if (alt.map)
                         alt.sym = map__find_symbol(alt.map, alt.addr);
 
-                symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
+                printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                putchar('/');
-                symbol__fprintf_symname_offs(alt.sym, &alt, stdout);
+                printed += fprintf(fp, "%c", '/');
+                printed += symbol__fprintf_symname_offs(alt.sym, &alt, fp);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str( br->entries + i),
                         br->entries[i].flags.in_tx? 'X' : '-',
                         br->entries[i].flags.abort? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 
-static void print_sample_brstackoff(struct perf_sample *sample,
-                                    struct thread *thread,
-                                    struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
+                                           struct thread *thread,
+                                           struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
 
@@ -682,24 +819,26 @@ static void print_sample_brstackoff(struct perf_sample *sample,
                 if (alt.map && !alt.map->dso->adjust_symbols)
                         to = map__map_ip(alt.map, to);
 
-                printf(" 0x%"PRIx64, from);
+                printed += fprintf(fp, " 0x%"PRIx64, from);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/0x%"PRIx64, to);
+                printed += fprintf(fp, "/0x%"PRIx64, to);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str(br->entries + i),
                         br->entries[i].flags.in_tx ? 'X' : '-',
                         br->entries[i].flags.abort ? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 #define MAXBB 16384UL
 
@@ -727,27 +866,26 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
          * but the exit is not. Let the caller patch it up.
          */
         if (kernel != machine__kernel_ip(machine, end)) {
-                printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n",
-                                start, end);
+                pr_debug("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n", start, end);
                 return -ENXIO;
         }
 
         memset(&al, 0, sizeof(al));
         if (end - start > MAXBB - MAXINSN) {
                 if (last)
-                        printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
+                        pr_debug("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
                 else
-                        printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
+                        pr_debug("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
                 return 0;
         }
 
         thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
         if (!al.map || !al.map->dso) {
-                printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+                pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
                 return 0;
         }
         if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
-                printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+                pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
                 return 0;
         }
 
@@ -760,36 +898,35 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
         *is64bit = al.map->dso->is_64_bit;
         if (len <= 0)
-                printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
+                pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
                         start, end);
         return len;
 }
 
-static void print_jump(uint64_t ip, struct branch_entry *en,
-                       struct perf_insn *x, u8 *inbuf, int len,
-                       int insn)
+static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
+                            struct perf_insn *x, u8 *inbuf, int len,
+                            int insn, FILE *fp)
 {
-        printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s",
-               ip,
-               dump_insn(x, ip, inbuf, len, NULL),
-               en->flags.predicted ? " PRED" : "",
-               en->flags.mispred ? " MISPRED" : "",
-               en->flags.in_tx ? " INTX" : "",
-               en->flags.abort ? " ABORT" : "");
+        int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
+                              dump_insn(x, ip, inbuf, len, NULL),
+                              en->flags.predicted ? " PRED" : "",
+                              en->flags.mispred ? " MISPRED" : "",
+                              en->flags.in_tx ? " INTX" : "",
+                              en->flags.abort ? " ABORT" : "");
         if (en->flags.cycles) {
-                printf(" %d cycles", en->flags.cycles);
+                printed += fprintf(fp, " %d cycles", en->flags.cycles);
                 if (insn)
-                        printf(" %.2f IPC", (float)insn / en->flags.cycles);
+                        printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
         }
-        putchar('\n');
+        return printed + fprintf(fp, "\n");
 }
 
-static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
-                         uint64_t addr, struct symbol **lastsym,
-                         struct perf_event_attr *attr)
+static int ip__fprintf_sym(uint64_t addr, struct thread *thread,
+                           u8 cpumode, int cpu, struct symbol **lastsym,
+                           struct perf_event_attr *attr, FILE *fp)
 {
         struct addr_location al;
-        int off;
+        int off, printed = 0;
 
         memset(&al, 0, sizeof(al));
 
@@ -798,7 +935,7 @@ static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
                 thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
                                       addr, &al);
         if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
-                return;
+                return 0;
 
         al.cpu = cpu;
         al.sym = NULL;
@@ -806,37 +943,39 @@ static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
                 al.sym = map__find_symbol(al.map, al.addr);
 
         if (!al.sym)
-                return;
+                return 0;
 
         if (al.addr < al.sym->end)
                 off = al.addr - al.sym->start;
         else
                 off = al.addr - al.map->start - al.sym->start;
-        printf("\t%s", al.sym->name);
+        printed += fprintf(fp, "\t%s", al.sym->name);
         if (off)
-                printf("%+d", off);
-        putchar(':');
+                printed += fprintf(fp, "%+d", off);
+        printed += fprintf(fp, ":");
         if (PRINT_FIELD(SRCLINE))
-                map__fprintf_srcline(al.map, al.addr, "\t", stdout);
-        putchar('\n');
+                printed += map__fprintf_srcline(al.map, al.addr, "\t", fp);
+        printed += fprintf(fp, "\n");
         *lastsym = al.sym;
+
+        return printed;
 }
 
-static void print_sample_brstackinsn(struct perf_sample *sample,
-                                     struct thread *thread,
-                                     struct perf_event_attr *attr,
-                                     struct machine *machine)
+static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
+                                            struct thread *thread,
+                                            struct perf_event_attr *attr,
+                                            struct machine *machine, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         u64 start, end;
-        int i, insn, len, nr, ilen;
+        int i, insn, len, nr, ilen, printed = 0;
         struct perf_insn x;
         u8 buffer[MAXBB];
         unsigned off;
         struct symbol *lastsym = NULL;
 
         if (!(br && br->nr))
-                return;
+                return 0;
         nr = br->nr;
         if (max_blocks && nr > max_blocks + 1)
                 nr = max_blocks + 1;
@@ -844,17 +983,17 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
         x.thread = thread;
         x.cpu = sample->cpu;
 
-        putchar('\n');
+        printed += fprintf(fp, "%c", '\n');
 
         /* Handle first from jump, of which we don't know the entry. */
         len = grab_bb(buffer, br->entries[nr-1].from,
                         br->entries[nr-1].from,
                         machine, thread, &x.is64bit, &x.cpumode, false);
         if (len > 0) {
-                print_ip_sym(thread, x.cpumode, x.cpu,
-                             br->entries[nr - 1].from, &lastsym, attr);
-                print_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-                            &x, buffer, len, 0);
+                printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
+                                           x.cpumode, x.cpu, &lastsym, attr, fp);
+                printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+                                            &x, buffer, len, 0, fp);
         }
 
         /* Print all blocks */
@@ -880,13 +1019,13 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
                 for (off = 0;; off += ilen) {
                         uint64_t ip = start + off;
 
-                        print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr);
+                        printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
                         if (ip == end) {
-                                print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn);
+                                printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
                                 break;
                         } else {
-                                printf("\t%016" PRIx64 "\t%s\n", ip,
-                                        dump_insn(&x, ip, buffer + off, len - off, &ilen));
+                                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
+                                                   dump_insn(&x, ip, buffer + off, len - off, &ilen));
                                 if (ilen == 0)
                                         break;
                                 insn++;
@@ -899,9 +1038,9 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
          * has not been executed yet.
          */
         if (br->entries[0].from == sample->ip)
-                return;
+                goto out;
         if (br->entries[0].flags.abort)
-                return;
+                goto out;
 
         /*
          * Print final block upto sample
@@ -909,58 +1048,61 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
         start = br->entries[0].to;
         end = sample->ip;
         len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
-        print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr);
+        printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
         if (len <= 0) {
                 /* Print at least last IP if basic block did not work */
                 len = grab_bb(buffer, sample->ip, sample->ip,
                               machine, thread, &x.is64bit, &x.cpumode, false);
                 if (len <= 0)
-                        return;
+                        goto out;
 
-                printf("\t%016" PRIx64 "\t%s\n", sample->ip,
+                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
                         dump_insn(&x, sample->ip, buffer, len, NULL));
-                return;
+                goto out;
         }
         for (off = 0; off <= end - start; off += ilen) {
-                printf("\t%016" PRIx64 "\t%s\n", start + off,
-                        dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
+                                   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
                 if (ilen == 0)
                         break;
         }
+out:
+        return printed;
 }
 
-static void print_sample_addr(struct perf_sample *sample,
-                          struct thread *thread,
-                          struct perf_event_attr *attr)
+static int perf_sample__fprintf_addr(struct perf_sample *sample,
+                                     struct thread *thread,
+                                     struct perf_event_attr *attr, FILE *fp)
 {
         struct addr_location al;
-
-        printf("%16" PRIx64, sample->addr);
+        int printed = fprintf(fp, "%16" PRIx64, sample->addr);
 
         if (!sample_addr_correlates_sym(attr))
-                return;
+                goto out;
 
         thread__resolve(thread, &al, sample);
 
         if (PRINT_FIELD(SYM)) {
-                printf(" ");
+                printed += fprintf(fp, " ");
                 if (PRINT_FIELD(SYMOFFSET))
-                        symbol__fprintf_symname_offs(al.sym, &al, stdout);
+                        printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
                 else
-                        symbol__fprintf_symname(al.sym, stdout);
+                        printed += symbol__fprintf_symname(al.sym, fp);
         }
 
         if (PRINT_FIELD(DSO)) {
-                printf(" (");
-                map__fprintf_dsoname(al.map, stdout);
-                printf(")");
+                printed += fprintf(fp, " (");
+                printed += map__fprintf_dsoname(al.map, fp);
+                printed += fprintf(fp, ")");
         }
+out:
+        return printed;
 }
 
-static void print_sample_callindent(struct perf_sample *sample,
-                                    struct perf_evsel *evsel,
-                                    struct thread *thread,
-                                    struct addr_location *al)
+static int perf_sample__fprintf_callindent(struct perf_sample *sample,
+                                           struct perf_evsel *evsel,
+                                           struct thread *thread,
+                                           struct addr_location *al, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         size_t depth = thread_stack__depth(thread);
@@ -995,12 +1137,12 @@ static void print_sample_callindent(struct perf_sample *sample,
         }
 
         if (name)
-                len = printf("%*s%s", (int)depth * 4, "", name);
+                len = fprintf(fp, "%*s%s", (int)depth * 4, "", name);
         else if (ip)
-                len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip);
+                len = fprintf(fp, "%*s%16" PRIx64, (int)depth * 4, "", ip);
 
         if (len < 0)
-                return;
+                return len;
 
         /*
          * Try to keep the output length from changing frequently so that the
@@ -1010,39 +1152,46 @@ static void print_sample_callindent(struct perf_sample *sample,
                 spacing = round_up(len + 4, 32);
 
         if (len < spacing)
-                printf("%*s", spacing - len, "");
+                len += fprintf(fp, "%*s", spacing - len, "");
+
+        return len;
 }
 
-static void print_insn(struct perf_sample *sample,
-                       struct perf_event_attr *attr,
-                       struct thread *thread,
-                       struct machine *machine)
+static int perf_sample__fprintf_insn(struct perf_sample *sample,
+                                     struct perf_event_attr *attr,
+                                     struct thread *thread,
+                                     struct machine *machine, FILE *fp)
 {
+        int printed = 0;
+
         if (PRINT_FIELD(INSNLEN))
-                printf(" ilen: %d", sample->insn_len);
+                printed += fprintf(fp, " ilen: %d", sample->insn_len);
         if (PRINT_FIELD(INSN)) {
                 int i;
 
-                printf(" insn:");
+                printed += fprintf(fp, " insn:");
                 for (i = 0; i < sample->insn_len; i++)
-                        printf(" %02x", (unsigned char)sample->insn[i]);
+                        printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]);
         }
         if (PRINT_FIELD(BRSTACKINSN))
-                print_sample_brstackinsn(sample, thread, attr, machine);
+                printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
+
+        return printed;
 }
 
-static void print_sample_bts(struct perf_sample *sample,
-                             struct perf_evsel *evsel,
-                             struct thread *thread,
-                             struct addr_location *al,
-                             struct machine *machine)
+static int perf_sample__fprintf_bts(struct perf_sample *sample,
+                                    struct perf_evsel *evsel,
+                                    struct thread *thread,
+                                    struct addr_location *al,
+                                    struct machine *machine, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         unsigned int type = output_type(attr->type);
         bool print_srcline_last = false;
+        int printed = 0;
 
         if (PRINT_FIELD(CALLINDENT))
-                print_sample_callindent(sample, evsel, thread, al);
+                printed += perf_sample__fprintf_callindent(sample, evsel, thread, al, fp);
 
         /* print branch_from information */
         if (PRINT_FIELD(IP)) {
@@ -1055,31 +1204,30 @@ static void print_sample_bts(struct perf_sample *sample,
                         cursor = &callchain_cursor;
 
                 if (cursor == NULL) {
-                        putchar(' ');
+                        printed += fprintf(fp, " ");
                         if (print_opts & EVSEL__PRINT_SRCLINE) {
                                 print_srcline_last = true;
                                 print_opts &= ~EVSEL__PRINT_SRCLINE;
                         }
                 } else
-                        putchar('\n');
+                        printed += fprintf(fp, "\n");
 
-                sample__fprintf_sym(sample, al, 0, print_opts, cursor, stdout);
+                printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, fp);
         }
 
         /* print branch_to information */
         if (PRINT_FIELD(ADDR) ||
             ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
              !output[type].user_set)) {
-                printf(" => ");
-                print_sample_addr(sample, thread, attr);
+                printed += fprintf(fp, " => ");
+                printed += perf_sample__fprintf_addr(sample, thread, attr, fp);
         }
 
         if (print_srcline_last)
-                map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
+                printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
 
-        print_insn(sample, attr, thread, machine);
-
-        printf("\n");
+        printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+        return printed + fprintf(fp, "\n");
 }
 
 static struct {
@@ -1102,7 +1250,7 @@ static struct {
         {0, NULL}
 };
 
-static void print_sample_flags(u32 flags)
+static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 {
         const char *chars = PERF_IP_FLAG_CHARS;
         const int n = strlen(PERF_IP_FLAG_CHARS);
@@ -1129,9 +1277,9 @@ static void print_sample_flags(u32 flags)
         str[pos] = 0;
 
         if (name)
-                printf("  %-7s%4s ", name, in_tx ? "(x)" : "");
-        else
-                printf("  %-11s ", str);
+                return fprintf(fp, "  %-7s%4s ", name, in_tx ? "(x)" : "");
+
+        return fprintf(fp, "  %-11s ", str);
 }
 
 struct printer_data {
@@ -1140,40 +1288,40 @@ struct printer_data {
         bool is_printable;
 };
 
-static void
-print_sample_bpf_output_printer(enum binary_printer_ops op,
-                                unsigned int val,
-                                void *extra)
+static int sample__fprintf_bpf_output(enum binary_printer_ops op,
+                                      unsigned int val,
+                                      void *extra, FILE *fp)
 {
         unsigned char ch = (unsigned char)val;
         struct printer_data *printer_data = extra;
+        int printed = 0;
 
         switch (op) {
         case BINARY_PRINT_DATA_BEGIN:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 break;
         case BINARY_PRINT_LINE_BEGIN:
-                printf("%17s", !printer_data->line_no ? "BPF output:" :
+                printed += fprintf(fp, "%17s", !printer_data->line_no ? "BPF output:" :
                                                         "           ");
                 break;
         case BINARY_PRINT_ADDR:
-                printf(" %04x:", val);
+                printed += fprintf(fp, " %04x:", val);
                 break;
         case BINARY_PRINT_NUM_DATA:
-                printf(" %02x", val);
+                printed += fprintf(fp, " %02x", val);
                 break;
         case BINARY_PRINT_NUM_PAD:
-                printf("   ");
+                printed += fprintf(fp, "   ");
                 break;
         case BINARY_PRINT_SEP:
-                printf("  ");
+                printed += fprintf(fp, "  ");
                 break;
         case BINARY_PRINT_CHAR_DATA:
                 if (printer_data->hit_nul && ch)
                         printer_data->is_printable = false;
 
                 if (!isprint(ch)) {
-                        printf("%c", '.');
+                        printed += fprintf(fp, "%c", '.');
 
                         if (!printer_data->is_printable)
                                 break;
@@ -1183,154 +1331,154 @@ print_sample_bpf_output_printer(enum binary_printer_ops op,
                         else
                                 printer_data->is_printable = false;
                 } else {
-                        printf("%c", ch);
+                        printed += fprintf(fp, "%c", ch);
                 }
                 break;
         case BINARY_PRINT_CHAR_PAD:
-                printf(" ");
+                printed += fprintf(fp, " ");
                 break;
         case BINARY_PRINT_LINE_END:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 printer_data->line_no++;
                 break;
         case BINARY_PRINT_DATA_END:
         default:
                 break;
         }
+
+        return printed;
 }
 
-static void print_sample_bpf_output(struct perf_sample *sample)
+static int perf_sample__fprintf_bpf_output(struct perf_sample *sample, FILE *fp)
 {
         unsigned int nr_bytes = sample->raw_size;
         struct printer_data printer_data = {0, false, true};
-
-        print_binary(sample->raw_data, nr_bytes, 8,
-                     print_sample_bpf_output_printer, &printer_data);
+        int printed = binary__fprintf(sample->raw_data, nr_bytes, 8,
+                                      sample__fprintf_bpf_output, &printer_data, fp);
 
         if (printer_data.is_printable && printer_data.hit_nul)
-                printf("%17s \"%s\"\n", "BPF string:",
-                       (char *)(sample->raw_data));
+                printed += fprintf(fp, "%17s \"%s\"\n", "BPF string:", (char *)(sample->raw_data));
+
+        return printed;
 }
 
-static void print_sample_spacing(int len, int spacing)
+static int perf_sample__fprintf_spacing(int len, int spacing, FILE *fp)
 {
         if (len > 0 && len < spacing)
-                printf("%*s", spacing - len, "");
+                return fprintf(fp, "%*s", spacing - len, "");
+
+        return 0;
 }
 
-static void print_sample_pt_spacing(int len)
+static int perf_sample__fprintf_pt_spacing(int len, FILE *fp)
 {
-        print_sample_spacing(len, 34);
+        return perf_sample__fprintf_spacing(len, 34, fp);
 }
 
-static void print_sample_synth_ptwrite(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_ptwrite(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" IP: %u payload: %#" PRIx64 " ",
+        len = fprintf(fp, " IP: %u payload: %#" PRIx64 " ",
                      data->ip, le64_to_cpu(data->payload));
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_mwait(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_mwait(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" hints: %#x extensions: %#x ",
-                     data->hints, data->extensions);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " hints: %#x extensions: %#x ",
+                      data->hints, data->extensions);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_pwre(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_pwre(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" hw: %u cstate: %u sub-cstate: %u ",
-                     data->hw, data->cstate, data->subcstate);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " hw: %u cstate: %u sub-cstate: %u ",
+                      data->hw, data->cstate, data->subcstate);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_exstop(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_exstop(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" IP: %u ", data->ip);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " IP: %u ", data->ip);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_pwrx(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_pwrx(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" deepest cstate: %u last cstate: %u wake reason: %#x ",
+        len = fprintf(fp, " deepest cstate: %u last cstate: %u wake reason: %#x ",
                      data->deepest_cstate, data->last_cstate,
                      data->wake_reason);
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_cbr(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_cbr(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample);
         unsigned int percent, freq;
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
         freq = (le32_to_cpu(data->freq) + 500) / 1000;
-        len = printf(" cbr: %2u freq: %4u MHz ", data->cbr, freq);
+        len = fprintf(fp, " cbr: %2u freq: %4u MHz ", data->cbr, freq);
         if (data->max_nonturbo) {
                 percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10;
-                len += printf("(%3u%%) ", percent);
+                len += fprintf(fp, "(%3u%%) ", percent);
         }
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth(struct perf_sample *sample,
-                               struct perf_evsel *evsel)
+static int perf_sample__fprintf_synth(struct perf_sample *sample,
+                                      struct perf_evsel *evsel, FILE *fp)
 {
         switch (evsel->attr.config) {
         case PERF_SYNTH_INTEL_PTWRITE:
-                print_sample_synth_ptwrite(sample);
-                break;
+                return perf_sample__fprintf_synth_ptwrite(sample, fp);
         case PERF_SYNTH_INTEL_MWAIT:
-                print_sample_synth_mwait(sample);
-                break;
+                return perf_sample__fprintf_synth_mwait(sample, fp);
         case PERF_SYNTH_INTEL_PWRE:
-                print_sample_synth_pwre(sample);
-                break;
+                return perf_sample__fprintf_synth_pwre(sample, fp);
         case PERF_SYNTH_INTEL_EXSTOP:
-                print_sample_synth_exstop(sample);
-                break;
+                return perf_sample__fprintf_synth_exstop(sample, fp);
         case PERF_SYNTH_INTEL_PWRX:
-                print_sample_synth_pwrx(sample);
-                break;
+                return perf_sample__fprintf_synth_pwrx(sample, fp);
         case PERF_SYNTH_INTEL_CBR:
-                print_sample_synth_cbr(sample);
-                break;
+                return perf_sample__fprintf_synth_cbr(sample, fp);
         default:
                 break;
         }
+
+        return 0;
 }
 
 struct perf_script {
@@ -1340,12 +1488,16 @@ struct perf_script {
         bool                    show_mmap_events;
         bool                    show_switch_events;
         bool                    show_namespace_events;
+        bool                    show_lost_events;
         bool                    allocated;
+        bool                    per_event_dump;
         struct cpu_map          *cpus;
         struct thread_map       *threads;
         int                     name_width;
         const char              *time_str;
-        struct perf_time_interval ptime;
+        struct perf_time_interval *ptime_range;
+        int                     range_size;
+        int                     range_num;
 };
 
 static int perf_evlist__max_name_len(struct perf_evlist *evlist)
@@ -1362,7 +1514,7 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
         return max;
 }
 
-static size_t data_src__printf(u64 data_src)
+static int data_src__fprintf(u64 data_src, FILE *fp)
 {
         struct mem_info mi = { .data_src.val = data_src };
         char decode[100];
@@ -1376,7 +1528,89 @@ static size_t data_src__printf(u64 data_src)
         if (maxlen < len)
                 maxlen = len;
 
-        return printf("%-*s", maxlen, out);
+        return fprintf(fp, "%-*s", maxlen, out);
+}
+
+struct metric_ctx {
+        struct perf_sample      *sample;
+        struct thread           *thread;
+        struct perf_evsel       *evsel;
+        FILE                    *fp;
+};
+
+static void script_print_metric(void *ctx, const char *color,
+                                const char *fmt,
+                                const char *unit, double val)
+{
+        struct metric_ctx *mctx = ctx;
+
+        if (!fmt)
+                return;
+        perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+                                   PERF_RECORD_SAMPLE, mctx->fp);
+        fputs("\tmetric: ", mctx->fp);
+        if (color)
+                color_fprintf(mctx->fp, color, fmt, val);
+        else
+                printf(fmt, val);
+        fprintf(mctx->fp, " %s\n", unit);
+}
+
+static void script_new_line(void *ctx)
+{
+        struct metric_ctx *mctx = ctx;
+
+        perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+                                   PERF_RECORD_SAMPLE, mctx->fp);
+        fputs("\tmetric: ", mctx->fp);
+}
+
+static void perf_sample__fprint_metric(struct perf_script *script,
+                                       struct thread *thread,
+                                       struct perf_evsel *evsel,
+                                       struct perf_sample *sample,
+                                       FILE *fp)
+{
+        struct perf_stat_output_ctx ctx = {
+                .print_metric = script_print_metric,
+                .new_line = script_new_line,
+                .ctx = &(struct metric_ctx) {
+                                .sample = sample,
+                                .thread = thread,
+                                .evsel  = evsel,
+                                .fp     = fp,
+                         },
+                .force_header = false,
+        };
+        struct perf_evsel *ev2;
+        static bool init;
+        u64 val;
+
+        if (!init) {
+                perf_stat__init_shadow_stats();
+                init = true;
+        }
+        if (!evsel->stats)
+                perf_evlist__alloc_stats(script->session->evlist, false);
+        if (evsel_script(evsel->leader)->gnum++ == 0)
+                perf_stat__reset_shadow_stats();
+        val = sample->period * evsel->scale;
+        perf_stat__update_shadow_stats(evsel,
+                                       val,
+                                       sample->cpu,
+                                       &rt_stat);
+        evsel_script(evsel)->val = val;
+        if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
+                for_each_group_member (ev2, evsel->leader) {
+                        perf_stat__print_shadow_stats(ev2,
+                                                      evsel_script(ev2)->val,
+                                                      sample->cpu,
+                                                      &ctx,
+                                                      NULL,
+                                                      &rt_stat);
+                }
+                evsel_script(evsel->leader)->gnum = 0;
+        }
 }
 
 static void process_event(struct perf_script *script,
@@ -1387,14 +1621,19 @@ static void process_event(struct perf_script *script,
         struct thread *thread = al->thread;
         struct perf_event_attr *attr = &evsel->attr;
         unsigned int type = output_type(attr->type);
+        struct perf_evsel_script *es = evsel->priv;
+        FILE *fp = es->fp;
 
         if (output[type].fields == 0)
                 return;
 
-        print_sample_start(sample, thread, evsel);
+        ++es->samples;
+
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_SAMPLE, fp);
 
         if (PRINT_FIELD(PERIOD))
-                printf("%10" PRIu64 " ", sample->period);
+                fprintf(fp, "%10" PRIu64 " ", sample->period);
 
         if (PRINT_FIELD(EVNAME)) {
                 const char *evname = perf_evsel__name(evsel);
@@ -1402,33 +1641,33 @@ static void process_event(struct perf_script *script,
                 if (!script->name_width)
                         script->name_width = perf_evlist__max_name_len(script->session->evlist);
 
-                printf("%*s: ", script->name_width,
-                       evname ? evname : "[unknown]");
+                fprintf(fp, "%*s: ", script->name_width, evname ?: "[unknown]");
         }
 
         if (print_flags)
-                print_sample_flags(sample->flags);
+                perf_sample__fprintf_flags(sample->flags, fp);
 
         if (is_bts_event(attr)) {
-                print_sample_bts(sample, evsel, thread, al, machine);
+                perf_sample__fprintf_bts(sample, evsel, thread, al, machine, fp);
                 return;
         }
 
-        if (PRINT_FIELD(TRACE))
-                event_format__print(evsel->tp_format, sample->cpu,
-                                    sample->raw_data, sample->raw_size);
+        if (PRINT_FIELD(TRACE)) {
+                event_format__fprintf(evsel->tp_format, sample->cpu,
+                                      sample->raw_data, sample->raw_size, fp);
+        }
 
         if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH))
-                print_sample_synth(sample, evsel);
+                perf_sample__fprintf_synth(sample, evsel, fp);
 
         if (PRINT_FIELD(ADDR))
-                print_sample_addr(sample, thread, attr);
+                perf_sample__fprintf_addr(sample, thread, attr, fp);
 
         if (PRINT_FIELD(DATA_SRC))
-                data_src__printf(sample->data_src);
+                data_src__fprintf(sample->data_src, fp);
 
         if (PRINT_FIELD(WEIGHT))
-                printf("%16" PRIu64, sample->weight);
+                fprintf(fp, "%16" PRIu64, sample->weight);
 
         if (PRINT_FIELD(IP)) {
                 struct callchain_cursor *cursor = NULL;
@@ -1438,27 +1677,33 @@ static void process_event(struct perf_script *script,
                                               sample, NULL, NULL, scripting_max_stack) == 0)
                         cursor = &callchain_cursor;
 
-                putchar(cursor ? '\n' : ' ');
-                sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout);
+                fputc(cursor ? '\n' : ' ', fp);
+                sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, fp);
         }
 
         if (PRINT_FIELD(IREGS))
-                print_sample_iregs(sample, attr);
+                perf_sample__fprintf_iregs(sample, attr, fp);
+
+        if (PRINT_FIELD(UREGS))
+                perf_sample__fprintf_uregs(sample, attr, fp);
 
         if (PRINT_FIELD(BRSTACK))
-                print_sample_brstack(sample, thread, attr);
+                perf_sample__fprintf_brstack(sample, thread, attr, fp);
         else if (PRINT_FIELD(BRSTACKSYM))
-                print_sample_brstacksym(sample, thread, attr);
+                perf_sample__fprintf_brstacksym(sample, thread, attr, fp);
         else if (PRINT_FIELD(BRSTACKOFF))
-                print_sample_brstackoff(sample, thread, attr);
+                perf_sample__fprintf_brstackoff(sample, thread, attr, fp);
 
         if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
-                print_sample_bpf_output(sample);
-        print_insn(sample, attr, thread, machine);
+                perf_sample__fprintf_bpf_output(sample, fp);
+        perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
 
         if (PRINT_FIELD(PHYS_ADDR))
-                printf("%16" PRIx64, sample->phys_addr);
-        printf("\n");
+                fprintf(fp, "%16" PRIx64, sample->phys_addr);
+        fprintf(fp, "\n");
+
+        if (PRINT_FIELD(METRIC))
+                perf_sample__fprint_metric(script, thread, evsel, sample, fp);
 }
 
 static struct scripting_ops     *scripting_ops;
@@ -1538,8 +1783,10 @@ static int process_sample_event(struct perf_tool *tool,
         struct perf_script *scr = container_of(tool, struct perf_script, tool);
         struct addr_location al;
 
-        if (perf_time__skip_sample(&scr->ptime, sample->time))
+        if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num,
+                                          sample->time)) {
                 return 0;
+        }
 
         if (debug_mode) {
                 if (sample->time < last_timestamp) {
@@ -1632,7 +1879,8 @@ static int process_comm_event(struct perf_tool *tool,
                 sample->tid = event->comm.tid;
                 sample->pid = event->comm.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_COMM, stdout);
         perf_event__fprintf(event, stdout);
         ret = 0;
 out:
@@ -1667,7 +1915,8 @@ static int process_namespaces_event(struct perf_tool *tool,
                 sample->tid = event->namespaces.tid;
                 sample->pid = event->namespaces.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_NAMESPACES, stdout);
         perf_event__fprintf(event, stdout);
         ret = 0;
 out:
@@ -1700,7 +1949,8 @@ static int process_fork_event(struct perf_tool *tool,
                 sample->tid = event->fork.tid;
                 sample->pid = event->fork.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_FORK, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
 
@@ -1729,7 +1979,8 @@ static int process_exit_event(struct perf_tool *tool,
                 sample->tid = event->fork.tid;
                 sample->pid = event->fork.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_EXIT, stdout);
         perf_event__fprintf(event, stdout);
 
         if (perf_event__process_exit(tool, event, sample, machine) < 0)
@@ -1764,7 +2015,8 @@ static int process_mmap_event(struct perf_tool *tool,
                 sample->tid = event->mmap.tid;
                 sample->pid = event->mmap.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_MMAP, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1795,7 +2047,8 @@ static int process_mmap2_event(struct perf_tool *tool,
                 sample->tid = event->mmap2.tid;
                 sample->pid = event->mmap2.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_MMAP2, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1821,7 +2074,31 @@ static int process_switch_event(struct perf_tool *tool,
                 return -1;
         }
 
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_SWITCH, stdout);
+        perf_event__fprintf(event, stdout);
+        thread__put(thread);
+        return 0;
+}
+
+static int
+process_lost_event(struct perf_tool *tool,
+                   union perf_event *event,
+                   struct perf_sample *sample,
+                   struct machine *machine)
+{
+        struct perf_script *script = container_of(tool, struct perf_script, tool);
+        struct perf_session *session = script->session;
+        struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+        struct thread *thread;
+
+        thread = machine__findnew_thread(machine, sample->pid,
+                                         sample->tid);
+        if (thread == NULL)
+                return -1;
+
+        perf_sample__fprintf_start(sample, thread, evsel,
+                                   PERF_RECORD_LOST, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1832,6 +2109,75 @@ static void sig_handler(int sig __maybe_unused)
         session_done = 1;
 }
 
+static void perf_script__fclose_per_event_dump(struct perf_script *script)
+{
+        struct perf_evlist *evlist = script->session->evlist;
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (!evsel->priv)
+                        break;
+                perf_evsel_script__delete(evsel->priv);
+                evsel->priv = NULL;
+        }
+}
+
+static int perf_script__fopen_per_event_dump(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(script->session->evlist, evsel) {
+                /*
+                 * Already setup? I.e. we may be called twice in cases like
+                 * Intel PT, one for the intel_pt// and dummy events, then
+                 * for the evsels syntheized from the auxtrace info.
+                 *
+                 * Ses perf_script__process_auxtrace_info.
+                 */
+                if (evsel->priv != NULL)
+                        continue;
+
+                evsel->priv = perf_evsel_script__new(evsel, script->session->data);
+                if (evsel->priv == NULL)
+                        goto out_err_fclose;
+        }
+
+        return 0;
+
+out_err_fclose:
+        perf_script__fclose_per_event_dump(script);
+        return -1;
+}
+
+static int perf_script__setup_per_event_dump(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+        static struct perf_evsel_script es_stdout;
+
+        if (script->per_event_dump)
+                return perf_script__fopen_per_event_dump(script);
+
+        es_stdout.fp = stdout;
+
+        evlist__for_each_entry(script->session->evlist, evsel)
+                evsel->priv = &es_stdout;
+
+        return 0;
+}
+
+static void perf_script__exit_per_event_dump_stats(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(script->session->evlist, evsel) {
+                struct perf_evsel_script *es = evsel->priv;
+
+                perf_evsel_script__fprintf(es, stdout);
+                perf_evsel_script__delete(es);
+                evsel->priv = NULL;
+        }
+}
+
 static int __cmd_script(struct perf_script *script)
 {
         int ret;
@@ -1852,9 +2198,19 @@ static int __cmd_script(struct perf_script *script)
                 script->tool.context_switch = process_switch_event;
         if (script->show_namespace_events)
                 script->tool.namespaces = process_namespaces_event;
+        if (script->show_lost_events)
+                script->tool.lost = process_lost_event;
+
+        if (perf_script__setup_per_event_dump(script)) {
+                pr_err("Couldn't create the per event dump files\n");
+                return -1;
+        }
 
         ret = perf_session__process_events(script->session);
 
+        if (script->per_event_dump)
+                perf_script__exit_per_event_dump_stats(script);
+
         if (debug_mode)
                 pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
 
@@ -2129,19 +2485,6 @@ out:
         return rc;
 }
 
-/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
-static int is_directory(const char *base_path, const struct dirent *dent)
-{
-        char path[PATH_MAX];
-        struct stat st;
-
-        sprintf(path, "%s/%s", base_path, dent->d_name);
-        if (stat(path, &st))
-                return 0;
-
-        return S_ISDIR(st.st_mode);
-}
-
 #define for_each_lang(scripts_path, scripts_dir, lang_dirent)           \
         while ((lang_dirent = readdir(scripts_dir)) != NULL)            \
                 if ((lang_dirent->d_type == DT_DIR ||                   \
@@ -2419,14 +2762,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
         char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
         DIR *scripts_dir, *lang_dir;
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
         };
         char *temp;
         int i = 0;
 
-        session = perf_session__new(&file, false, NULL);
+        session = perf_session__new(&data, false, NULL);
         if (!session)
                 return -1;
 
@@ -2574,9 +2919,10 @@ static void script__setup_sample_type(struct perf_script *script)
 
         if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
                 if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-                    (sample_type & PERF_SAMPLE_STACK_USER))
+                    (sample_type & PERF_SAMPLE_STACK_USER)) {
                         callchain_param.record_mode = CALLCHAIN_DWARF;
-                else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+                        dwarf_callchain_users = true;
+                } else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
                         callchain_param.record_mode = CALLCHAIN_LBR;
                 else
                         callchain_param.record_mode = CALLCHAIN_FP;
@@ -2664,6 +3010,25 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
         return set_maps(script);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+static int perf_script__process_auxtrace_info(struct perf_tool *tool,
+                                              union perf_event *event,
+                                              struct perf_session *session)
+{
+        int ret = perf_event__process_auxtrace_info(tool, event, session);
+
+        if (ret == 0) {
+                struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+                ret = perf_script__setup_per_event_dump(script);
+        }
+
+        return ret;
+}
+#else
+#define perf_script__process_auxtrace_info 0
+#endif
+
 int cmd_script(int argc, const char **argv)
 {
         bool show_full_info = false;
@@ -2692,7 +3057,7 @@ int cmd_script(int argc, const char **argv)
                         .feature         = perf_event__process_feature,
                         .build_id        = perf_event__process_build_id,
                         .id_index        = perf_event__process_id_index,
-                        .auxtrace_info   = perf_event__process_auxtrace_info,
+                        .auxtrace_info   = perf_script__process_auxtrace_info,
                         .auxtrace        = perf_event__process_auxtrace,
                         .auxtrace_error  = perf_event__process_auxtrace_error,
                         .stat            = perf_event__process_stat_event,
@@ -2704,7 +3069,7 @@ int cmd_script(int argc, const char **argv)
                         .ordering_requires_timestamps = true,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         const struct option options[] = {
@@ -2740,7 +3105,7 @@ int cmd_script(int argc, const char **argv)
                      "+field to add and -field to remove."
                      "Valid types: hw,sw,trace,raw,synth. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-                     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
+                     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
                      "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
                      parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
@@ -2772,6 +3137,10 @@ int cmd_script(int argc, const char **argv)
                     "Show context switch events (if recorded)"),
         OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
                     "Show namespace events (if recorded)"),
+        OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events,
+                    "Show lost events (if recorded)"),
+        OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
+                    "Dump trace output to files named by the monitored events"),
         OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
         OPT_INTEGER(0, "max-blocks", &max_blocks,
                     "Maximum number of code blocks to dump with brstackinsn"),
@@ -2802,13 +3171,15 @@ int cmd_script(int argc, const char **argv)
                 NULL
         };
 
+        perf_set_singlethreaded();
+
         setup_scripting();
 
         argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
-        file.path = input_name;
-        file.force = symbol_conf.force;
+        data.file.path = input_name;
+        data.force     = symbol_conf.force;
 
         if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
                 rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
@@ -2975,7 +3346,7 @@ int cmd_script(int argc, const char **argv)
         if (!script_name)
                 setup_pager();
 
-        session = perf_session__new(&file, false, &script.tool);
+        session = perf_session__new(&data, false, &script.tool);
         if (session == NULL)
                 return -1;
 
@@ -3016,7 +3387,8 @@ int cmd_script(int argc, const char **argv)
                                          machine__resolve_kernel_addr,
                                          &session->machines.host) < 0) {
                 pr_err("%s: failed to set libtraceevent function resolver\n", __func__);
-                return -1;
+                err = -1;
+                goto out_delete;
         }
 
         if (generate_script_lang) {
@@ -3030,7 +3402,7 @@ int cmd_script(int argc, const char **argv)
                         goto out_delete;
                 }
 
-                input = open(file.path, O_RDONLY);      /* input_name */
+                input = open(data.file.path, O_RDONLY); /* input_name */
                 if (input < 0) {
                         err = -errno;
                         perror("failed to open file");
@@ -3073,10 +3445,37 @@ int cmd_script(int argc, const char **argv)
         if (err < 0)
                 goto out_delete;
 
+        script.ptime_range = perf_time__range_alloc(script.time_str,
+                                                    &script.range_size);
+        if (!script.ptime_range) {
+                err = -ENOMEM;
+                goto out_delete;
+        }
+
         /* needs to be parsed after looking up reference time */
-        if (perf_time__parse_str(&script.ptime, script.time_str) != 0) {
-                pr_err("Invalid time string\n");
-                return -EINVAL;
+        if (perf_time__parse_str(script.ptime_range, script.time_str) != 0) {
+                if (session->evlist->first_sample_time == 0 &&
+                    session->evlist->last_sample_time == 0) {
+                        pr_err("HINT: no first/last sample time found in perf data.\n"
+                               "Please use latest perf binary to execute 'perf record'\n"
+                               "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
+                        err = -EINVAL;
+                        goto out_delete;
+                }
+
+                script.range_num = perf_time__percent_parse_str(
+                                        script.ptime_range, script.range_size,
+                                        script.time_str,
+                                        session->evlist->first_sample_time,
+                                        session->evlist->last_sample_time);
+
+                if (script.range_num < 0) {
+                        pr_err("Invalid time string\n");
+                        err = -EINVAL;
+                        goto out_delete;
+                }
+        } else {
+                script.range_num = 1;
         }
 
         err = __cmd_script(&script);
@@ -3084,6 +3483,8 @@ int cmd_script(int argc, const char **argv)
         flush_scripting();
 
 out_delete:
+        zfree(&script.ptime_range);
+
         perf_evlist__free_stats(session->evlist);
         perf_session__delete(session);
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 69523ed55894..98bf9d32f222 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -63,8 +63,8 @@
 #include "util/group.h"
 #include "util/session.h"
 #include "util/tool.h"
-#include "util/group.h"
 #include "util/string2.h"
+#include "util/metricgroup.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -133,6 +133,8 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist       *evsel_list;
 
+static struct rblist             metric_events;
+
 static struct target target = {
         .uid    = UINT_MAX,
 };
@@ -172,7 +174,7 @@ static int			print_free_counters_hint;
 
 struct perf_stat {
         bool                     record;
-        struct perf_data_file    file;
+        struct perf_data         data;
         struct perf_session     *session;
         u64                      bytes_written;
         struct perf_tool         tool;
@@ -192,6 +194,11 @@ static struct perf_stat_config stat_config = {
         .scale          = true,
 };
 
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+        return !strcmp(evsel->name, "duration_time");
+}
+
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
                                  struct timespec *b)
 {
@@ -206,8 +213,13 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 
 static void perf_stat__reset_stats(void)
 {
+        int i;
+
         perf_evlist__reset_stats(evsel_list);
         perf_stat__reset_shadow_stats();
+
+        for (i = 0; i < stat_config.stats_num; i++)
+                perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
 }
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -245,7 +257,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
          * by attr->sample_type != 0, and we can't run it on
          * stat sessions.
          */
-        if (!(STAT_RECORD && perf_stat.file.is_pipe))
+        if (!(STAT_RECORD && perf_stat.data.is_pipe))
                 attr->sample_type = PERF_SAMPLE_IDENTIFIER;
 
         /*
@@ -264,7 +276,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
                         attr->enable_on_exec = 1;
         }
 
-        if (target__has_cpu(&target))
+        if (target__has_cpu(&target) && !target__has_per_thread(&target))
                 return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
         return perf_evsel__open_per_thread(evsel, evsel_list->threads);
@@ -287,7 +299,7 @@ static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
                                      struct perf_sample *sample __maybe_unused,
                                      struct machine *machine __maybe_unused)
 {
-        if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
+        if (perf_data__write(&perf_stat.data, event, event->header.size) < 0) {
                 pr_err("failed to write perf data, error: %m\n");
                 return -1;
         }
@@ -327,7 +339,7 @@ static int read_counter(struct perf_evsel *counter)
         int nthreads = thread_map__nr(evsel_list->threads);
         int ncpus, cpu, thread;
 
-        if (target__has_cpu(&target))
+        if (target__has_cpu(&target) && !target__has_per_thread(&target))
                 ncpus = perf_evsel__nr_cpus(counter);
         else
                 ncpus = 1;
@@ -407,6 +419,8 @@ static void process_interval(void)
                         pr_err("failed to write stat round event\n");
         }
 
+        init_stats(&walltime_nsecs_stats);
+        update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000);
         print_counters(&rs, 0, NULL);
 }
 
@@ -448,19 +462,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
         workload_exec_errno = info->si_value.sival_int;
 }
 
-static bool has_unit(struct perf_evsel *counter)
-{
-        return counter->unit && *counter->unit;
-}
-
-static bool has_scale(struct perf_evsel *counter)
-{
-        return counter->scale != 1;
-}
-
 static int perf_stat_synthesize_config(bool is_pipe)
 {
-        struct perf_evsel *counter;
         int err;
 
         if (is_pipe) {
@@ -472,53 +475,10 @@ static int perf_stat_synthesize_config(bool is_pipe)
                 }
         }
 
-        /*
-         * Synthesize other events stuff not carried within
-         * attr event - unit, scale, name
-         */
-        evlist__for_each_entry(evsel_list, counter) {
-                if (!counter->supported)
-                        continue;
-
-                /*
-                 * Synthesize unit and scale only if it's defined.
-                 */
-                if (has_unit(counter)) {
-                        err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event);
-                        if (err < 0) {
-                                pr_err("Couldn't synthesize evsel unit.\n");
-                                return err;
-                        }
-                }
-
-                if (has_scale(counter)) {
-                        err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event);
-                        if (err < 0) {
-                                pr_err("Couldn't synthesize evsel scale.\n");
-                                return err;
-                        }
-                }
-
-                if (counter->own_cpus) {
-                        err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event);
-                        if (err < 0) {
-                                pr_err("Couldn't synthesize evsel scale.\n");
-                                return err;
-                        }
-                }
-
-                /*
-                 * Name is needed only for pipe output,
-                 * perf.data carries event names.
-                 */
-                if (is_pipe) {
-                        err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event);
-                        if (err < 0) {
-                                pr_err("Couldn't synthesize evsel name.\n");
-                                return err;
-                        }
-                }
-        }
+        err = perf_event__synthesize_extra_attr(NULL,
+                                                evsel_list,
+                                                process_synthesized_event,
+                                                is_pipe);
 
         err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
                                                 process_synthesized_event,
@@ -582,6 +542,32 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)
         return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
 }
 
+static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
+{
+        struct perf_evsel *c2, *leader;
+        bool is_open = true;
+
+        leader = evsel->leader;
+        pr_debug("Weak group for %s/%d failed\n",
+                        leader->name, leader->nr_members);
+
+        /*
+         * for_each_group_member doesn't work here because it doesn't
+         * include the first entry.
+         */
+        evlist__for_each_entry(evsel_list, c2) {
+                if (c2 == evsel)
+                        is_open = false;
+                if (c2->leader == leader) {
+                        if (is_open)
+                                perf_evsel__close(c2);
+                        c2->leader = c2;
+                        c2->nr_members = 0;
+                }
+        }
+        return leader;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
         int interval = stat_config.interval;
@@ -592,7 +578,7 @@ static int __run_perf_stat(int argc, const char **argv)
         size_t l;
         int status = 0;
         const bool forks = (argc > 0);
-        bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
+        bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
         struct perf_evsel_config_term *err_term;
 
         if (interval) {
@@ -618,6 +604,15 @@ static int __run_perf_stat(int argc, const char **argv)
         evlist__for_each_entry(evsel_list, counter) {
 try_again:
                 if (create_perf_stat_counter(counter) < 0) {
+
+                        /* Weak group failed. Reset the group. */
+                        if ((errno == EINVAL || errno == EBADF) &&
+                            counter->leader != counter &&
+                            counter->weak_group) {
+                                counter = perf_evsel__reset_weak_group(counter);
+                                goto try_again;
+                        }
+
                         /*
                          * PPC returns ENXIO for HW counters until 2.6.37
                          * (behavior changed with commit b0a873e).
@@ -674,10 +669,10 @@ try_again:
         }
 
         if (STAT_RECORD) {
-                int err, fd = perf_data_file__fd(&perf_stat.file);
+                int err, fd = perf_data__fd(&perf_stat.data);
 
                 if (is_pipe) {
-                        err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file));
+                        err = perf_header__write_pipe(perf_data__fd(&perf_stat.data));
                 } else {
                         err = perf_session__write_header(perf_stat.session, evsel_list,
                                                          fd, false);
@@ -800,7 +795,7 @@ static void print_noise(struct perf_evsel *evsel, double avg)
         if (run_count == 1)
                 return;
 
-        ps = evsel->priv;
+        ps = evsel->stats;
         print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
@@ -1106,7 +1101,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 }
 
 static void printout(int id, int nr, struct perf_evsel *counter, double uval,
-                     char *prefix, u64 run, u64 ena, double noise)
+                     char *prefix, u64 run, u64 ena, double noise,
+                     struct runtime_stat *st)
 {
         struct perf_stat_output_ctx out;
         struct outstate os = {
@@ -1199,7 +1195,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
         perf_stat__print_shadow_stats(counter, uval,
                                 first_shadow_cpu(counter, id),
-                                &out);
+                                &out, &metric_events, st);
         if (!csv_output && !metric_only) {
                 print_noise(counter, noise);
                 print_running(run, ena);
@@ -1222,9 +1218,9 @@ static void aggr_update_shadow(void)
                                         continue;
                                 val += perf_counts(counter->counts, cpu, 0)->val;
                         }
-                        val = val * counter->scale;
-                        perf_stat__update_shadow_stats(counter, &val,
-                                                       first_shadow_cpu(counter, id));
+                        perf_stat__update_shadow_stats(counter, val,
+                                        first_shadow_cpu(counter, id),
+                                        &rt_stat);
                 }
         }
 }
@@ -1325,6 +1321,9 @@ static void print_aggr(char *prefix)
                 ad.id = id = aggr_map->map[s];
                 first = true;
                 evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
+
                         ad.val = ad.ena = ad.run = 0;
                         ad.nr = 0;
                         if (!collect_data(counter, aggr_cb, &ad))
@@ -1341,7 +1340,8 @@ static void print_aggr(char *prefix)
                                 fprintf(output, "%s", prefix);
 
                         uval = val * counter->scale;
-                        printout(id, nr, counter, uval, prefix, run, ena, 1.0);
+                        printout(id, nr, counter, uval, prefix, run, ena, 1.0,
+                                 &rt_stat);
                         if (!metric_only)
                                 fputc('\n', output);
                 }
@@ -1350,13 +1350,24 @@ static void print_aggr(char *prefix)
         }
 }
 
-static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+static int cmp_val(const void *a, const void *b)
 {
-        FILE *output = stat_config.output;
-        int nthreads = thread_map__nr(counter->threads);
-        int ncpus = cpu_map__nr(counter->cpus);
-        int cpu, thread;
+        return ((struct perf_aggr_thread_value *)b)->val -
+                ((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+                                        struct perf_evsel *counter,
+                                        int nthreads, int ncpus,
+                                        int *ret)
+{
+        int cpu, thread, i = 0;
         double uval;
+        struct perf_aggr_thread_value *buf;
+
+        buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+        if (!buf)
+                return NULL;
 
         for (thread = 0; thread < nthreads; thread++) {
                 u64 ena = 0, run = 0, val = 0;
@@ -1367,13 +1378,63 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
                         run += perf_counts(counter->counts, cpu, thread)->run;
                 }
 
+                uval = val * counter->scale;
+
+                /*
+                 * Skip value 0 when enabling --per-thread globally,
+                 * otherwise too many 0 output.
+                 */
+                if (uval == 0.0 && target__has_per_thread(&target))
+                        continue;
+
+                buf[i].counter = counter;
+                buf[i].id = thread;
+                buf[i].uval = uval;
+                buf[i].val = val;
+                buf[i].run = run;
+                buf[i].ena = ena;
+                i++;
+        }
+
+        qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+        if (ret)
+                *ret = i;
+
+        return buf;
+}
+
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+        FILE *output = stat_config.output;
+        int nthreads = thread_map__nr(counter->threads);
+        int ncpus = cpu_map__nr(counter->cpus);
+        int thread, sorted_threads, id;
+        struct perf_aggr_thread_value *buf;
+
+        buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads);
+        if (!buf) {
+                perror("cannot sort aggr thread");
+                return;
+        }
+
+        for (thread = 0; thread < sorted_threads; thread++) {
                 if (prefix)
                         fprintf(output, "%s", prefix);
 
-                uval = val * counter->scale;
-                printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
+                id = buf[thread].id;
+                if (stat_config.stats)
+                        printout(id, 0, buf[thread].counter, buf[thread].uval,
+                                 prefix, buf[thread].run, buf[thread].ena, 1.0,
+                                 &stat_config.stats[id]);
+                else
+                        printout(id, 0, buf[thread].counter, buf[thread].uval,
+                                 prefix, buf[thread].run, buf[thread].ena, 1.0,
+                                 &rt_stat);
                 fputc('\n', output);
         }
+
+        free(buf);
 }
 
 struct caggr_data {
@@ -1384,7 +1445,7 @@ static void counter_aggr_cb(struct perf_evsel *counter, void *data,
                             bool first __maybe_unused)
 {
         struct caggr_data *cd = data;
-        struct perf_stat_evsel *ps = counter->priv;
+        struct perf_stat_evsel *ps = counter->stats;
 
         cd->avg += avg_stats(&ps->res_stats[0]);
         cd->avg_enabled += avg_stats(&ps->res_stats[1]);
@@ -1408,7 +1469,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
                 fprintf(output, "%s", prefix);
 
         uval = cd.avg * counter->scale;
-        printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
+        printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+                 cd.avg, &rt_stat);
         if (!metric_only)
                 fprintf(output, "\n");
 }
@@ -1447,7 +1509,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
                         fprintf(output, "%s", prefix);
 
                 uval = val * counter->scale;
-                printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+                printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+                         &rt_stat);
 
                 fputc('\n', output);
         }
@@ -1468,6 +1531,8 @@ static void print_no_aggr_metric(char *prefix)
                 if (prefix)
                         fputs(prefix, stat_config.output);
                 evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
                         if (first) {
                                 aggr_printout(counter, cpu, 0);
                                 first = false;
@@ -1477,7 +1542,8 @@ static void print_no_aggr_metric(char *prefix)
                         run = perf_counts(counter->counts, cpu, 0)->run;
 
                         uval = val * counter->scale;
-                        printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+                        printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+                                 &rt_stat);
                 }
                 fputc('\n', stat_config.output);
         }
@@ -1522,6 +1588,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 
         /* Print metrics headers only */
         evlist__for_each_entry(evsel_list, counter) {
+                if (is_duration_time(counter))
+                        continue;
                 os.evsel = counter;
                 out.ctx = &os;
                 out.print_metric = print_metric_header;
@@ -1530,7 +1598,9 @@ static void print_metric_headers(const char *prefix, bool no_indent)
                 os.evsel = counter;
                 perf_stat__print_shadow_stats(counter, 0,
                                               0,
-                                              &out);
+                                              &out,
+                                              &metric_events,
+                                              &rt_stat);
         }
         fputc('\n', stat_config.output);
 }
@@ -1643,7 +1713,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
         char buf[64], *prefix = NULL;
 
         /* Do not print anything if we record to the pipe. */
-        if (STAT_RECORD && perf_stat.file.is_pipe)
+        if (STAT_RECORD && perf_stat.data.is_pipe)
                 return;
 
         if (interval)
@@ -1668,12 +1738,18 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
                 print_aggr(prefix);
                 break;
         case AGGR_THREAD:
-                evlist__for_each_entry(evsel_list, counter)
+                evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
                         print_aggr_thread(counter, prefix);
+                }
                 break;
         case AGGR_GLOBAL:
-                evlist__for_each_entry(evsel_list, counter)
+                evlist__for_each_entry(evsel_list, counter) {
+                        if (is_duration_time(counter))
+                                continue;
                         print_counter_aggr(counter, prefix);
+                }
                 if (metric_only)
                         fputc('\n', stat_config.output);
                 break;
@@ -1681,8 +1757,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
                 if (metric_only)
                         print_no_aggr_metric(prefix);
                 else {
-                        evlist__for_each_entry(evsel_list, counter)
+                        evlist__for_each_entry(evsel_list, counter) {
+                                if (is_duration_time(counter))
+                                        continue;
                                 print_counter(counter, prefix);
+                        }
                 }
                 break;
         case AGGR_UNSET:
@@ -1754,6 +1833,13 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
         return 0;
 }
 
+static int parse_metric_groups(const struct option *opt,
+                               const char *str,
+                               int unset __maybe_unused)
+{
+        return metricgroup__parse_groups(opt, str, &metric_events);
+}
+
 static const struct option stat_options[] = {
         OPT_BOOLEAN('T', "transaction", &transaction_run,
                     "hardware transaction statistics"),
@@ -1819,6 +1905,9 @@ static const struct option stat_options[] = {
                         "measure topdown level 1 statistics"),
         OPT_BOOLEAN(0, "smi-cost", &smi_cost,
                         "measure SMI cost"),
+        OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
+                     "monitor specified metrics or metric groups (separated by ,)",
+                     parse_metric_groups),
         OPT_END()
 };
 
@@ -2334,20 +2423,20 @@ static void init_features(struct perf_session *session)
 static int __cmd_record(int argc, const char **argv)
 {
         struct perf_session *session;
-        struct perf_data_file *file = &perf_stat.file;
+        struct perf_data *data = &perf_stat.data;
 
         argc = parse_options(argc, argv, stat_options, stat_record_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
         if (output_name)
-                file->path = output_name;
+                data->file.path = output_name;
 
         if (run_count != 1 || forever) {
                 pr_err("Cannot use -r option with perf stat record.\n");
                 return -1;
         }
 
-        session = perf_session__new(file, false, NULL);
+        session = perf_session__new(data, false, NULL);
         if (session == NULL) {
                 pr_err("Perf session creation failed.\n");
                 return -1;
@@ -2405,7 +2494,7 @@ int process_stat_config_event(struct perf_tool *tool,
         if (st->aggr_mode != AGGR_UNSET)
                 stat_config.aggr_mode = st->aggr_mode;
 
-        if (perf_stat.file.is_pipe)
+        if (perf_stat.data.is_pipe)
                 perf_stat_init_aggr_mode();
         else
                 perf_stat_init_aggr_mode_file(st);
@@ -2470,6 +2559,35 @@ int process_cpu_map_event(struct perf_tool *tool,
         return set_maps(st);
 }
 
+static int runtime_stat_new(struct perf_stat_config *config, int nthreads)
+{
+        int i;
+
+        config->stats = calloc(nthreads, sizeof(struct runtime_stat));
+        if (!config->stats)
+                return -1;
+
+        config->stats_num = nthreads;
+
+        for (i = 0; i < nthreads; i++)
+                runtime_stat__init(&config->stats[i]);
+
+        return 0;
+}
+
+static void runtime_stat_delete(struct perf_stat_config *config)
+{
+        int i;
+
+        if (!config->stats)
+                return;
+
+        for (i = 0; i < config->stats_num; i++)
+                runtime_stat__exit(&config->stats[i]);
+
+        free(config->stats);
+}
+
 static const char * const stat_report_usage[] = {
         "perf stat report [<options>]",
         NULL,
@@ -2513,10 +2631,10 @@ static int __cmd_report(int argc, const char **argv)
                         input_name = "perf.data";
         }
 
-        perf_stat.file.path = input_name;
-        perf_stat.file.mode = PERF_DATA_MODE_READ;
+        perf_stat.data.file.path = input_name;
+        perf_stat.data.mode      = PERF_DATA_MODE_READ;
 
-        session = perf_session__new(&perf_stat.file, false, &perf_stat.tool);
+        session = perf_session__new(&perf_stat.data, false, &perf_stat.tool);
         if (session == NULL)
                 return -1;
 
@@ -2679,12 +2797,16 @@ int cmd_stat(int argc, const char **argv)
                 run_count = 1;
         }
 
-        if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
-                fprintf(stderr, "The --per-thread option is only available "
-                        "when monitoring via -p -t options.\n");
-                parse_options_usage(NULL, stat_options, "p", 1);
-                parse_options_usage(NULL, stat_options, "t", 1);
-                goto out;
+        if ((stat_config.aggr_mode == AGGR_THREAD) &&
+                !target__has_task(&target)) {
+                if (!target.system_wide || target.cpu_list) {
+                        fprintf(stderr, "The --per-thread option is only "
+                                "available when monitoring via -p -t -a "
+                                "options or only --per-thread.\n");
+                        parse_options_usage(NULL, stat_options, "p", 1);
+                        parse_options_usage(NULL, stat_options, "t", 1);
+                        goto out;
+                }
         }
 
         /*
@@ -2708,6 +2830,9 @@ int cmd_stat(int argc, const char **argv)
 
         target__validate(&target);
 
+        if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
+                target.per_thread = true;
+
         if (perf_evlist__create_maps(evsel_list, &target) < 0) {
                 if (target__has_task(&target)) {
                         pr_err("Problems finding threads of monitor\n");
@@ -2725,8 +2850,15 @@ int cmd_stat(int argc, const char **argv)
          * Initialize thread_map with comm names,
          * so we could print it out on output.
          */
-        if (stat_config.aggr_mode == AGGR_THREAD)
+        if (stat_config.aggr_mode == AGGR_THREAD) {
                 thread_map__read_comms(evsel_list->threads);
+                if (target.system_wide) {
+                        if (runtime_stat_new(&stat_config,
+                                thread_map__nr(evsel_list->threads))) {
+                                goto out;
+                        }
+                }
+        }
 
         if (interval && interval < 100) {
                 if (interval < 10) {
@@ -2787,7 +2919,7 @@ int cmd_stat(int argc, const char **argv)
                  * records, but the need to suppress the kptr_restrict messages in older
                  * tools remain  -acme
                  */
-                int fd = perf_data_file__fd(&perf_stat.file);
+                int fd = perf_data__fd(&perf_stat.data);
                 int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,
                                                              process_synthesized_event,
                                                              &perf_stat.session->machines.host);
@@ -2801,7 +2933,7 @@ int cmd_stat(int argc, const char **argv)
                                 pr_err("failed to write stat round event\n");
                 }
 
-                if (!perf_stat.file.is_pipe) {
+                if (!perf_stat.data.is_pipe) {
                         perf_stat.session->header.data_size += perf_stat.bytes_written;
                         perf_session__write_header(perf_stat.session, evsel_list, fd, true);
                 }
@@ -2816,5 +2948,8 @@ out:
                 sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
 
         perf_evlist__delete(evsel_list);
+
+        runtime_stat_delete(&stat_config);
+
         return status;
 }
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 4e2e61695986..813698a9b8c7 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1601,13 +1601,15 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
                 { "syscalls:sys_exit_pselect6",         process_exit_poll },
                 { "syscalls:sys_exit_select",           process_exit_poll },
         };
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
-                .force = tchart->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = tchart->force,
         };
 
-        struct perf_session *session = perf_session__new(&file, false,
+        struct perf_session *session = perf_session__new(&data, false,
                                                          &tchart->tool);
         int ret = -EINVAL;
 
@@ -1617,7 +1619,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
         symbol__init(&session->header.env);
 
         (void)perf_header__process_sections(&session->header,
-                                            perf_data_file__fd(session->file),
+                                            perf_data__fd(session->data),
                                             tchart,
                                             process_header);
 
@@ -1732,8 +1734,10 @@ static int timechart__io_record(int argc, const char **argv)
         if (rec_argv == NULL)
                 return -ENOMEM;
 
-        if (asprintf(&filter, "common_pid != %d", getpid()) < 0)
+        if (asprintf(&filter, "common_pid != %d", getpid()) < 0) {
+                free(rec_argv);
                 return -ENOMEM;
+        }
 
         p = rec_argv;
         for (i = 0; i < common_args_nr; i++)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ee954bde7e3e..b7c823ba8374 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -77,6 +77,7 @@
 #include "sane_ctype.h"
 
 static volatile int done;
+static volatile int resize;
 
 #define HEADER_LINE_NR  5
 
@@ -85,17 +86,20 @@ static void perf_top__update_print_entries(struct perf_top *top)
         top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
-static void perf_top__sig_winch(int sig __maybe_unused,
-                                siginfo_t *info __maybe_unused, void *arg)
+static void winch_sig(int sig __maybe_unused)
 {
-        struct perf_top *top = arg;
+        resize = 1;
+}
 
+static void perf_top__resize(struct perf_top *top)
+{
         get_term_dimensions(&top->winsize);
         perf_top__update_print_entries(top);
 }
 
 static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 {
+        struct perf_evsel *evsel = hists_to_evsel(he->hists);
         struct symbol *sym;
         struct annotation *notes;
         struct map *map;
@@ -134,7 +138,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
                 return err;
         }
 
-        err = symbol__disassemble(sym, map, NULL, 0, NULL, NULL);
+        err = symbol__annotate(sym, map, evsel, 0, NULL);
         if (err == 0) {
 out_assign:
                 top->sym_filter_entry = he;
@@ -226,6 +230,7 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 static void perf_top__show_details(struct perf_top *top)
 {
         struct hist_entry *he = top->sym_filter_entry;
+        struct perf_evsel *evsel = hists_to_evsel(he->hists);
         struct annotation *notes;
         struct symbol *symbol;
         int more;
@@ -238,6 +243,8 @@ static void perf_top__show_details(struct perf_top *top)
 
         pthread_mutex_lock(&notes->lock);
 
+        symbol__calc_percent(symbol, evsel);
+
         if (notes->src == NULL)
                 goto out_unlock;
 
@@ -276,8 +283,9 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
         printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-        if (hists->stats.nr_lost_warned !=
-            hists->stats.nr_events[PERF_RECORD_LOST]) {
+        if (!top->record_opts.overwrite &&
+            (hists->stats.nr_lost_warned !=
+            hists->stats.nr_events[PERF_RECORD_LOST])) {
                 hists->stats.nr_lost_warned =
                               hists->stats.nr_events[PERF_RECORD_LOST];
                 color_fprintf(stdout, PERF_COLOR_RED,
@@ -409,7 +417,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top)
         fprintf(stdout, "\t[S]     stop annotation.\n");
 
         fprintf(stdout,
-                "\t[K]     hide kernel_symbols symbols.     \t(%s)\n",
+                "\t[K]     hide kernel symbols.             \t(%s)\n",
                 top->hide_kernel_symbols ? "yes" : "no");
         fprintf(stdout,
                 "\t[U]     hide user symbols.               \t(%s)\n",
@@ -473,12 +481,8 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
                 case 'e':
                         prompt_integer(&top->print_entries, "Enter display entries (lines)");
                         if (top->print_entries == 0) {
-                                struct sigaction act = {
-                                        .sa_sigaction = perf_top__sig_winch,
-                                        .sa_flags     = SA_SIGINFO,
-                                };
-                                perf_top__sig_winch(SIGWINCH, NULL, top);
-                                sigaction(SIGWINCH, &act, NULL);
+                                perf_top__resize(top);
+                                signal(SIGWINCH, winch_sig);
                         } else {
                                 signal(SIGWINCH, SIG_DFL);
                         }
@@ -608,7 +612,8 @@ static void *display_thread_tui(void *arg)
 
         perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
                                       top->min_percent,
-                                      &top->session->header.env);
+                                      &top->session->header.env,
+                                      !top->record_opts.overwrite);
 
         done = 1;
         return NULL;
@@ -732,14 +737,16 @@ static void perf_event__process_sample(struct perf_tool *tool,
         if (!machine->kptr_restrict_warned &&
             symbol_conf.kptr_restrict &&
             al.cpumode == PERF_RECORD_MISC_KERNEL) {
-                ui__warning(
+                if (!perf_evlist__exclude_kernel(top->session->evlist)) {
+                        ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
                           al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
                           " modules" : "");
-                if (use_browser <= 0)
-                        sleep(5);
+                        if (use_browser <= 0)
+                                sleep(5);
+                }
                 machine->kptr_restrict_warned = true;
         }
 
@@ -802,15 +809,23 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 {
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
         struct perf_sample sample;
         struct perf_evsel *evsel;
+        struct perf_mmap *md;
         struct perf_session *session = top->session;
         union perf_event *event;
         struct machine *machine;
+        u64 end, start;
         int ret;
 
-        while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-                ret = perf_evlist__parse_sample(top->evlist, event, &sample);
+        md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
+        if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
+                return;
+
+        while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) {
+                ret = perf_evlist__parse_sample(evlist, event, &sample);
                 if (ret) {
                         pr_err("Can't parse sample, err = %d\n", ret);
                         goto next_event;
@@ -864,16 +879,120 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                 } else
                         ++session->evlist->stats.nr_unknown_events;
 next_event:
-                perf_evlist__mmap_consume(top->evlist, idx);
+                perf_mmap__consume(md, opts->overwrite);
         }
+
+        perf_mmap__read_done(md);
 }
 
 static void perf_top__mmap_read(struct perf_top *top)
 {
+        bool overwrite = top->record_opts.overwrite;
+        struct perf_evlist *evlist = top->evlist;
+        unsigned long long start, end;
         int i;
 
+        start = rdclock();
+        if (overwrite)
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
+
         for (i = 0; i < top->evlist->nr_mmaps; i++)
                 perf_top__mmap_read_idx(top, i);
+
+        if (overwrite) {
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+        }
+        end = rdclock();
+
+        if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC)
+                ui__warning("Too slow to read ring buffer.\n"
+                            "Please try increasing the period (-c) or\n"
+                            "decreasing the freq (-F) or\n"
+                            "limiting the number of CPUs (-C)\n");
+}
+
+/*
+ * Check per-event overwrite term.
+ * perf top should support consistent term for all events.
+ * - All events don't have per-event term
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions/"
+ *   Nothing change, return 0.
+ * - All events have same per-event term
+ *   E.g. "cpu/cpu-cycles,no-overwrite/,cpu/instructions,no-overwrite/
+ *   Using the per-event setting to replace the opts->overwrite if
+ *   they are different, then return 0.
+ * - Events have different per-event term
+ *   E.g. "cpu/cpu-cycles,overwrite/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ * - Some of the event set per-event term, but some not.
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ */
+static int perf_top__overwrite_check(struct perf_top *top)
+{
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
+        struct perf_evsel_config_term *term;
+        struct list_head *config_terms;
+        struct perf_evsel *evsel;
+        int set, overwrite = -1;
+
+        evlist__for_each_entry(evlist, evsel) {
+                set = -1;
+                config_terms = &evsel->config_terms;
+                list_for_each_entry(term, config_terms, list) {
+                        if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE)
+                                set = term->val.overwrite ? 1 : 0;
+                }
+
+                /* no term for current and previous event (likely) */
+                if ((overwrite < 0) && (set < 0))
+                        continue;
+
+                /* has term for both current and previous event, compare */
+                if ((overwrite >= 0) && (set >= 0) && (overwrite != set))
+                        return -1;
+
+                /* no term for current event but has term for previous one */
+                if ((overwrite >= 0) && (set < 0))
+                        return -1;
+
+                /* has term for current event */
+                if ((overwrite < 0) && (set >= 0)) {
+                        /* if it's first event, set overwrite */
+                        if (evsel == perf_evlist__first(evlist))
+                                overwrite = set;
+                        else
+                                return -1;
+                }
+        }
+
+        if ((overwrite >= 0) && (opts->overwrite != overwrite))
+                opts->overwrite = overwrite;
+
+        return 0;
+}
+
+static int perf_top_overwrite_fallback(struct perf_top *top,
+                                       struct perf_evsel *evsel)
+{
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
+        struct perf_evsel *counter;
+
+        if (!opts->overwrite)
+                return 0;
+
+        /* only fall back when first event fails */
+        if (evsel != perf_evlist__first(evlist))
+                return 0;
+
+        evlist__for_each_entry(evlist, counter)
+                counter->attr.write_backward = false;
+        opts->overwrite = false;
+        ui__warning("fall back to non-overwrite mode\n");
+        return 1;
 }
 
 static int perf_top__start_counters(struct perf_top *top)
@@ -883,12 +1002,33 @@ static int perf_top__start_counters(struct perf_top *top)
         struct perf_evlist *evlist = top->evlist;
         struct record_opts *opts = &top->record_opts;
 
+        if (perf_top__overwrite_check(top)) {
+                ui__error("perf top only support consistent per-event "
+                          "overwrite setting for all events\n");
+                goto out_err;
+        }
+
         perf_evlist__config(evlist, opts, &callchain_param);
 
         evlist__for_each_entry(evlist, counter) {
 try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads) < 0) {
+
+                        /*
+                         * Specially handle overwrite fall back.
+                         * Because perf top is the only tool which has
+                         * overwrite mode by default, support
+                         * both overwrite and non-overwrite mode, and
+                         * require consistent mode for all events.
+                         *
+                         * May move it to generic code with more tools
+                         * have similar attribute.
+                         */
+                        if (perf_missing_features.write_backward &&
+                            perf_top_overwrite_fallback(top, counter))
+                                goto try_again;
+
                         if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
                                 if (verbose > 0)
                                         ui__warning("%s\n", msg);
@@ -902,7 +1042,7 @@ try_again:
                 }
         }
 
-        if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+        if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
                 ui__error("Failed to mmap with %d (%s)\n",
                             errno, str_error_r(errno, msg, sizeof(msg)));
                 goto out_err;
@@ -958,8 +1098,16 @@ static int __cmd_top(struct perf_top *top)
         if (perf_session__register_idle_thread(top->session) < 0)
                 goto out_delete;
 
+        if (top->nr_threads_synthesize > 1)
+                perf_set_multithreaded();
+
         machine__synthesize_threads(&top->session->machines.host, &opts->target,
-                                    top->evlist->threads, false, opts->proc_map_timeout);
+                                    top->evlist->threads, false,
+                                    opts->proc_map_timeout,
+                                    top->nr_threads_synthesize);
+
+        if (top->nr_threads_synthesize > 1)
+                perf_set_singlethreaded();
 
         if (perf_hpp_list.socket) {
                 ret = perf_env__read_cpu_topology_map(&perf_env);
@@ -1020,8 +1168,13 @@ static int __cmd_top(struct perf_top *top)
 
                 perf_top__mmap_read(top);
 
-                if (hits == top->samples)
+                if (opts->overwrite || (hits == top->samples))
                         ret = perf_evlist__poll(top->evlist, 100);
+
+                if (resize) {
+                        perf_top__resize(top);
+                        resize = 0;
+                }
         }
 
         ret = 0;
@@ -1109,9 +1262,11 @@ int cmd_top(int argc, const char **argv)
                                 .uses_mmap   = true,
                         },
                         .proc_map_timeout    = 500,
+                        .overwrite      = 1,
                 },
                 .max_stack           = sysctl_perf_event_max_stack,
                 .sym_pcnt_filter     = 5,
+                .nr_threads_synthesize = UINT_MAX,
         };
         struct record_opts *opts = &top.record_opts;
         struct target *target = &opts->target;
@@ -1221,6 +1376,8 @@ int cmd_top(int argc, const char **argv)
         OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
                     "Show entries in a hierarchy"),
         OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
+        OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
+                        "number of thread to run event synthesize"),
         OPT_END()
         };
         const char * const top_usage[] = {
@@ -1341,12 +1498,8 @@ int cmd_top(int argc, const char **argv)
 
         get_term_dimensions(&top.winsize);
         if (top.print_entries == 0) {
-                struct sigaction act = {
-                        .sa_sigaction = perf_top__sig_winch,
-                        .sa_flags     = SA_SIGINFO,
-                };
                 perf_top__update_print_entries(&top);
-                sigaction(SIGWINCH, &act, NULL);
+                signal(SIGWINCH, winch_sig);
         }
 
         status = __cmd_top(&top);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 771ddab94bb0..e7f1b182fc15 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -21,6 +21,7 @@
 #include "builtin.h"
 #include "util/color.h"
 #include "util/debug.h"
+#include "util/env.h"
 #include "util/event.h"
 #include "util/evlist.h"
 #include <subcmd/exec-cmd.h>
@@ -45,18 +46,17 @@
 
 #include <errno.h>
 #include <inttypes.h>
-#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <poll.h>
 #include <signal.h>
 #include <stdlib.h>
 #include <string.h>
 #include <linux/err.h>
 #include <linux/filter.h>
-#include <linux/audit.h>
 #include <linux/kernel.h>
 #include <linux/random.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
+#include <fcntl.h>
 
 #include "sane_ctype.h"
 
@@ -111,6 +111,7 @@ struct trace {
         bool                    summary;
         bool                    summary_only;
         bool                    show_comm;
+        bool                    print_sample;
         bool                    show_tool_stats;
         bool                    trace_syscalls;
         bool                    kernel_syscallchains;
@@ -545,9 +546,10 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
           { .scnprintf  = SCA_STRARRAY, \
             .parm       = &strarray__##array, }
 
+#include "trace/beauty/arch_errno_names.c"
 #include "trace/beauty/eventfd.c"
-#include "trace/beauty/flock.c"
 #include "trace/beauty/futex_op.c"
+#include "trace/beauty/futex_val3.c"
 #include "trace/beauty/mmap.c"
 #include "trace/beauty/mode_t.c"
 #include "trace/beauty/msg_flags.c"
@@ -578,7 +580,6 @@ static struct syscall_fmt {
 } syscall_fmts[] = {
         { .name     = "access",
           .arg = { [1] = { .scnprintf = SCA_ACCMODE,  /* mode */ }, }, },
-        { .name     = "arch_prctl", .alias = "prctl", },
         { .name     = "bpf",
           .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
         { .name     = "brk",        .hexret = true,
@@ -611,7 +612,8 @@ static struct syscall_fmt {
         { .name     = "fstat", .alias = "newfstat", },
         { .name     = "fstatat", .alias = "newfstatat", },
         { .name     = "futex",
-          .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ }, }, },
+          .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ },
+                   [5] = { .scnprintf = SCA_FUTEX_VAL3, /* val3 */ }, }, },
         { .name     = "futimesat",
           .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
         { .name     = "getitimer",
@@ -623,6 +625,7 @@ static struct syscall_fmt {
           .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, },
         { .name     = "getrlimit",
           .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
+        { .name     = "gettid",     .errpid = true, },
         { .name     = "ioctl",
           .arg = {
 #if defined(__i386__) || defined(__x86_64__)
@@ -634,6 +637,12 @@ static struct syscall_fmt {
 #else
                    [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
 #endif
+        { .name     = "kcmp",       .nr_args = 5,
+          .arg = { [0] = { .name = "pid1",      .scnprintf = SCA_PID, },
+                   [1] = { .name = "pid2",      .scnprintf = SCA_PID, },
+                   [2] = { .name = "type",      .scnprintf = SCA_KCMP_TYPE, },
+                   [3] = { .name = "idx1",      .scnprintf = SCA_KCMP_IDX, },
+                   [4] = { .name = "idx2",      .scnprintf = SCA_KCMP_IDX, }, }, },
         { .name     = "keyctl",
           .arg = { [0] = STRARRAY(option, keyctl_options), }, },
         { .name     = "kill",
@@ -703,6 +712,10 @@ static struct syscall_fmt {
                    [3] = { .scnprintf = SCA_INT,        /* pkey */ }, }, },
         { .name     = "poll", .timeout = true, },
         { .name     = "ppoll", .timeout = true, },
+        { .name     = "prctl", .alias = "arch_prctl",
+          .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
+                   [1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
+                   [2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
         { .name     = "pread", .alias = "pread64", },
         { .name     = "preadv", .alias = "pread", },
         { .name     = "prlimit64",
@@ -810,7 +823,7 @@ static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
         size_t printed = fprintf(fp, "(");
 
         if (!calculated)
-                printed += fprintf(fp, "     ?   ");
+                printed += fprintf(fp, "         ");
         else if (duration >= 1.0)
                 printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
         else if (duration >= 0.01)
@@ -985,6 +998,23 @@ size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg)
         return printed;
 }
 
+size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size)
+{
+        size_t printed = scnprintf(bf, size, "%d", fd);
+        struct thread *thread = machine__find_thread(trace->host, pid, pid);
+
+        if (thread) {
+                const char *path = thread__fd_path(thread, fd, trace);
+
+                if (path)
+                        printed += scnprintf(bf + printed, size - printed, "<%s>", path);
+
+                thread__put(thread);
+        }
+
+        return printed;
+}
+
 static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
                                               struct syscall_arg *arg)
 {
@@ -1126,18 +1156,28 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
         if (trace->host == NULL)
                 return -ENOMEM;
 
-        if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
-                return -errno;
+        err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
+        if (err < 0)
+                goto out;
 
         err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
                                             evlist->threads, trace__tool_process, false,
-                                            trace->opts.proc_map_timeout);
+                                            trace->opts.proc_map_timeout, 1);
+out:
         if (err)
                 symbol__exit();
 
         return err;
 }
 
+static void trace__symbols__exit(struct trace *trace)
+{
+        machine__exit(trace->host);
+        trace->host = NULL;
+
+        symbol__exit();
+}
+
 static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 {
         int idx;
@@ -1518,10 +1558,9 @@ static void thread__update_stats(struct thread_trace *ttrace,
         update_stats(stats, duration);
 }
 
-static int trace__printf_interrupted_entry(struct trace *trace, struct perf_sample *sample)
+static int trace__printf_interrupted_entry(struct trace *trace)
 {
         struct thread_trace *ttrace;
-        u64 duration;
         size_t printed;
 
         if (trace->current == NULL)
@@ -1532,15 +1571,30 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp
         if (!ttrace->entry_pending)
                 return 0;
 
-        duration = sample->time - ttrace->entry_time;
-
-        printed  = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output);
+        printed  = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
         printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
         ttrace->entry_pending = false;
 
         return printed;
 }
 
+static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
+                                 struct perf_sample *sample, struct thread *thread)
+{
+        int printed = 0;
+
+        if (trace->print_sample) {
+                double ts = (double)sample->time / NSEC_PER_MSEC;
+
+                printed += fprintf(trace->output, "%22s %10.3f %s %d/%d [%d]\n",
+                                   perf_evsel__name(evsel), ts,
+                                   thread__comm_str(thread),
+                                   sample->pid, sample->tid, sample->cpu);
+        }
+
+        return printed;
+}
+
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
                             union perf_event *event __maybe_unused,
                             struct perf_sample *sample)
@@ -1561,6 +1615,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
         if (ttrace == NULL)
                 goto out_put;
 
+        trace__fprintf_sample(trace, evsel, sample, thread);
+
         args = perf_evsel__sc_tp_ptr(evsel, args, sample);
 
         if (ttrace->entry_str == NULL) {
@@ -1570,7 +1626,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
         }
 
         if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
-                trace__printf_interrupted_entry(trace, sample);
+                trace__printf_interrupted_entry(trace);
 
         ttrace->entry_time = sample->time;
         msg = ttrace->entry_str;
@@ -1605,9 +1661,12 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
                                     struct callchain_cursor *cursor)
 {
         struct addr_location al;
+        int max_stack = evsel->attr.sample_max_stack ?
+                        evsel->attr.sample_max_stack :
+                        trace->max_stack;
 
         if (machine__resolve(trace->host, &al, sample) < 0 ||
-            thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, trace->max_stack))
+            thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
                 return -1;
 
         return 0;
@@ -1623,6 +1682,14 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam
         return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output);
 }
 
+static const char *errno_to_name(struct perf_evsel *evsel, int err)
+{
+        struct perf_env *env = perf_evsel__env(evsel);
+        const char *arch_name = perf_env__arch(env);
+
+        return arch_syscalls__strerrno(arch_name, err);
+}
+
 static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
                            union perf_event *event __maybe_unused,
                            struct perf_sample *sample)
@@ -1643,6 +1710,8 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
         if (ttrace == NULL)
                 goto out_put;
 
+        trace__fprintf_sample(trace, evsel, sample, thread);
+
         if (trace->summary)
                 thread__update_stats(ttrace, id, sample);
 
@@ -1693,7 +1762,7 @@ signed_print:
 errno_print: {
                 char bf[STRERR_BUFSIZE];
                 const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
-                           *e = audit_errno_to_name(-ret);
+                           *e = errno_to_name(evsel, -ret);
 
                 fprintf(trace->output, ") = -1 %s %s", e, emsg);
         }
@@ -1828,16 +1897,14 @@ out_dump:
         goto out_put;
 }
 
-static void bpf_output__printer(enum binary_printer_ops op,
-                                unsigned int val, void *extra)
+static int bpf_output__printer(enum binary_printer_ops op,
+                               unsigned int val, void *extra __maybe_unused, FILE *fp)
 {
-        FILE *output = extra;
         unsigned char ch = (unsigned char)val;
 
         switch (op) {
         case BINARY_PRINT_CHAR_DATA:
-                fprintf(output, "%c", isprint(ch) ? ch : '.');
-                break;
+                return fprintf(fp, "%c", isprint(ch) ? ch : '.');
         case BINARY_PRINT_DATA_BEGIN:
         case BINARY_PRINT_LINE_BEGIN:
         case BINARY_PRINT_ADDR:
@@ -1850,13 +1917,15 @@ static void bpf_output__printer(enum binary_printer_ops op,
         default:
                 break;
         }
+
+        return 0;
 }
 
 static void bpf_output__fprintf(struct trace *trace,
                                 struct perf_sample *sample)
 {
-        print_binary(sample->raw_data, sample->raw_size, 8,
-                     bpf_output__printer, trace->output);
+        binary__fprintf(sample->raw_data, sample->raw_size, 8,
+                        bpf_output__printer, NULL, trace->output);
 }
 
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
@@ -1874,7 +1943,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
                 }
         }
 
-        trace__printf_interrupted_entry(trace, sample);
+        trace__printf_interrupted_entry(trace);
         trace__fprintf_tstamp(trace, sample->time, trace->output);
 
         if (trace->trace_syscalls)
@@ -2078,6 +2147,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
                         rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
                 else {
                         pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+                        free(rec_argv);
                         return -1;
                 }
         }
@@ -2184,6 +2254,9 @@ static int trace__add_syscall_newtp(struct trace *trace)
         if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
                 goto out_delete_sys_exit;
 
+        perf_evsel__config_callchain(sys_enter, &trace->opts, &callchain_param);
+        perf_evsel__config_callchain(sys_exit, &trace->opts, &callchain_param);
+
         perf_evlist__add(evlist, sys_enter);
         perf_evlist__add(evlist, sys_exit);
 
@@ -2280,6 +2353,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
                 pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
                 if (pgfault_maj == NULL)
                         goto out_error_mem;
+                perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
                 perf_evlist__add(evlist, pgfault_maj);
         }
 
@@ -2287,6 +2361,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
                 pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN);
                 if (pgfault_min == NULL)
                         goto out_error_mem;
+                perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
                 perf_evlist__add(evlist, pgfault_min);
         }
 
@@ -2307,45 +2382,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
                 goto out_delete_evlist;
         }
 
-        perf_evlist__config(evlist, &trace->opts, NULL);
-
-        if (callchain_param.enabled) {
-                bool use_identifier = false;
-
-                if (trace->syscalls.events.sys_exit) {
-                        perf_evsel__config_callchain(trace->syscalls.events.sys_exit,
-                                                     &trace->opts, &callchain_param);
-                        use_identifier = true;
-                }
-
-                if (pgfault_maj) {
-                        perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
-                        use_identifier = true;
-                }
-
-                if (pgfault_min) {
-                        perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
-                        use_identifier = true;
-                }
-
-                if (use_identifier) {
-                       /*
-                        * Now we have evsels with different sample_ids, use
-                        * PERF_SAMPLE_IDENTIFIER to map from sample to evsel
-                        * from a fixed position in each ring buffer record.
-                        *
-                        * As of this the changeset introducing this comment, this
-                        * isn't strictly needed, as the fields that can come before
-                        * PERF_SAMPLE_ID are all used, but we'll probably disable
-                        * some of those for things like copying the payload of
-                        * pointer syscall arguments, and for vfs_getname we don't
-                        * need PERF_SAMPLE_ADDR and PERF_SAMPLE_IP, so do this
-                        * here as a warning we need to use PERF_SAMPLE_IDENTIFIER.
-                        */
-                        perf_evlist__set_sample_bit(evlist, IDENTIFIER);
-                        perf_evlist__reset_sample_bit(evlist, ID);
-                }
-        }
+        perf_evlist__config(evlist, &trace->opts, &callchain_param);
 
         signal(SIGCHLD, sig_handler);
         signal(SIGINT, sig_handler);
@@ -2400,7 +2437,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         if (err < 0)
                 goto out_error_apply_filters;
 
-        err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
+        err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
         if (err < 0)
                 goto out_error_mmap;
 
@@ -2418,6 +2455,18 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
                                   evlist->threads->nr > 1 ||
                                   perf_evlist__first(evlist)->attr.inherit;
+
+        /*
+         * Now that we already used evsel->attr to ask the kernel to setup the
+         * events, lets reuse evsel->attr.sample_max_stack as the limit in
+         * trace__resolve_callchain(), allowing per-event max-stack settings
+         * to override an explicitely set --max-stack global setting.
+         */
+        evlist__for_each_entry(evlist, evsel) {
+                if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
+                    evsel->attr.sample_max_stack == 0)
+                        evsel->attr.sample_max_stack = trace->max_stack;
+        }
 again:
         before = trace->nr_events;
 
@@ -2481,6 +2530,8 @@ out_disable:
         }
 
 out_delete_evlist:
+        trace__symbols__exit(trace);
+
         perf_evlist__delete(evlist);
         trace->evlist = NULL;
         trace->live = false;
@@ -2528,10 +2579,12 @@ static int trace__replay(struct trace *trace)
         const struct perf_evsel_str_handler handlers[] = {
                 { "probe:vfs_getname",       trace__vfs_getname, },
         };
-        struct perf_data_file file = {
-                .path  = input_name,
-                .mode  = PERF_DATA_MODE_READ,
-                .force = trace->force,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = trace->force,
         };
         struct perf_session *session;
         struct perf_evsel *evsel;
@@ -2554,7 +2607,7 @@ static int trace__replay(struct trace *trace)
         /* add tid to output */
         trace->multiple_threads = true;
 
-        session = perf_session__new(&file, false, &trace->tool);
+        session = perf_session__new(&data, false, &trace->tool);
         if (session == NULL)
                 return -1;
 
@@ -2730,20 +2783,23 @@ DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_event
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 {
-        DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
         size_t printed = trace__fprintf_threads_header(fp);
         struct rb_node *nd;
+        int i;
 
-        if (threads == NULL) {
-                fprintf(fp, "%s", "Error sorting output by nr_events!\n");
-                return 0;
-        }
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host, i);
 
-        resort_rb__for_each_entry(nd, threads)
-                printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
+                if (threads == NULL) {
+                        fprintf(fp, "%s", "Error sorting output by nr_events!\n");
+                        return 0;
+                }
 
-        resort_rb__delete(threads);
+                resort_rb__for_each_entry(nd, threads)
+                        printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
 
+                resort_rb__delete(threads);
+        }
         return printed;
 }
 
@@ -3002,6 +3058,8 @@ int cmd_trace(int argc, const char **argv)
                      "Set the maximum stack depth when parsing the callchain, "
                      "anything beyond the specified depth will be ignored. "
                      "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
+        OPT_BOOLEAN(0, "print-sample", &trace.print_sample,
+                        "print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
         OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
                         "per thread proc mmap processing timeout in ms"),
         OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
@@ -3053,8 +3111,9 @@ int cmd_trace(int argc, const char **argv)
         }
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-        if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
+        if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled) {
                 record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
+        }
 #endif
 
         if (callchain_param.enabled) {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 50cd6228f506..790ec25919a0 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -5,8 +5,10 @@ HEADERS='
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/perf_event.h
+include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
 include/uapi/linux/stat.h
 include/uapi/linux/vhost.h
@@ -19,6 +21,7 @@ arch/x86/include/asm/cpufeatures.h
 arch/arm/include/uapi/asm/perf_regs.h
 arch/arm64/include/uapi/asm/perf_regs.h
 arch/powerpc/include/uapi/asm/perf_regs.h
+arch/s390/include/uapi/asm/perf_regs.h
 arch/x86/include/uapi/asm/perf_regs.h
 arch/x86/include/uapi/asm/kvm.h
 arch/x86/include/uapi/asm/kvm_perf.h
@@ -28,22 +31,31 @@ arch/x86/include/uapi/asm/vmx.h
 arch/powerpc/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
+arch/alpha/include/uapi/asm/errno.h
+arch/mips/include/asm/errno.h
+arch/mips/include/uapi/asm/errno.h
+arch/parisc/include/uapi/asm/errno.h
+arch/powerpc/include/uapi/asm/errno.h
+arch/sparc/include/uapi/asm/errno.h
+arch/x86/include/uapi/asm/errno.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/asm-generic/bitops/fls64.h
 include/linux/coresight-pmu.h
+include/uapi/asm-generic/errno.h
+include/uapi/asm-generic/errno-base.h
 include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
 '
 
 check () {
   file=$1
-  opts="--ignore-blank-lines --ignore-space-change"
 
   shift
   while [ -n "$*" ]; do
@@ -58,6 +70,11 @@ check () {
 }
 
 
+# Check if we have the kernel headers (tools/perf/../../include), else
+# we're probably on a detached tarball, so no point in trying to check
+# differences.
+test -d ../../include || exit 0
+
 # simple diff check
 for i in $HEADERS; do
   check $i -B
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index cf36de7ea255..0c6d1002b524 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -384,13 +384,13 @@ jvmti_write_code(void *agent, char const *sym,
 }
 
 int
-jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
-                       jvmti_line_info_t *li, int nr_lines)
+jvmti_write_debug_info(void *agent, uint64_t code,
+    int nr_lines, jvmti_line_info_t *li,
+    const char * const * file_names)
 {
         struct jr_code_debug_info rec;
-        size_t sret, len, size, flen;
+        size_t sret, len, size, flen = 0;
         uint64_t addr;
-        const char *fn = file;
         FILE *fp = agent;
         int i;
 
@@ -405,7 +405,9 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
                 return -1;
         }
 
-        flen = strlen(file) + 1;
+        for (i = 0; i < nr_lines; ++i) {
+            flen += strlen(file_names[i]) + 1;
+        }
 
         rec.p.id        = JIT_CODE_DEBUG_INFO;
         size            = sizeof(rec);
@@ -421,7 +423,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
          * file[]   : source file name
          */
         size += nr_lines * sizeof(struct debug_entry);
-        size += flen * nr_lines;
+        size += flen;
         rec.p.total_size = size;
 
         /*
@@ -452,7 +454,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
                 if (sret != 1)
                         goto error;
 
-                sret = fwrite_unlocked(fn, flen, 1, fp);
+                sret = fwrite_unlocked(file_names[i], strlen(file_names[i]) + 1, 1, fp);
                 if (sret != 1)
                         goto error;
         }
diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h
index fe32d8344a82..6ed82f6c06dd 100644
--- a/tools/perf/jvmti/jvmti_agent.h
+++ b/tools/perf/jvmti/jvmti_agent.h
@@ -14,6 +14,7 @@ typedef struct {
         unsigned long   pc;
         int             line_number;
         int             discrim; /* discriminator -- 0 for now */
+        jmethodID       methodID;
 } jvmti_line_info_t;
 
 void *jvmti_open(void);
@@ -22,11 +23,9 @@ int   jvmti_write_code(void *agent, char const *symbol_name,
                        uint64_t vma, void const *code,
                        const unsigned int code_size);
 
-int   jvmti_write_debug_info(void *agent,
-                             uint64_t code,
-                             const char *file,
+int   jvmti_write_debug_info(void *agent, uint64_t code, int nr_lines,
                              jvmti_line_info_t *li,
-                             int nr_lines);
+                             const char * const * file_names);
 
 #if defined(__cplusplus)
 }
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
index c62c9fc9a525..6add3e982614 100644
--- a/tools/perf/jvmti/libjvmti.c
+++ b/tools/perf/jvmti/libjvmti.c
@@ -47,6 +47,7 @@ do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci,
                         tab[lines].pc = (unsigned long)pc;
                         tab[lines].line_number = loc_tab[i].line_number;
                         tab[lines].discrim = 0; /* not yet used */
+                        tab[lines].methodID = m;
                         lines++;
                 } else {
                         break;
@@ -125,6 +126,99 @@ get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t **
         return JVMTI_ERROR_NONE;
 }
 
+static void
+copy_class_filename(const char * class_sign, const char * file_name, char * result, size_t max_length)
+{
+        /*
+        * Assume path name is class hierarchy, this is a common practice with Java programs
+        */
+        if (*class_sign == 'L') {
+                int j, i = 0;
+                char *p = strrchr(class_sign, '/');
+                if (p) {
+                        /* drop the 'L' prefix and copy up to the final '/' */
+                        for (i = 0; i < (p - class_sign); i++)
+                                result[i] = class_sign[i+1];
+                }
+                /*
+                * append file name, we use loops and not string ops to avoid modifying
+                * class_sign which is used later for the symbol name
+                */
+                for (j = 0; i < (max_length - 1) && file_name && j < strlen(file_name); j++, i++)
+                        result[i] = file_name[j];
+
+                result[i] = '\0';
+        } else {
+                /* fallback case */
+                size_t file_name_len = strlen(file_name);
+                strncpy(result, file_name, file_name_len < max_length ? file_name_len : max_length);
+        }
+}
+
+static jvmtiError
+get_source_filename(jvmtiEnv *jvmti, jmethodID methodID, char ** buffer)
+{
+        jvmtiError ret;
+        jclass decl_class;
+        char *file_name = NULL;
+        char *class_sign = NULL;
+        char fn[PATH_MAX];
+        size_t len;
+
+        ret = (*jvmti)->GetMethodDeclaringClass(jvmti, methodID, &decl_class);
+        if (ret != JVMTI_ERROR_NONE) {
+                print_error(jvmti, "GetMethodDeclaringClass", ret);
+                return ret;
+        }
+
+        ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name);
+        if (ret != JVMTI_ERROR_NONE) {
+                print_error(jvmti, "GetSourceFileName", ret);
+                return ret;
+        }
+
+        ret = (*jvmti)->GetClassSignature(jvmti, decl_class, &class_sign, NULL);
+        if (ret != JVMTI_ERROR_NONE) {
+                print_error(jvmti, "GetClassSignature", ret);
+                goto free_file_name_error;
+        }
+
+        copy_class_filename(class_sign, file_name, fn, PATH_MAX);
+        len = strlen(fn);
+        *buffer = malloc((len + 1) * sizeof(char));
+        if (!*buffer) {
+                print_error(jvmti, "GetClassSignature", ret);
+                ret = JVMTI_ERROR_OUT_OF_MEMORY;
+                goto free_class_sign_error;
+        }
+        strcpy(*buffer, fn);
+        ret = JVMTI_ERROR_NONE;
+
+free_class_sign_error:
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign);
+free_file_name_error:
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name);
+
+        return ret;
+}
+
+static jvmtiError
+fill_source_filenames(jvmtiEnv *jvmti, int nr_lines,
+                      const jvmti_line_info_t * line_tab,
+                      char ** file_names)
+{
+        int index;
+        jvmtiError ret;
+
+        for (index = 0; index < nr_lines; ++index) {
+                ret = get_source_filename(jvmti, line_tab[index].methodID, &(file_names[index]));
+                if (ret != JVMTI_ERROR_NONE)
+                        return ret;
+        }
+
+        return JVMTI_ERROR_NONE;
+}
+
 static void JNICALL
 compiled_method_load_cb(jvmtiEnv *jvmti,
                         jmethodID method,
@@ -135,16 +229,18 @@ compiled_method_load_cb(jvmtiEnv *jvmti,
                         const void *compile_info)
 {
         jvmti_line_info_t *line_tab = NULL;
+        char ** line_file_names = NULL;
         jclass decl_class;
         char *class_sign = NULL;
         char *func_name = NULL;
         char *func_sign = NULL;
-        char *file_name= NULL;
+        char *file_name = NULL;
         char fn[PATH_MAX];
         uint64_t addr = (uint64_t)(uintptr_t)code_addr;
         jvmtiError ret;
         int nr_lines = 0; /* in line_tab[] */
         size_t len;
+        int output_debug_info = 0;
 
         ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method,
                                                 &decl_class);
@@ -158,6 +254,19 @@ compiled_method_load_cb(jvmtiEnv *jvmti,
                 if (ret != JVMTI_ERROR_NONE) {
                         warnx("jvmti: cannot get line table for method");
                         nr_lines = 0;
+                } else if (nr_lines > 0) {
+                        line_file_names = malloc(sizeof(char*) * nr_lines);
+                        if (!line_file_names) {
+                                warnx("jvmti: cannot allocate space for line table method names");
+                        } else {
+                                memset(line_file_names, 0, sizeof(char*) * nr_lines);
+                                ret = fill_source_filenames(jvmti, nr_lines, line_tab, line_file_names);
+                                if (ret != JVMTI_ERROR_NONE) {
+                                        warnx("jvmti: fill_source_filenames failed");
+                                } else {
+                                        output_debug_info = 1;
+                                }
+                        }
                 }
         }
 
@@ -181,33 +290,14 @@ compiled_method_load_cb(jvmtiEnv *jvmti,
                 goto error;
         }
 
-        /*
-         * Assume path name is class hierarchy, this is a common practice with Java programs
-         */
-        if (*class_sign == 'L') {
-                int j, i = 0;
-                char *p = strrchr(class_sign, '/');
-                if (p) {
-                        /* drop the 'L' prefix and copy up to the final '/' */
-                        for (i = 0; i < (p - class_sign); i++)
-                                fn[i] = class_sign[i+1];
-                }
-                /*
-                 * append file name, we use loops and not string ops to avoid modifying
-                 * class_sign which is used later for the symbol name
-                 */
-                for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++)
-                        fn[i] = file_name[j];
-                fn[i] = '\0';
-        } else {
-                /* fallback case */
-                strcpy(fn, file_name);
-        }
+        copy_class_filename(class_sign, file_name, fn, PATH_MAX);
+
         /*
          * write source line info record if we have it
          */
-        if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines))
-                warnx("jvmti: write_debug_info() failed");
+        if (output_debug_info)
+                if (jvmti_write_debug_info(jvmti_agent, addr, nr_lines, line_tab, (const char * const *) line_file_names))
+                        warnx("jvmti: write_debug_info() failed");
 
         len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2;
         {
@@ -223,6 +313,13 @@ error:
         (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign);
         (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name);
         free(line_tab);
+        while (line_file_names && (nr_lines > 0)) {
+            if (line_file_names[nr_lines - 1]) {
+                free(line_file_names[nr_lines - 1]);
+            }
+            nr_lines -= 1;
+        }
+        free(line_file_names);
 }
 
 static void JNICALL
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
index 345f5d6e9ed5..fdf75d45efff 100644
--- a/tools/perf/perf-completion.sh
+++ b/tools/perf/perf-completion.sh
@@ -162,8 +162,37 @@ __perf_main ()
         # List possible events for -e option
         elif [[ $prev == @("-e"|"--event") &&
                 $prev_skip_opts == @(record|stat|top) ]]; then
-                evts=$($cmd list --raw-dump)
-                __perfcomp_colon "$evts" "$cur"
+
+                local cur1=${COMP_WORDS[COMP_CWORD]}
+                local raw_evts=$($cmd list --raw-dump)
+                local arr s tmp result
+
+                if [[ "$cur1" == */* && ${cur1#*/} =~ ^[A-Z] ]]; then
+                        OLD_IFS="$IFS"
+                        IFS=" "
+                        arr=($raw_evts)
+                        IFS="$OLD_IFS"
+
+                        for s in ${arr[@]}
+                        do
+                                if [[ "$s" == *cpu/* ]]; then
+                                        tmp=${s#*cpu/}
+                                        result=$result" ""cpu/"${tmp^^}
+                                else
+                                        result=$result" "$s
+                                fi
+                        done
+
+                        evts=${result}" "$(ls /sys/bus/event_source/devices/cpu/events)
+                else
+                        evts=${raw_evts}" "$(ls /sys/bus/event_source/devices/cpu/events)
+                fi
+
+                if [[ "$cur1" == , ]]; then
+                        __perfcomp_colon "$evts" ""
+                else
+                        __perfcomp_colon "$evts" "$cur1"
+                fi
         else
                 # List subcommands for perf commands
                 if [[ $prev_skip_opts == @(kvm|kmem|mem|lock|sched|
@@ -246,11 +275,21 @@ fi
 type perf &>/dev/null &&
 _perf()
 {
+        if [[ "$COMP_WORDBREAKS" != *,* ]]; then
+                COMP_WORDBREAKS="${COMP_WORDBREAKS},"
+                export COMP_WORDBREAKS
+        fi
+
+        if [[ "$COMP_WORDBREAKS" == *:* ]]; then
+                COMP_WORDBREAKS="${COMP_WORDBREAKS/:/}"
+                export COMP_WORDBREAKS
+        fi
+
         local cur words cword prev
         if [ $preload_get_comp_words_by_ref = "true" ]; then
-                _get_comp_words_by_ref -n =: cur words cword prev
+                _get_comp_words_by_ref -n =:, cur words cword prev
         else
-                __perf_get_comp_words_by_ref -n =: cur words cword prev
+                __perf_get_comp_words_by_ref -n =:, cur words cword prev
         fi
         __perf_main
 } &&
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 62b13518bc6e..1b3fc8ec0fa2 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -73,7 +73,7 @@ static struct cmd_struct commands[] = {
         { "lock",       cmd_lock,       0 },
         { "kvm",        cmd_kvm,        0 },
         { "test",       cmd_test,       0 },
-#ifdef HAVE_LIBAUDIT_SUPPORT
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
         { "trace",      cmd_trace,      0 },
 #endif
         { "inject",     cmd_inject,     0 },
@@ -485,7 +485,7 @@ int main(int argc, const char **argv)
                 argv[0] = cmd;
         }
         if (strstarts(cmd, "trace")) {
-#ifdef HAVE_LIBAUDIT_SUPPORT
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
                 setup_path();
                 argv[0] = "trace";
                 return cmd_trace(argc, argv);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index f75f3dec7485..cfe46236a5e5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -50,6 +50,7 @@ struct record_opts {
         bool         sample_time_set;
         bool         sample_cpu;
         bool         period;
+        bool         period_set;
         bool         running_time;
         bool         full_auxtrace;
         bool         auxtrace_snapshot_mode;
@@ -66,6 +67,7 @@ struct record_opts {
         unsigned int user_freq;
         u64          branch_stack;
         u64          sample_intr_regs;
+        u64          sample_user_regs;
         u64          default_interval;
         u64          user_interval;
         size_t       auxtrace_snapshot_size;
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json
new file mode 100644
index 000000000000..2db45c40ebc7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json
@@ -0,0 +1,62 @@
+[
+    {
+        "PublicDescription": "Attributable Level 1 data cache access, read",
+        "EventCode": "0x40",
+        "EventName": "l1d_cache_rd",
+        "BriefDescription": "L1D cache read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache access, write ",
+        "EventCode": "0x41",
+        "EventName": "l1d_cache_wr",
+        "BriefDescription": "L1D cache write",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, read",
+        "EventCode": "0x42",
+        "EventName": "l1d_cache_refill_rd",
+        "BriefDescription": "L1D cache refill read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, write",
+        "EventCode": "0x43",
+        "EventName": "l1d_cache_refill_wr",
+        "BriefDescription": "L1D refill write",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data TLB refill, read",
+        "EventCode": "0x4C",
+        "EventName": "l1d_tlb_refill_rd",
+        "BriefDescription": "L1D tlb refill read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data TLB refill, write",
+        "EventCode": "0x4D",
+        "EventName": "l1d_tlb_refill_wr",
+        "BriefDescription": "L1D tlb refill write",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data or unified TLB access, read",
+        "EventCode": "0x4E",
+        "EventName": "l1d_tlb_rd",
+        "BriefDescription": "L1D tlb read",
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data or unified TLB access, write",
+        "EventCode": "0x4F",
+        "EventName": "l1d_tlb_wr",
+        "BriefDescription": "L1D tlb write",
+    },
+    {
+        "PublicDescription": "Bus access read",
+        "EventCode": "0x60",
+        "EventName": "bus_access_rd",
+        "BriefDescription": "Bus access read",
+   },
+   {
+        "PublicDescription": "Bus access write",
+        "EventCode": "0x61",
+        "EventName": "bus_access_wr",
+        "BriefDescription": "Bus access write",
+   }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json
new file mode 100644
index 000000000000..3b6208763e50
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json
@@ -0,0 +1,27 @@
+[
+  {,
+    "EventCode": "0x7A",
+    "EventName": "BR_INDIRECT_SPEC",
+    "BriefDescription": "Branch speculatively executed - Indirect branch"
+  },
+  {,
+    "EventCode": "0xC9",
+    "EventName": "BR_COND",
+    "BriefDescription": "Conditional branch executed"
+  },
+  {,
+    "EventCode": "0xCA",
+    "EventName": "BR_INDIRECT_MISPRED",
+    "BriefDescription": "Indirect branch mispredicted"
+  },
+  {,
+    "EventCode": "0xCB",
+    "EventName": "BR_INDIRECT_MISPRED_ADDR",
+    "BriefDescription": "Indirect branch mispredicted because of address miscompare"
+  },
+  {,
+    "EventCode": "0xCC",
+    "EventName": "BR_COND_MISPRED",
+    "BriefDescription": "Conditional branch mispredicted"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json
new file mode 100644
index 000000000000..480d9f7460ab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json
@@ -0,0 +1,22 @@
+[
+  {,
+    "EventCode": "0x60",
+    "EventName": "BUS_ACCESS_LD",
+    "BriefDescription": "Bus access - Read"
+  },
+  {,
+    "EventCode": "0x61",
+    "EventName": "BUS_ACCESS_ST",
+    "BriefDescription": "Bus access - Write"
+  },
+  {,
+    "EventCode": "0xC0",
+    "EventName": "EXT_MEM_REQ",
+    "BriefDescription": "External memory request"
+  },
+  {,
+    "EventCode": "0xC1",
+    "EventName": "EXT_MEM_REQ_NC",
+    "BriefDescription": "Non-cacheable external memory request"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json
new file mode 100644
index 000000000000..11baad6344b9
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json
@@ -0,0 +1,27 @@
+[
+  {,
+    "EventCode": "0xC2",
+    "EventName": "PREFETCH_LINEFILL",
+    "BriefDescription": "Linefill because of prefetch"
+  },
+  {,
+    "EventCode": "0xC3",
+    "EventName": "PREFETCH_LINEFILL_DROP",
+    "BriefDescription": "Instruction Cache Throttle occurred"
+  },
+  {,
+    "EventCode": "0xC4",
+    "EventName": "READ_ALLOC_ENTER",
+    "BriefDescription": "Entering read allocate mode"
+  },
+  {,
+    "EventCode": "0xC5",
+    "EventName": "READ_ALLOC",
+    "BriefDescription": "Read allocate mode"
+  },
+  {,
+    "EventCode": "0xC8",
+    "EventName": "EXT_SNOOP",
+    "BriefDescription": "SCU Snooped data from another CPU for this CPU"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json
new file mode 100644
index 000000000000..480d9f7460ab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json
@@ -0,0 +1,22 @@
+[
+  {,
+    "EventCode": "0x60",
+    "EventName": "BUS_ACCESS_LD",
+    "BriefDescription": "Bus access - Read"
+  },
+  {,
+    "EventCode": "0x61",
+    "EventName": "BUS_ACCESS_ST",
+    "BriefDescription": "Bus access - Write"
+  },
+  {,
+    "EventCode": "0xC0",
+    "EventName": "EXT_MEM_REQ",
+    "BriefDescription": "External memory request"
+  },
+  {,
+    "EventCode": "0xC1",
+    "EventName": "EXT_MEM_REQ_NC",
+    "BriefDescription": "Non-cacheable external memory request"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json
new file mode 100644
index 000000000000..73a22402d003
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json
@@ -0,0 +1,32 @@
+[
+  {,
+    "EventCode": "0x86",
+    "EventName": "EXC_IRQ",
+    "BriefDescription": "Exception taken, IRQ"
+  },
+  {,
+    "EventCode": "0x87",
+    "EventName": "EXC_FIQ",
+    "BriefDescription": "Exception taken, FIQ"
+  },
+  {,
+    "EventCode": "0xC6",
+    "EventName": "PRE_DECODE_ERR",
+    "BriefDescription": "Pre-decode error"
+  },
+  {,
+    "EventCode": "0xD0",
+    "EventName": "L1I_CACHE_ERR",
+    "BriefDescription": "L1 Instruction Cache (data or tag) memory error"
+  },
+  {,
+    "EventCode": "0xD1",
+    "EventName": "L1D_CACHE_ERR",
+    "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable"
+  },
+  {,
+    "EventCode": "0xD2",
+    "EventName": "TLB_ERR",
+    "BriefDescription": "TLB memory error"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json
new file mode 100644
index 000000000000..3149fb90555a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json
@@ -0,0 +1,52 @@
+[
+  {,
+    "EventCode": "0xC7",
+    "EventName": "STALL_SB_FULL",
+    "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full"
+  },
+  {,
+    "EventCode": "0xE0",
+    "EventName": "OTHER_IQ_DEP_STALL",
+    "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error"
+  },
+  {,
+    "EventCode": "0xE1",
+    "EventName": "IC_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed"
+  },
+  {,
+    "EventCode": "0xE2",
+    "EventName": "IUTLB_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed"
+  },
+  {,
+    "EventCode": "0xE3",
+    "EventName": "DECODE_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed"
+  },
+  {,
+    "EventCode": "0xE4",
+    "EventName": "OTHER_INTERLOCK_STALL",
+    "BriefDescription": "Cycles there is an interlock other than  Advanced SIMD/Floating-point instructions or load/store instruction"
+  },
+  {,
+    "EventCode": "0xE5",
+    "EventName": "AGU_DEP_STALL",
+    "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU"
+  },
+  {,
+    "EventCode": "0xE6",
+    "EventName": "SIMD_DEP_STALL",
+    "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation."
+  },
+  {,
+    "EventCode": "0xE7",
+    "EventName": "LD_DEP_STALL",
+    "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss"
+  },
+  {,
+    "EventCode": "0xE8",
+    "EventName": "ST_DEP_STALL",
+    "BriefDescription": "Cycles there is a stall in the Wr stage because of a store"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
new file mode 100644
index 000000000000..e61c9ca6cf9e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -0,0 +1,16 @@
+# Format:
+#       MIDR,Version,JSON/file/pathname,Type
+#
+# where
+#       MIDR    Processor version
+#               Variant[23:20] and Revision [3:0] should be zero.
+#       Version could be used to track version of of JSON file
+#               but currently unused.
+#       JSON/file/pathname is the path to JSON file, relative
+#               to tools/perf/pmu-events/arch/arm64/.
+#       Type is core, uncore etc
+#
+#
+#Family-model,Version,Filename,EventType
+0x00000000420f5160,v1,cavium,core
+0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core
diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
index a0f3a11ca19f..229150e7ab7d 100644
--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -13,13 +13,5 @@
 #
 
 # Power8 entries
-004b0000,1,power8,core
-004b0201,1,power8,core
-004c0000,1,power8,core
-004d0000,1,power8,core
-004d0100,1,power8,core
-004d0200,1,power8,core
-004c0100,1,power8,core
-004e0100,1,power9,core
-004e0200,1,power9,core
-004e1200,1,power9,core
+004[bcd][[:xdigit:]]{4},1,power8,core
+004e[[:xdigit:]]{4},1,power9,core
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
index 18f6645f2897..7945c5196c43 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
@@ -125,11 +125,6 @@
     "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied"
   },
   {,
-    "EventCode": "0x3006C",
-    "EventName": "PM_RUN_CYC_SMT2_MODE",
-    "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT2 mode"
-  },
-  {,
     "EventCode": "0x1C058",
     "EventName": "PM_DTLB_MISS_16G",
     "BriefDescription": "Data TLB Miss page size 16G"
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
index c63a919eda98..bd8361b5fd6a 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
@@ -1,10 +1,5 @@
 [
   {,
-    "EventCode": "0x3E15C",
-    "EventName": "PM_MRK_L2_TM_ST_ABORT_SISTER",
-    "BriefDescription": "TM marked store abort for this thread"
-  },
-  {,
     "EventCode": "0x25044",
     "EventName": "PM_IPTEG_FROM_L31_MOD",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a instruction side request"
@@ -369,4 +364,4 @@
     "EventName": "PM_IPTEG_FROM_L31_ECO_MOD",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
index b9df54fb37e3..22f9f32060a8 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
@@ -1,10 +1,5 @@
 [
   {,
-    "EventCode": "0x3C052",
-    "EventName": "PM_DATA_SYS_PUMP_MPRED",
-    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load"
-  },
-  {,
     "EventCode": "0x3013E",
     "EventName": "PM_MRK_STALL_CMPLU_CYC",
     "BriefDescription": "Number of cycles the marked instruction is experiencing a stall while it is next to complete (NTC)"
@@ -255,6 +250,11 @@
     "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L3 data cache"
   },
   {,
+    "EventCode": "0x3C052",
+    "EventName": "PM_DATA_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load"
+  },
+  {,
     "EventCode": "0x4D142",
     "EventName": "PM_MRK_DATA_FROM_L3",
     "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a marked load"
@@ -435,21 +435,6 @@
     "BriefDescription": "ITLB Reloaded. Counts 1 per ITLB miss for HPT but multiple for radix depending on number of levels traveresed"
   },
   {,
-    "EventCode": "0x2D024",
-    "EventName": "PM_RADIX_PWC_L2_HIT",
-    "BriefDescription": "A radix translation attempt missed in the TLB but hit on both the first and second levels of page walk cache."
-  },
-  {,
-    "EventCode": "0x3F056",
-    "EventName": "PM_RADIX_PWC_L3_HIT",
-    "BriefDescription": "A radix translation attempt missed in the TLB but hit on the first, second, and third levels of page walk cache."
-  },
-  {,
-    "EventCode": "0x4E014",
-    "EventName": "PM_TM_TX_PASS_RUN_INST",
-    "BriefDescription": "Run instructions spent in successful transactions"
-  },
-  {,
     "EventCode": "0x1E044",
     "EventName": "PM_DPTEG_FROM_L3_NO_CONFLICT",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
@@ -644,4 +629,4 @@
     "EventName": "PM_MRK_BR_MPRED_CMPL",
     "BriefDescription": "Marked Branch Mispredicted"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json
index 54cc3be00fc2..5ce312973f1e 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
@@ -80,6 +80,11 @@
     "BriefDescription": "A radix translation attempt missed in the TLB and all levels of page walk cache."
   },
   {,
+    "EventCode": "0x26882",
+    "EventName": "PM_L2_DC_INV",
+    "BriefDescription": "D-cache invalidates sent over the reload bus to the core"
+  },
+  {,
     "EventCode": "0x24048",
     "EventName": "PM_INST_FROM_LMEM",
     "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's Memory due to an instruction fetch (not prefetch)"
@@ -95,11 +100,6 @@
     "BriefDescription": "Number of TM transactions that passed"
   },
   {,
-    "EventCode": "0xD1A0",
-    "EventName": "PM_MRK_LSU_FLUSH_LHS",
-    "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
-  },
-  {,
     "EventCode": "0xF088",
     "EventName": "PM_LSU0_STORE_REJECT",
     "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
@@ -127,7 +127,7 @@
   {,
     "EventCode": "0xD08C",
     "EventName": "PM_LSU2_LDMX_FIN",
-    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])"
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
   },
   {,
     "EventCode": "0x300F8",
@@ -205,11 +205,6 @@
     "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load"
   },
   {,
-    "EventCode": "0xF0B4",
-    "EventName": "PM_DC_PREF_CONS_ALLOC",
-    "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch"
-  },
-  {,
     "EventCode": "0xF894",
     "EventName": "PM_LSU3_L1_CAM_CANCEL",
     "BriefDescription": "ls3 l1 tm cam cancel"
@@ -220,21 +215,11 @@
     "BriefDescription": "Dispatch Flush: TLBIE"
   },
   {,
-    "EventCode": "0xD1A4",
-    "EventName": "PM_MRK_LSU_FLUSH_SAO",
-    "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush"
-  },
-  {,
     "EventCode": "0x4E11E",
     "EventName": "PM_MRK_DATA_FROM_DMEM_CYC",
     "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group (Distant) due to a marked load"
   },
   {,
-    "EventCode": "0x5894",
-    "EventName": "PM_LWSYNC",
-    "BriefDescription": "Lwsync instruction decoded and transferred"
-  },
-  {,
     "EventCode": "0x14156",
     "EventName": "PM_MRK_DATA_FROM_L2_CYC",
     "BriefDescription": "Duration in cycles to reload from local core's L2 due to a marked load"
@@ -245,11 +230,6 @@
     "BriefDescription": "Read clearing SC"
   },
   {,
-    "EventCode": "0x50A0",
-    "EventName": "PM_HWSYNC",
-    "BriefDescription": "Hwsync instruction decoded and transferred"
-  },
-  {,
     "EventCode": "0x168B0",
     "EventName": "PM_L3_P1_NODE_PUMP",
     "BriefDescription": "L3 PF sent with nodal scope port 1, counts even retried requests"
@@ -265,6 +245,11 @@
     "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a marked load"
   },
   {,
+    "EventCode": "0x468AE",
+    "EventName": "PM_L3_P3_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 3 (memory only), every retry counted"
+  },
+  {,
     "EventCode": "0x460A8",
     "EventName": "PM_SN_HIT",
     "BriefDescription": "Any port snooper hit L3.  Up to 4 can happen in a cycle but we only count 1"
@@ -280,11 +265,6 @@
     "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism"
   },
   {,
-    "EventCode": "0xF0BC",
-    "EventName": "PM_LS2_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
-  {,
     "EventCode": "0xD0AC",
     "EventName": "PM_SRQ_SYNC_CYC",
     "BriefDescription": "A sync is in the S2Q (edge detect to count)"
@@ -380,26 +360,11 @@
     "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT4 mode"
   },
   {,
-    "EventCode": "0x5088",
-    "EventName": "PM_DECODE_FUSION_OP_PRESERV",
-    "BriefDescription": "Destructive op operand preservation"
-  },
-  {,
     "EventCode": "0x1D14E",
     "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE_CYC",
     "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load"
   },
   {,
-    "EventCode": "0x509C",
-    "EventName": "PM_FORCED_NOP",
-    "BriefDescription": "Instruction was forced to execute as a nop because it was found to behave like a nop (have no effect) at decode time"
-  },
-  {,
-    "EventCode": "0xC098",
-    "EventName": "PM_LS2_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
-  {,
     "EventCode": "0x20058",
     "EventName": "PM_DARQ1_10_12_ENTRIES",
     "BriefDescription": "Cycles in which 10 or  more DARQ1 entries (out of 12) are in use"
@@ -435,11 +400,6 @@
     "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
   },
   {,
-    "EventCode": "0x4505E",
-    "EventName": "PM_FLOP_CMPL",
-    "BriefDescription": "Floating Point Operation Finished"
-  },
-  {,
     "EventCode": "0x1D144",
     "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT",
     "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a marked load"
@@ -480,14 +440,9 @@
     "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT.  The EAT forces a mispredict in this case since there is no predicated target to validate.  This is a rare case that may occur when the EAT is full and a branch is issued"
   },
   {,
-    "EventCode": "0xC094",
-    "EventName": "PM_LS0_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
-  {,
-    "EventCode": "0xF8BC",
-    "EventName": "PM_LS3_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+    "EventCode": "0x460AE",
+    "EventName": "PM_L3_P2_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 2 (memory only), every retry counted"
   },
   {,
     "EventCode": "0x58B0",
@@ -505,11 +460,6 @@
     "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)"
   },
   {,
-    "EventCode": "0xD998",
-    "EventName": "PM_MRK_LSU_FLUSH_EMSH",
-    "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
-  },
-  {,
     "EventCode": "0xF8A0",
     "EventName": "PM_NON_DATA_STORE",
     "BriefDescription": "All ops that drain from s2q to L2 and contain no data"
@@ -525,11 +475,6 @@
     "BriefDescription": "Unconditional Branch Completed. HW branch prediction was not used for this branch. This can be an I-form branch, a B-form branch with BO-field set to branch always, or a B-form branch which was covenrted to a Resolve."
   },
   {,
-    "EventCode": "0x1F056",
-    "EventName": "PM_RADIX_PWC_L1_HIT",
-    "BriefDescription": "A radix translation attempt missed in the TLB and only the first level page walk cache was a hit."
-  },
-  {,
     "EventCode": "0xF8A8",
     "EventName": "PM_DC_PREF_FUZZY_CONF",
     "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)"
@@ -545,6 +490,11 @@
     "BriefDescription": "Load tm L1 miss"
   },
   {,
+    "EventCode": "0xC880",
+    "EventName": "PM_LS1_LD_VECTOR_FIN",
+    "BriefDescription": ""
+  },
+  {,
     "EventCode": "0x2894",
     "EventName": "PM_TM_OUTER_TEND",
     "BriefDescription": "Completion time outer tend"
@@ -565,21 +515,11 @@
     "BriefDescription": "Marked derat reload (miss) for any page size"
   },
   {,
-    "EventCode": "0x160A0",
-    "EventName": "PM_L3_PF_MISS_L3",
-    "BriefDescription": "L3 PF missed in L3"
-  },
-  {,
     "EventCode": "0x1C04A",
     "EventName": "PM_DATA_FROM_RL2L3_SHR",
     "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
   },
   {,
-    "EventCode": "0xD99C",
-    "EventName": "PM_MRK_LSU_FLUSH_UE",
-    "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time"
-  },
-  {,
     "EventCode": "0x268B0",
     "EventName": "PM_L3_P1_GRP_PUMP",
     "BriefDescription": "L3 PF sent with grp scope port 1, counts even retried requests"
@@ -630,11 +570,6 @@
     "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding"
   },
   {,
-    "EventCode": "0x5884",
-    "EventName": "PM_DECODE_LANES_NOT_AVAIL",
-    "BriefDescription": "Decode has something to transmit but dispatch lanes are not available"
-  },
-  {,
     "EventCode": "0x3C042",
     "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT",
     "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a demand load"
@@ -690,9 +625,9 @@
     "BriefDescription": "False LHS match detected"
   },
   {,
-    "EventCode": "0xD9A4",
-    "EventName": "PM_MRK_LSU_FLUSH_LARX_STCX",
-    "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread.  A stcx is flushed because an older stcx is in the LMQ.  The flush happens when the older larx/stcx relaunches"
+    "EventCode": "0xF0B0",
+    "EventName": "PM_L3_LD_PREF",
+    "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest"
   },
   {,
     "EventCode": "0x4D012",
@@ -715,9 +650,9 @@
     "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)"
   },
   {,
-    "EventCode": "0xF8B8",
-    "EventName": "PM_LS1_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+    "EventCode": "0x160A0",
+    "EventName": "PM_L3_PF_MISS_L3",
+    "BriefDescription": "L3 PF missed in L3"
   },
   {,
     "EventCode": "0x408C",
@@ -765,11 +700,6 @@
     "BriefDescription": "Completion time nested tend"
   },
   {,
-    "EventCode": "0x36084",
-    "EventName": "PM_L2_RCST_DISP",
-    "BriefDescription": "All D-side store dispatch attempts for this thread"
-  },
-  {,
     "EventCode": "0x368A0",
     "EventName": "PM_L3_PF_OFF_CHIP_CACHE",
     "BriefDescription": "L3 PF from Off chip cache"
@@ -830,11 +760,6 @@
     "BriefDescription": "Rotating sample of 16 snoop valids"
   },
   {,
-    "EventCode": "0x16084",
-    "EventName": "PM_L2_RCLD_DISP",
-    "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
-  },
-  {,
     "EventCode": "0x1608C",
     "EventName": "PM_RC0_BUSY",
     "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)"
@@ -842,7 +767,7 @@
   {,
     "EventCode": "0x36082",
     "EventName": "PM_L2_LD_DISP",
-    "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)."
+    "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)"
   },
   {,
     "EventCode": "0xF8B0",
@@ -905,11 +830,6 @@
     "BriefDescription": "Instruction prefetch requests"
   },
   {,
-    "EventCode": "0xC898",
-    "EventName": "PM_LS3_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
-  {,
     "EventCode": "0x488C",
     "EventName": "PM_IC_PREF_WRITE",
     "BriefDescription": "Instruction prefetch written into IL1"
@@ -1017,7 +937,7 @@
   {,
     "EventCode": "0x3E05E",
     "EventName": "PM_L3_CO_MEPF",
-    "BriefDescription": "L3 castouts in Mepf state for this thread"
+    "BriefDescription": "L3 CO of line in Mep state (includes casthrough to memory).  The Mepf state indicates that a line was brought in to satisfy an L3 prefetch request"
   },
   {,
     "EventCode": "0x460A2",
@@ -1205,11 +1125,6 @@
     "BriefDescription": "Non transactional conflict from LSU, gets reported to TEXASR"
   },
   {,
-    "EventCode": "0xD198",
-    "EventName": "PM_MRK_LSU_FLUSH_ATOMIC",
-    "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices.  If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed"
-  },
-  {,
     "EventCode": "0x201E0",
     "EventName": "PM_MRK_DATA_FROM_MEMORY",
     "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a marked load"
@@ -1295,11 +1210,6 @@
     "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)"
   },
   {,
-    "EventCode": "0xC894",
-    "EventName": "PM_LS1_UNALIGNED_LD",
-    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
-  {,
     "EventCode": "0x360A2",
     "EventName": "PM_L3_L2_CO_HIT",
     "BriefDescription": "L2 CO hits"
@@ -1325,11 +1235,6 @@
     "BriefDescription": "L2 Castouts - Shared (Tx,Sx)"
   },
   {,
-    "EventCode": "0xD884",
-    "EventName": "PM_LSU3_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
-  {,
     "EventCode": "0x26092",
     "EventName": "PM_L2_LD_MISS_64B",
     "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B(i.e., M=1)"
@@ -1362,12 +1267,12 @@
   {,
     "EventCode": "0xD8A8",
     "EventName": "PM_ISLB_MISS",
-    "BriefDescription": "Instruction SLB miss - Total of all segment sizes"
+    "BriefDescription": "Instruction SLB Miss - Total of all segment sizes"
   },
   {,
-    "EventCode": "0xD19C",
-    "EventName": "PM_MRK_LSU_FLUSH_RELAUNCH_MISS",
-    "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent"
+    "EventCode": "0x368AE",
+    "EventName": "PM_L3_P1_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted"
   },
   {,
     "EventCode": "0x260A2",
@@ -1385,6 +1290,11 @@
     "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tbegin. This is a short delay, and it includes ROT"
   },
   {,
+    "EventCode": "0xC084",
+    "EventName": "PM_LS2_LD_VECTOR_FIN",
+    "BriefDescription": ""
+  },
+  {,
     "EventCode": "0x1608E",
     "EventName": "PM_ST_CAUSED_FAIL",
     "BriefDescription": "Non-TM Store caused any thread to fail"
@@ -1410,11 +1320,6 @@
     "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
   },
   {,
-    "EventCode": "0xD084",
-    "EventName": "PM_LSU2_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
-  {,
     "EventCode": "0x48B8",
     "EventName": "PM_BR_MPRED_TAKEN_TA",
     "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Target Address Prediction from the Count Cache or Link Stack.  Only XL-form branches that resolved Taken set this event."
@@ -1450,29 +1355,24 @@
     "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software."
   },
   {,
+    "EventCode": "0x36084",
+    "EventName": "PM_L2_RCST_DISP",
+    "BriefDescription": "All D-side store dispatch attempts for this thread"
+  },
+  {,
     "EventCode": "0x45054",
     "EventName": "PM_FMA_CMPL",
     "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. "
   },
   {,
-    "EventCode": "0x5090",
-    "EventName": "PM_SHL_ST_DISABLE",
-    "BriefDescription": "Store-Hit-Load Table Read Hit with entry Disabled (entry was disabled due to the entry shown to not prevent the flush)"
-  },
-  {,
     "EventCode": "0x201E8",
     "EventName": "PM_THRESH_EXC_512",
     "BriefDescription": "Threshold counter exceeded a value of 512"
   },
   {,
-    "EventCode": "0x5084",
-    "EventName": "PM_DECODE_FUSION_EXT_ADD",
-    "BriefDescription": "32-bit extended addition"
-  },
-  {,
     "EventCode": "0x36080",
     "EventName": "PM_L2_INST",
-    "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)."
+    "BriefDescription": "All successful I-side dispatches for this thread   (excludes i_l2mru_tch reqs)"
   },
   {,
     "EventCode": "0x3504C",
@@ -1555,21 +1455,11 @@
     "BriefDescription": "Memory Read With Intent to Modify for this thread"
   },
   {,
-    "EventCode": "0x26882",
-    "EventName": "PM_L2_DC_INV",
-    "BriefDescription": "D-cache invalidates sent over the reload bus to the core"
-  },
-  {,
     "EventCode": "0xC090",
     "EventName": "PM_LSU_STCX",
     "BriefDescription": "STCX sent to nest, i.e. total"
   },
   {,
-    "EventCode": "0xD080",
-    "EventName": "PM_LSU0_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
-  {,
     "EventCode": "0x2C120",
     "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT",
     "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a marked load"
@@ -1610,11 +1500,6 @@
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request"
   },
   {,
-    "EventCode": "0xD9A0",
-    "EventName": "PM_MRK_LSU_FLUSH_LHL_SHL",
-    "BriefDescription": "The instruction was flushed because of a sequential load/store consistency.  If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)."
-  },
-  {,
     "EventCode": "0x35042",
     "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a instruction side request"
@@ -1692,7 +1577,7 @@
   {,
     "EventCode": "0x2001A",
     "EventName": "PM_NTC_ALL_FIN",
-    "BriefDescription": "Cycles after all instructions have finished to group completed"
+    "BriefDescription": "Cycles after instruction finished to instruction completed."
   },
   {,
     "EventCode": "0x3005A",
@@ -1710,6 +1595,11 @@
     "BriefDescription": "ls1 l1 tm cam cancel"
   },
   {,
+    "EventCode": "0x268AE",
+    "EventName": "PM_L3_P3_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 3, every retry counted"
+  },
+  {,
     "EventCode": "0xE884",
     "EventName": "PM_LS1_ERAT_MISS_PREF",
     "BriefDescription": "LS1 Erat miss due to prefetch"
@@ -1742,7 +1632,7 @@
   {,
     "EventCode": "0x160B6",
     "EventName": "PM_L3_WI0_BUSY",
-    "BriefDescription": "Rotating sample of 8 WI valid"
+    "BriefDescription": "Rotating sample of 8 WI valid (duplicate)"
   },
   {,
     "EventCode": "0x368AC",
@@ -1790,9 +1680,9 @@
     "BriefDescription": "L2 guess system (VGS or RNS) and guess was correct (ie data beyond-group)"
   },
   {,
-    "EventCode": "0x589C",
-    "EventName": "PM_PTESYNC",
-    "BriefDescription": "ptesync instruction counted when the instruction is decoded and transmitted"
+    "EventCode": "0x260AE",
+    "EventName": "PM_L3_P2_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 2, every retry counted"
   },
   {,
     "EventCode": "0x26086",
@@ -1825,6 +1715,11 @@
     "BriefDescription": "Store-Hit-Load Table Read Hit with entry Enabled"
   },
   {,
+    "EventCode": "0x46882",
+    "EventName": "PM_L2_ST_HIT",
+    "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits"
+  },
+  {,
     "EventCode": "0x360AC",
     "EventName": "PM_L3_SN0_BUSY",
     "BriefDescription": "Lifetime, sample of snooper machine 0 valid"
@@ -1845,11 +1740,6 @@
     "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread"
   },
   {,
-    "EventCode": "0xF8B4",
-    "EventName": "PM_DC_PREF_XCONS_ALLOC",
-    "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch"
-  },
-  {,
     "EventCode": "0x35048",
     "EventName": "PM_IPTEG_FROM_DL2L3_SHR",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request"
@@ -1970,11 +1860,6 @@
     "BriefDescription": "Cycles thread running at priority level 2 or 3"
   },
   {,
-    "EventCode": "0x10134",
-    "EventName": "PM_MRK_ST_DONE_L2",
-    "BriefDescription": "marked store completed in L2 ( RC machine done)"
-  },
-  {,
     "EventCode": "0x368B2",
     "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH",
     "BriefDescription": "Initial scope=group (GS or NNS) but data from local node. Prediction too high"
@@ -2005,11 +1890,6 @@
     "BriefDescription": "L2 guess grp (GS or NNS) and guess was not correct (ie data on-chip OR beyond-group)"
   },
   {,
-    "EventCode": "0x368AE",
-    "EventName": "PM_L3_P1_CO_RTY",
-    "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted"
-  },
-  {,
     "EventCode": "0xC0AC",
     "EventName": "PM_LSU_FLUSH_EMSH",
     "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
@@ -2035,11 +1915,6 @@
     "BriefDescription": "RC requests that were on group (aka nodel) pump attempts"
   },
   {,
-    "EventCode": "0xF0B0",
-    "EventName": "PM_L3_LD_PREF",
-    "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest"
-  },
-  {,
     "EventCode": "0x16080",
     "EventName": "PM_L2_LD",
     "BriefDescription": "All successful D-side Load dispatches for this thread (L2 miss + L2 hits)"
@@ -2050,6 +1925,11 @@
     "BriefDescription": "Math flop instruction completed"
   },
   {,
+    "EventCode": "0xC080",
+    "EventName": "PM_LS0_LD_VECTOR_FIN",
+    "BriefDescription": ""
+  },
+  {,
     "EventCode": "0x368B0",
     "EventName": "PM_L3_P1_SYS_PUMP",
     "BriefDescription": "L3 PF sent with sys scope port 1, counts even retried requests"
@@ -2120,11 +2000,6 @@
     "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken.  Counted at completion time"
   },
   {,
-    "EventCode": "0xF0B8",
-    "EventName": "PM_LS0_UNALIGNED_ST",
-    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
-  },
-  {,
     "EventCode": "0x20132",
     "EventName": "PM_MRK_DFU_FIN",
     "BriefDescription": "Decimal Unit marked Instruction Finish"
@@ -2140,6 +2015,11 @@
     "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
   },
   {,
+    "EventCode": "0x16084",
+    "EventName": "PM_L2_RCLD_DISP",
+    "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+  },
+  {,
     "EventCode": "0x3F150",
     "EventName": "PM_MRK_ST_DRAIN_TO_L2DISP_CYC",
     "BriefDescription": "cycles to drain st from core to L2"
@@ -2225,11 +2105,6 @@
     "BriefDescription": "Prefetch Canceled due to page boundary"
   },
   {,
-    "EventCode": "0xF09C",
-    "EventName": "PM_SLB_TABLEWALK_CYC",
-    "BriefDescription": "Cycles when a tablewalk is pending on this thread on the SLB table"
-  },
-  {,
     "EventCode": "0x460AA",
     "EventName": "PM_L3_P0_CO_L31",
     "BriefDescription": "L3 CO to L3.1 (LCO) port 0 with or without data"
@@ -2247,10 +2122,10 @@
   {,
     "EventCode": "0x46082",
     "EventName": "PM_L2_ST_DISP",
-    "BriefDescription": "All successful D-side store dispatches for this thread "
+    "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)"
   },
   {,
-    "EventCode": "0x4609E",
+    "EventCode": "0x36880",
     "EventName": "PM_L2_INST_MISS",
     "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
   },
@@ -2340,9 +2215,9 @@
     "BriefDescription": "All ISU rejects"
   },
   {,
-    "EventCode": "0x46882",
-    "EventName": "PM_L2_ST_HIT",
-    "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits"
+    "EventCode": "0xC884",
+    "EventName": "PM_LS3_LD_VECTOR_FIN",
+    "BriefDescription": ""
   },
   {,
     "EventCode": "0x360A8",
@@ -2360,11 +2235,6 @@
     "BriefDescription": "Asserts when a i=1 store op is sent to the nest. No record of issue pipe (LS0/LS1) is maintained so this is for both pipes. Probably don't need separate LS0 and LS1"
   },
   {,
-    "EventCode": "0xD880",
-    "EventName": "PM_LSU1_SET_MPRED",
-    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
-  },
-  {,
     "EventCode": "0xD0B8",
     "EventName": "PM_LSU_LMQ_FULL_CYC",
     "BriefDescription": "Counts the number of cycles the LMQ is full"
@@ -2389,4 +2259,4 @@
     "EventName": "PM_L3_PF_USAGE",
     "BriefDescription": "Rotating sample of 32 PF actives"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
index bc2db636dabf..5af1abbe82c4 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
@@ -125,6 +125,11 @@
     "BriefDescription": "Overflow from counter 5"
   },
   {,
+    "EventCode": "0x4505E",
+    "EventName": "PM_FLOP_CMPL",
+    "BriefDescription": "Floating Point Operation Finished"
+  },
+  {,
     "EventCode": "0x2C018",
     "EventName": "PM_CMPLU_STALL_DMISS_L21_L31",
     "BriefDescription": "Completion stall by Dcache miss which resolved on chip ( excluding local L2/L3)"
@@ -390,11 +395,6 @@
     "BriefDescription": "Ict empty for this thread due to branch mispred"
   },
   {,
-    "EventCode": "0x3405E",
-    "EventName": "PM_IFETCH_THROTTLE",
-    "BriefDescription": "Cycles in which Instruction fetch throttle was active."
-  },
-  {,
     "EventCode": "0x1F148",
     "EventName": "PM_MRK_DPTEG_FROM_ON_CHIP_CACHE",
     "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
@@ -422,7 +422,7 @@
   {,
     "EventCode": "0xD0A8",
     "EventName": "PM_DSLB_MISS",
-    "BriefDescription": "Data SLB Miss - Total of all segment sizes"
+    "BriefDescription": "gate_and(sd_pc_c0_comp_valid AND sd_pc_c0_comp_thread(0:1)=tid,sd_pc_c0_comp_ppc_count(0:3)) + gate_and(sd_pc_c1_comp_valid AND sd_pc_c1_comp_thread(0:1)=tid,sd_pc_c1_comp_ppc_count(0:3))"
   },
   {,
     "EventCode": "0x4C058",
@@ -549,4 +549,4 @@
     "EventName": "PM_MRK_DATA_FROM_L21_SHR_CYC",
     "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L2 on the same chip due to a marked load"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
index 3ef8a10aac86..d0b89f930567 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
@@ -119,4 +119,4 @@
     "EventName": "PM_1FLOP_CMPL",
     "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed"
   }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
index 8c0f12024afa..bc8e03d7a6b0 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
@@ -90,11 +90,6 @@
     "BriefDescription": "stcx failed"
   },
   {,
-    "EventCode": "0x20112",
-    "EventName": "PM_MRK_NTF_FIN",
-    "BriefDescription": "Marked next to finish instruction finished"
-  },
-  {,
     "EventCode": "0x300F0",
     "EventName": "PM_ST_MISS_L1",
     "BriefDescription": "Store Missed L1"
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
new file mode 100644
index 000000000000..00bfdb5c5acb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
index 73688a9dab2a..bba3152ec54a 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
@@ -10,13 +10,30 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "UMask": "0x22",
+        "EventName": "L2_RQSTS.RFO_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "BriefDescription": "RFO requests that miss L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x24",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache misses when fetching instructions.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x27",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand requests that miss L2 cache.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -30,6 +47,43 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3f",
+        "EventName": "L2_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "All requests that miss L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x42",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x44",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of requests from the L2 hardware prefetchers that hit L2 cache. L3 prefetch new types.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -70,6 +124,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe7",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand requests to L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the total number of requests from the L2 hardware prefetchers.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -80,6 +143,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0xff",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "All L2 requests.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of WB requests that hit L2 cache.",
         "EventCode": "0x27",
         "Counter": "0,1,2,3",
@@ -131,6 +203,27 @@
         "CounterHTOff": "2"
     },
     {
+        "EventCode": "0x48",
+        "Counter": "2",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "CounterMask": "1",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
         "EventCode": "0x51",
         "Counter": "0,1,2,3",
@@ -152,7 +245,30 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "This event counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "Errata": "BDM76",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "Errata": "BDM76",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -174,26 +290,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
+        "UMask": "0x4",
         "Errata": "BDM76",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "PublicDescription": "This event counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "UMask": "0x8",
         "Errata": "BDM76",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
-        "CounterMask": "1",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -209,18 +325,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "Errata": "BDM76",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).",
         "EventCode": "0x63",
         "Counter": "0,1,2,3",
@@ -261,7 +365,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable \"Demands\" and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable Demands and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
         "EventCode": "0xB0",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
@@ -281,152 +385,161 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xB7, 0xBB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x11",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that miss the STLB.",
+        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x12",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that miss the STLB.",
+        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1",
         "L1_Hit_Indication": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts load uops with locked access retired to the architected path.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x21",
         "Errata": "BDM35",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops with locked access.",
+        "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x41",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x42",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1",
         "L1_Hit_Indication": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x81",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "All retired load uops. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x82",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1",
         "L1_Hit_Indication": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "Errata": "BDM35",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "Errata": "BDM100",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
+        "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops misses in L1 cache as data sources.",
+        "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -438,84 +551,83 @@
         "Errata": "BDM100, BDE70",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "Errata": "BDM100",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "Errata": "BDM100",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "Errata": "BDM100",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "Errata": "BDM100",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.",
+        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).",
+        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
         "EventCode": "0xD3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "Errata": "BDE70, BDM100",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -659,119 +771,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that hit L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x22",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that miss L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x44",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache misses when fetching instructions.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x27",
-        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand requests that miss L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe7",
-        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand requests to L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3f",
-        "EventName": "L2_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "All requests that miss L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xff",
-        "EventName": "L2_RQSTS.REFERENCES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "All L2 requests.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "BDM76",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "2",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
+        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010001 ",
         "Counter": "0,1,2,3",
@@ -784,6 +784,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020001 ",
         "Counter": "0,1,2,3",
@@ -796,6 +797,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020001 ",
         "Counter": "0,1,2,3",
@@ -808,6 +810,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020001 ",
         "Counter": "0,1,2,3",
@@ -820,6 +823,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020001 ",
         "Counter": "0,1,2,3",
@@ -832,6 +836,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020001 ",
         "Counter": "0,1,2,3",
@@ -844,6 +849,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020001 ",
         "Counter": "0,1,2,3",
@@ -856,6 +862,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0001 ",
         "Counter": "0,1,2,3",
@@ -868,6 +875,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0001 ",
         "Counter": "0,1,2,3",
@@ -880,6 +888,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0001 ",
         "Counter": "0,1,2,3",
@@ -892,6 +901,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0001 ",
         "Counter": "0,1,2,3",
@@ -904,6 +914,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0001 ",
         "Counter": "0,1,2,3",
@@ -916,6 +927,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0001 ",
         "Counter": "0,1,2,3",
@@ -928,6 +940,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010002 ",
         "Counter": "0,1,2,3",
@@ -940,6 +953,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0002 ",
         "Counter": "0,1,2,3",
@@ -952,6 +966,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0002 ",
         "Counter": "0,1,2,3",
@@ -964,6 +979,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0002 ",
         "Counter": "0,1,2,3",
@@ -976,6 +992,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0002 ",
         "Counter": "0,1,2,3",
@@ -988,6 +1005,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0002 ",
         "Counter": "0,1,2,3",
@@ -1000,6 +1018,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0002 ",
         "Counter": "0,1,2,3",
@@ -1012,6 +1031,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010004 ",
         "Counter": "0,1,2,3",
@@ -1024,6 +1044,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020004 ",
         "Counter": "0,1,2,3",
@@ -1036,6 +1057,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020004 ",
         "Counter": "0,1,2,3",
@@ -1048,6 +1070,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020004 ",
         "Counter": "0,1,2,3",
@@ -1060,6 +1083,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020004 ",
         "Counter": "0,1,2,3",
@@ -1072,6 +1096,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020004 ",
         "Counter": "0,1,2,3",
@@ -1084,6 +1109,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020004 ",
         "Counter": "0,1,2,3",
@@ -1096,6 +1122,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0004 ",
         "Counter": "0,1,2,3",
@@ -1108,6 +1135,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0004 ",
         "Counter": "0,1,2,3",
@@ -1120,6 +1148,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0004 ",
         "Counter": "0,1,2,3",
@@ -1132,6 +1161,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0004 ",
         "Counter": "0,1,2,3",
@@ -1144,6 +1174,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0004 ",
         "Counter": "0,1,2,3",
@@ -1156,6 +1187,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0004 ",
         "Counter": "0,1,2,3",
@@ -1168,6 +1200,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010008 ",
         "Counter": "0,1,2,3",
@@ -1180,6 +1213,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020008 ",
         "Counter": "0,1,2,3",
@@ -1192,6 +1226,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020008 ",
         "Counter": "0,1,2,3",
@@ -1204,6 +1239,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020008 ",
         "Counter": "0,1,2,3",
@@ -1216,6 +1252,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020008 ",
         "Counter": "0,1,2,3",
@@ -1228,6 +1265,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020008 ",
         "Counter": "0,1,2,3",
@@ -1240,6 +1278,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020008 ",
         "Counter": "0,1,2,3",
@@ -1252,6 +1291,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0008 ",
         "Counter": "0,1,2,3",
@@ -1264,6 +1304,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0008 ",
         "Counter": "0,1,2,3",
@@ -1276,6 +1317,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0008 ",
         "Counter": "0,1,2,3",
@@ -1288,6 +1330,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0008 ",
         "Counter": "0,1,2,3",
@@ -1300,6 +1343,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0008 ",
         "Counter": "0,1,2,3",
@@ -1312,6 +1356,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0008 ",
         "Counter": "0,1,2,3",
@@ -1324,6 +1369,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010010 ",
         "Counter": "0,1,2,3",
@@ -1336,6 +1382,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020010 ",
         "Counter": "0,1,2,3",
@@ -1348,6 +1395,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020010 ",
         "Counter": "0,1,2,3",
@@ -1360,6 +1408,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020010 ",
         "Counter": "0,1,2,3",
@@ -1372,6 +1421,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020010 ",
         "Counter": "0,1,2,3",
@@ -1384,6 +1434,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020010 ",
         "Counter": "0,1,2,3",
@@ -1396,6 +1447,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020010 ",
         "Counter": "0,1,2,3",
@@ -1408,6 +1460,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0010 ",
         "Counter": "0,1,2,3",
@@ -1420,6 +1473,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0010 ",
         "Counter": "0,1,2,3",
@@ -1432,6 +1486,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0010 ",
         "Counter": "0,1,2,3",
@@ -1444,6 +1499,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0010 ",
         "Counter": "0,1,2,3",
@@ -1456,6 +1512,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0010 ",
         "Counter": "0,1,2,3",
@@ -1468,6 +1525,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0010 ",
         "Counter": "0,1,2,3",
@@ -1480,6 +1538,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010020 ",
         "Counter": "0,1,2,3",
@@ -1492,6 +1551,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020020 ",
         "Counter": "0,1,2,3",
@@ -1504,6 +1564,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020020 ",
         "Counter": "0,1,2,3",
@@ -1516,6 +1577,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020020 ",
         "Counter": "0,1,2,3",
@@ -1528,6 +1590,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020020 ",
         "Counter": "0,1,2,3",
@@ -1540,6 +1603,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020020 ",
         "Counter": "0,1,2,3",
@@ -1552,6 +1616,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020020 ",
         "Counter": "0,1,2,3",
@@ -1564,6 +1629,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0020 ",
         "Counter": "0,1,2,3",
@@ -1576,6 +1642,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0020 ",
         "Counter": "0,1,2,3",
@@ -1588,6 +1655,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0020 ",
         "Counter": "0,1,2,3",
@@ -1600,6 +1668,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0020 ",
         "Counter": "0,1,2,3",
@@ -1612,6 +1681,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0020 ",
         "Counter": "0,1,2,3",
@@ -1624,6 +1694,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0020 ",
         "Counter": "0,1,2,3",
@@ -1636,6 +1707,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010040 ",
         "Counter": "0,1,2,3",
@@ -1648,6 +1720,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020040 ",
         "Counter": "0,1,2,3",
@@ -1660,6 +1733,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020040 ",
         "Counter": "0,1,2,3",
@@ -1672,6 +1746,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020040 ",
         "Counter": "0,1,2,3",
@@ -1684,6 +1759,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020040 ",
         "Counter": "0,1,2,3",
@@ -1696,6 +1772,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020040 ",
         "Counter": "0,1,2,3",
@@ -1708,6 +1785,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020040 ",
         "Counter": "0,1,2,3",
@@ -1720,6 +1798,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0040 ",
         "Counter": "0,1,2,3",
@@ -1732,6 +1811,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0040 ",
         "Counter": "0,1,2,3",
@@ -1744,6 +1824,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0040 ",
         "Counter": "0,1,2,3",
@@ -1756,6 +1837,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0040 ",
         "Counter": "0,1,2,3",
@@ -1768,6 +1850,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0040 ",
         "Counter": "0,1,2,3",
@@ -1780,6 +1863,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0040 ",
         "Counter": "0,1,2,3",
@@ -1792,6 +1876,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010080 ",
         "Counter": "0,1,2,3",
@@ -1804,6 +1889,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020080 ",
         "Counter": "0,1,2,3",
@@ -1816,6 +1902,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020080 ",
         "Counter": "0,1,2,3",
@@ -1828,6 +1915,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020080 ",
         "Counter": "0,1,2,3",
@@ -1840,6 +1928,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020080 ",
         "Counter": "0,1,2,3",
@@ -1852,6 +1941,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020080 ",
         "Counter": "0,1,2,3",
@@ -1864,6 +1954,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020080 ",
         "Counter": "0,1,2,3",
@@ -1876,6 +1967,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0080 ",
         "Counter": "0,1,2,3",
@@ -1888,6 +1980,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0080 ",
         "Counter": "0,1,2,3",
@@ -1900,6 +1993,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0080 ",
         "Counter": "0,1,2,3",
@@ -1912,6 +2006,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0080 ",
         "Counter": "0,1,2,3",
@@ -1924,6 +2019,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0080 ",
         "Counter": "0,1,2,3",
@@ -1936,6 +2032,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0080 ",
         "Counter": "0,1,2,3",
@@ -1948,6 +2045,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010100 ",
         "Counter": "0,1,2,3",
@@ -1960,6 +2058,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020100 ",
         "Counter": "0,1,2,3",
@@ -1972,6 +2071,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020100 ",
         "Counter": "0,1,2,3",
@@ -1984,6 +2084,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020100 ",
         "Counter": "0,1,2,3",
@@ -1996,6 +2097,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020100 ",
         "Counter": "0,1,2,3",
@@ -2008,6 +2110,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020100 ",
         "Counter": "0,1,2,3",
@@ -2020,6 +2123,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020100 ",
         "Counter": "0,1,2,3",
@@ -2032,6 +2136,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0100 ",
         "Counter": "0,1,2,3",
@@ -2044,6 +2149,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0100 ",
         "Counter": "0,1,2,3",
@@ -2056,6 +2162,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0100 ",
         "Counter": "0,1,2,3",
@@ -2068,6 +2175,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0100 ",
         "Counter": "0,1,2,3",
@@ -2080,6 +2188,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0100 ",
         "Counter": "0,1,2,3",
@@ -2092,6 +2201,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0100 ",
         "Counter": "0,1,2,3",
@@ -2104,6 +2214,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010200 ",
         "Counter": "0,1,2,3",
@@ -2116,6 +2227,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020200 ",
         "Counter": "0,1,2,3",
@@ -2128,6 +2240,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020200 ",
         "Counter": "0,1,2,3",
@@ -2140,6 +2253,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020200 ",
         "Counter": "0,1,2,3",
@@ -2152,6 +2266,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020200 ",
         "Counter": "0,1,2,3",
@@ -2164,6 +2279,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020200 ",
         "Counter": "0,1,2,3",
@@ -2176,6 +2292,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020200 ",
         "Counter": "0,1,2,3",
@@ -2188,6 +2305,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0200 ",
         "Counter": "0,1,2,3",
@@ -2200,6 +2318,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0200 ",
         "Counter": "0,1,2,3",
@@ -2212,6 +2331,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0200 ",
         "Counter": "0,1,2,3",
@@ -2224,6 +2344,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0200 ",
         "Counter": "0,1,2,3",
@@ -2236,6 +2357,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0200 ",
         "Counter": "0,1,2,3",
@@ -2248,6 +2370,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0200 ",
         "Counter": "0,1,2,3",
@@ -2260,6 +2383,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000018000 ",
         "Counter": "0,1,2,3",
@@ -2272,6 +2396,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080028000 ",
         "Counter": "0,1,2,3",
@@ -2284,6 +2409,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100028000 ",
         "Counter": "0,1,2,3",
@@ -2296,6 +2422,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200028000 ",
         "Counter": "0,1,2,3",
@@ -2308,6 +2435,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400028000 ",
         "Counter": "0,1,2,3",
@@ -2320,6 +2448,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000028000 ",
         "Counter": "0,1,2,3",
@@ -2332,6 +2461,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80028000 ",
         "Counter": "0,1,2,3",
@@ -2344,6 +2474,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c8000 ",
         "Counter": "0,1,2,3",
@@ -2356,6 +2487,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c8000 ",
         "Counter": "0,1,2,3",
@@ -2368,6 +2500,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c8000 ",
         "Counter": "0,1,2,3",
@@ -2380,6 +2513,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c8000 ",
         "Counter": "0,1,2,3",
@@ -2392,6 +2526,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c8000 ",
         "Counter": "0,1,2,3",
@@ -2404,6 +2539,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c8000 ",
         "Counter": "0,1,2,3",
@@ -2416,6 +2552,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010090 ",
         "Counter": "0,1,2,3",
@@ -2428,6 +2565,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020090 ",
         "Counter": "0,1,2,3",
@@ -2440,6 +2578,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020090 ",
         "Counter": "0,1,2,3",
@@ -2452,6 +2591,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020090 ",
         "Counter": "0,1,2,3",
@@ -2464,6 +2604,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020090 ",
         "Counter": "0,1,2,3",
@@ -2476,6 +2617,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020090 ",
         "Counter": "0,1,2,3",
@@ -2488,6 +2630,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020090 ",
         "Counter": "0,1,2,3",
@@ -2500,6 +2643,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0090 ",
         "Counter": "0,1,2,3",
@@ -2512,6 +2656,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0090 ",
         "Counter": "0,1,2,3",
@@ -2524,6 +2669,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0090 ",
         "Counter": "0,1,2,3",
@@ -2536,6 +2682,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0090 ",
         "Counter": "0,1,2,3",
@@ -2548,6 +2695,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0090 ",
         "Counter": "0,1,2,3",
@@ -2560,6 +2708,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0090 ",
         "Counter": "0,1,2,3",
@@ -2572,6 +2721,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010120 ",
         "Counter": "0,1,2,3",
@@ -2584,6 +2734,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020120 ",
         "Counter": "0,1,2,3",
@@ -2596,6 +2747,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020120 ",
         "Counter": "0,1,2,3",
@@ -2608,6 +2760,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020120 ",
         "Counter": "0,1,2,3",
@@ -2620,6 +2773,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020120 ",
         "Counter": "0,1,2,3",
@@ -2632,6 +2786,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020120 ",
         "Counter": "0,1,2,3",
@@ -2644,6 +2799,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020120 ",
         "Counter": "0,1,2,3",
@@ -2656,6 +2812,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0120 ",
         "Counter": "0,1,2,3",
@@ -2668,6 +2825,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0120 ",
         "Counter": "0,1,2,3",
@@ -2680,6 +2838,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0120 ",
         "Counter": "0,1,2,3",
@@ -2692,6 +2851,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0120 ",
         "Counter": "0,1,2,3",
@@ -2704,6 +2864,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0120 ",
         "Counter": "0,1,2,3",
@@ -2716,6 +2877,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0120 ",
         "Counter": "0,1,2,3",
@@ -2728,6 +2890,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010240 ",
         "Counter": "0,1,2,3",
@@ -2740,6 +2903,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020240 ",
         "Counter": "0,1,2,3",
@@ -2752,6 +2916,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020240 ",
         "Counter": "0,1,2,3",
@@ -2764,6 +2929,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020240 ",
         "Counter": "0,1,2,3",
@@ -2776,6 +2942,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020240 ",
         "Counter": "0,1,2,3",
@@ -2788,6 +2955,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020240 ",
         "Counter": "0,1,2,3",
@@ -2800,6 +2968,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020240 ",
         "Counter": "0,1,2,3",
@@ -2812,6 +2981,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0240 ",
         "Counter": "0,1,2,3",
@@ -2824,6 +2994,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0240 ",
         "Counter": "0,1,2,3",
@@ -2836,6 +3007,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0240 ",
         "Counter": "0,1,2,3",
@@ -2848,6 +3020,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0240 ",
         "Counter": "0,1,2,3",
@@ -2860,6 +3033,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0240 ",
         "Counter": "0,1,2,3",
@@ -2872,6 +3046,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0240 ",
         "Counter": "0,1,2,3",
@@ -2884,6 +3059,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010091 ",
         "Counter": "0,1,2,3",
@@ -2896,6 +3072,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020091 ",
         "Counter": "0,1,2,3",
@@ -2908,6 +3085,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020091 ",
         "Counter": "0,1,2,3",
@@ -2920,6 +3098,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020091 ",
         "Counter": "0,1,2,3",
@@ -2932,6 +3111,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020091 ",
         "Counter": "0,1,2,3",
@@ -2944,6 +3124,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020091 ",
         "Counter": "0,1,2,3",
@@ -2956,6 +3137,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020091 ",
         "Counter": "0,1,2,3",
@@ -2968,6 +3150,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0091 ",
         "Counter": "0,1,2,3",
@@ -2980,6 +3163,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0091 ",
         "Counter": "0,1,2,3",
@@ -2992,6 +3176,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0091 ",
         "Counter": "0,1,2,3",
@@ -3004,6 +3189,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0091 ",
         "Counter": "0,1,2,3",
@@ -3016,6 +3202,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0091 ",
         "Counter": "0,1,2,3",
@@ -3028,6 +3215,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0091 ",
         "Counter": "0,1,2,3",
@@ -3040,6 +3228,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010122 ",
         "Counter": "0,1,2,3",
@@ -3052,6 +3241,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020122 ",
         "Counter": "0,1,2,3",
@@ -3064,6 +3254,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020122 ",
         "Counter": "0,1,2,3",
@@ -3076,6 +3267,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020122 ",
         "Counter": "0,1,2,3",
@@ -3088,6 +3280,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020122 ",
         "Counter": "0,1,2,3",
@@ -3100,6 +3293,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020122 ",
         "Counter": "0,1,2,3",
@@ -3112,6 +3306,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f80020122 ",
         "Counter": "0,1,2,3",
@@ -3124,6 +3319,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00803c0122 ",
         "Counter": "0,1,2,3",
@@ -3136,6 +3332,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01003c0122 ",
         "Counter": "0,1,2,3",
@@ -3148,6 +3345,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02003c0122 ",
         "Counter": "0,1,2,3",
@@ -3160,6 +3358,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0122 ",
         "Counter": "0,1,2,3",
@@ -3172,6 +3371,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0122 ",
         "Counter": "0,1,2,3",
@@ -3184,6 +3384,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0122 ",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
index 102bfb808199..689d478dae93 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
@@ -1,6 +1,6 @@
 [
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
+        "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
@@ -11,7 +11,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
+        "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -22,7 +22,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
         "EventCode": "0xC7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -32,7 +31,6 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PEBS": "1",
         "EventCode": "0xC7",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -42,7 +40,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PEBS": "1",
+        "EventCode": "0xC7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xC7",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
@@ -52,7 +58,6 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PEBS": "1",
         "EventCode": "0xC7",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
@@ -62,7 +67,6 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PEBS": "1",
         "EventCode": "0xC7",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -72,7 +76,43 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
+        "EventCode": "0xC7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x15",
+        "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
+        "SampleAfterValue": "2000006",
+        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xc7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2a",
+        "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
+        "SampleAfterValue": "2000005",
+        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3c",
+        "EventName": "FP_ARITH_INST_RETIRED.PACKED",
+        "SampleAfterValue": "2000004",
+        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -82,7 +122,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
+        "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
@@ -92,7 +132,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
+        "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
@@ -102,7 +142,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
+        "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -121,51 +161,5 @@
         "BriefDescription": "Cycles with any input/output SSE or FP assist",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xc7",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3c",
-        "EventName": "FP_ARITH_INST_RETIRED.PACKED",
-        "SampleAfterValue": "2000004",
-        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2a",
-        "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
-        "SampleAfterValue": "2000005",
-        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "Counter": "0,1,2,3",
-        "UMask": "0x15",
-        "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
-        "SampleAfterValue": "2000006",
-        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
-        "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
index b0cdf1f097a0..7142c76d7f11 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
@@ -10,7 +10,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
@@ -20,80 +20,49 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "IDQ.MS_MITE_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
+        "UMask": "0x4",
+        "EventName": "IDQ.MITE_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterMask": "1",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_CYCLES",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
-        "CounterMask": "1",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -104,7 +73,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -116,7 +85,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x18",
@@ -127,7 +96,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of cycles  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x18",
@@ -138,7 +107,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x24",
@@ -149,7 +128,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles  uops were delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of cycles  uops were delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x24",
@@ -160,7 +139,39 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_SWITCHES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x3c",
@@ -200,7 +211,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding ?4 ? x? when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -263,7 +274,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0?2 cycles.",
+        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
         "EventCode": "0xAB",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -271,16 +282,5 @@
         "SampleAfterValue": "2000003",
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
index ff5416d29d0d..c9154cebbdf0 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
@@ -90,7 +90,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Unfriendly TSX abort triggered by  a flowmarker.",
         "EventCode": "0x5d",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -170,13 +169,13 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of times HLE abort was triggered.",
+        "PublicDescription": "Number of times HLE abort was triggered (PEBS).",
         "EventCode": "0xc8",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "HLE_RETIRED.ABORTED",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times HLE abort was triggered",
+        "BriefDescription": "Number of times HLE abort was triggered (PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -251,13 +250,13 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of times RTM abort was triggered .",
+        "PublicDescription": "Number of times RTM abort was triggered (PEBS).",
         "EventCode": "0xc9",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "RTM_RETIRED.ABORTED",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times RTM abort was triggered",
+        "BriefDescription": "Number of times RTM abort was triggered (PEBS)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -431,6 +430,7 @@
         "CounterHTOff": "3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020001 ",
         "Counter": "0,1,2,3",
@@ -443,6 +443,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0001 ",
         "Counter": "0,1,2,3",
@@ -455,6 +456,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000001 ",
         "Counter": "0,1,2,3",
@@ -467,6 +469,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000001 ",
         "Counter": "0,1,2,3",
@@ -479,6 +482,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000001 ",
         "Counter": "0,1,2,3",
@@ -491,6 +495,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000001 ",
         "Counter": "0,1,2,3",
@@ -503,6 +508,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000001 ",
         "Counter": "0,1,2,3",
@@ -515,6 +521,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000001 ",
         "Counter": "0,1,2,3",
@@ -527,6 +534,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000001 ",
         "Counter": "0,1,2,3",
@@ -539,6 +547,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000001 ",
         "Counter": "0,1,2,3",
@@ -551,6 +560,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000001 ",
         "Counter": "0,1,2,3",
@@ -563,6 +573,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000001 ",
         "Counter": "0,1,2,3",
@@ -575,6 +586,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000001 ",
         "Counter": "0,1,2,3",
@@ -587,6 +599,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0002 ",
         "Counter": "0,1,2,3",
@@ -599,6 +612,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000002 ",
         "Counter": "0,1,2,3",
@@ -611,6 +625,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000002 ",
         "Counter": "0,1,2,3",
@@ -623,6 +638,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000002 ",
         "Counter": "0,1,2,3",
@@ -635,6 +651,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000002 ",
         "Counter": "0,1,2,3",
@@ -647,6 +664,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000002 ",
         "Counter": "0,1,2,3",
@@ -659,6 +677,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020004 ",
         "Counter": "0,1,2,3",
@@ -671,6 +690,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0004 ",
         "Counter": "0,1,2,3",
@@ -683,6 +703,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000004 ",
         "Counter": "0,1,2,3",
@@ -695,6 +716,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000004 ",
         "Counter": "0,1,2,3",
@@ -707,6 +729,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000004 ",
         "Counter": "0,1,2,3",
@@ -719,6 +742,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000004 ",
         "Counter": "0,1,2,3",
@@ -731,6 +755,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000004 ",
         "Counter": "0,1,2,3",
@@ -743,6 +768,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000004 ",
         "Counter": "0,1,2,3",
@@ -755,6 +781,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000004 ",
         "Counter": "0,1,2,3",
@@ -767,6 +794,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000004 ",
         "Counter": "0,1,2,3",
@@ -779,6 +807,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000004 ",
         "Counter": "0,1,2,3",
@@ -791,6 +820,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000004 ",
         "Counter": "0,1,2,3",
@@ -803,6 +833,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000004 ",
         "Counter": "0,1,2,3",
@@ -815,6 +846,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020008 ",
         "Counter": "0,1,2,3",
@@ -827,6 +859,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0008 ",
         "Counter": "0,1,2,3",
@@ -839,6 +872,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000008 ",
         "Counter": "0,1,2,3",
@@ -851,6 +885,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000008 ",
         "Counter": "0,1,2,3",
@@ -863,6 +898,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000008 ",
         "Counter": "0,1,2,3",
@@ -875,6 +911,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000008 ",
         "Counter": "0,1,2,3",
@@ -887,6 +924,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000008 ",
         "Counter": "0,1,2,3",
@@ -899,6 +937,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000008 ",
         "Counter": "0,1,2,3",
@@ -911,6 +950,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000008 ",
         "Counter": "0,1,2,3",
@@ -923,6 +963,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000008 ",
         "Counter": "0,1,2,3",
@@ -935,6 +976,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000008 ",
         "Counter": "0,1,2,3",
@@ -947,6 +989,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000008 ",
         "Counter": "0,1,2,3",
@@ -959,6 +1002,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000008 ",
         "Counter": "0,1,2,3",
@@ -971,6 +1015,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020010 ",
         "Counter": "0,1,2,3",
@@ -983,6 +1028,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0010 ",
         "Counter": "0,1,2,3",
@@ -995,6 +1041,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000010 ",
         "Counter": "0,1,2,3",
@@ -1007,6 +1054,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000010 ",
         "Counter": "0,1,2,3",
@@ -1019,6 +1067,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000010 ",
         "Counter": "0,1,2,3",
@@ -1031,6 +1080,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000010 ",
         "Counter": "0,1,2,3",
@@ -1043,6 +1093,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000010 ",
         "Counter": "0,1,2,3",
@@ -1055,6 +1106,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000010 ",
         "Counter": "0,1,2,3",
@@ -1067,6 +1119,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000010 ",
         "Counter": "0,1,2,3",
@@ -1079,6 +1132,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000010 ",
         "Counter": "0,1,2,3",
@@ -1091,6 +1145,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000010 ",
         "Counter": "0,1,2,3",
@@ -1103,6 +1158,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000010 ",
         "Counter": "0,1,2,3",
@@ -1115,6 +1171,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000010 ",
         "Counter": "0,1,2,3",
@@ -1127,6 +1184,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020020 ",
         "Counter": "0,1,2,3",
@@ -1139,6 +1197,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0020 ",
         "Counter": "0,1,2,3",
@@ -1151,6 +1210,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000020 ",
         "Counter": "0,1,2,3",
@@ -1163,6 +1223,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000020 ",
         "Counter": "0,1,2,3",
@@ -1175,6 +1236,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000020 ",
         "Counter": "0,1,2,3",
@@ -1187,6 +1249,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000020 ",
         "Counter": "0,1,2,3",
@@ -1199,6 +1262,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000020 ",
         "Counter": "0,1,2,3",
@@ -1211,6 +1275,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000020 ",
         "Counter": "0,1,2,3",
@@ -1223,6 +1288,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000020 ",
         "Counter": "0,1,2,3",
@@ -1235,6 +1301,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000020 ",
         "Counter": "0,1,2,3",
@@ -1247,6 +1314,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000020 ",
         "Counter": "0,1,2,3",
@@ -1259,6 +1327,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000020 ",
         "Counter": "0,1,2,3",
@@ -1271,6 +1340,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000020 ",
         "Counter": "0,1,2,3",
@@ -1283,6 +1353,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020040 ",
         "Counter": "0,1,2,3",
@@ -1295,6 +1366,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0040 ",
         "Counter": "0,1,2,3",
@@ -1307,6 +1379,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000040 ",
         "Counter": "0,1,2,3",
@@ -1319,6 +1392,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000040 ",
         "Counter": "0,1,2,3",
@@ -1331,6 +1405,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000040 ",
         "Counter": "0,1,2,3",
@@ -1343,6 +1418,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000040 ",
         "Counter": "0,1,2,3",
@@ -1355,6 +1431,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000040 ",
         "Counter": "0,1,2,3",
@@ -1367,6 +1444,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000040 ",
         "Counter": "0,1,2,3",
@@ -1379,6 +1457,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000040 ",
         "Counter": "0,1,2,3",
@@ -1391,6 +1470,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000040 ",
         "Counter": "0,1,2,3",
@@ -1403,6 +1483,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000040 ",
         "Counter": "0,1,2,3",
@@ -1415,6 +1496,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000040 ",
         "Counter": "0,1,2,3",
@@ -1427,6 +1509,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000040 ",
         "Counter": "0,1,2,3",
@@ -1439,6 +1522,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020080 ",
         "Counter": "0,1,2,3",
@@ -1451,6 +1535,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0080 ",
         "Counter": "0,1,2,3",
@@ -1463,6 +1548,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000080 ",
         "Counter": "0,1,2,3",
@@ -1475,6 +1561,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000080 ",
         "Counter": "0,1,2,3",
@@ -1487,6 +1574,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000080 ",
         "Counter": "0,1,2,3",
@@ -1499,6 +1587,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000080 ",
         "Counter": "0,1,2,3",
@@ -1511,6 +1600,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000080 ",
         "Counter": "0,1,2,3",
@@ -1523,6 +1613,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000080 ",
         "Counter": "0,1,2,3",
@@ -1535,6 +1626,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000080 ",
         "Counter": "0,1,2,3",
@@ -1547,6 +1639,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000080 ",
         "Counter": "0,1,2,3",
@@ -1559,6 +1652,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000080 ",
         "Counter": "0,1,2,3",
@@ -1571,6 +1665,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000080 ",
         "Counter": "0,1,2,3",
@@ -1583,6 +1678,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000080 ",
         "Counter": "0,1,2,3",
@@ -1595,6 +1691,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020100 ",
         "Counter": "0,1,2,3",
@@ -1607,6 +1704,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0100 ",
         "Counter": "0,1,2,3",
@@ -1619,6 +1717,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000100 ",
         "Counter": "0,1,2,3",
@@ -1631,6 +1730,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000100 ",
         "Counter": "0,1,2,3",
@@ -1643,6 +1743,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000100 ",
         "Counter": "0,1,2,3",
@@ -1655,6 +1756,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000100 ",
         "Counter": "0,1,2,3",
@@ -1667,6 +1769,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000100 ",
         "Counter": "0,1,2,3",
@@ -1679,6 +1782,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000100 ",
         "Counter": "0,1,2,3",
@@ -1691,6 +1795,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000100 ",
         "Counter": "0,1,2,3",
@@ -1703,6 +1808,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000100 ",
         "Counter": "0,1,2,3",
@@ -1715,6 +1821,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000100 ",
         "Counter": "0,1,2,3",
@@ -1727,6 +1834,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000100 ",
         "Counter": "0,1,2,3",
@@ -1739,6 +1847,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000100 ",
         "Counter": "0,1,2,3",
@@ -1751,6 +1860,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020200 ",
         "Counter": "0,1,2,3",
@@ -1763,6 +1873,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0200 ",
         "Counter": "0,1,2,3",
@@ -1775,6 +1886,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000200 ",
         "Counter": "0,1,2,3",
@@ -1787,6 +1899,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000200 ",
         "Counter": "0,1,2,3",
@@ -1799,6 +1912,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000200 ",
         "Counter": "0,1,2,3",
@@ -1811,6 +1925,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000200 ",
         "Counter": "0,1,2,3",
@@ -1823,6 +1938,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000200 ",
         "Counter": "0,1,2,3",
@@ -1835,6 +1951,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000200 ",
         "Counter": "0,1,2,3",
@@ -1847,6 +1964,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000200 ",
         "Counter": "0,1,2,3",
@@ -1859,6 +1977,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000200 ",
         "Counter": "0,1,2,3",
@@ -1871,6 +1990,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000200 ",
         "Counter": "0,1,2,3",
@@ -1883,6 +2003,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000200 ",
         "Counter": "0,1,2,3",
@@ -1895,6 +2016,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000200 ",
         "Counter": "0,1,2,3",
@@ -1907,6 +2029,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000028000 ",
         "Counter": "0,1,2,3",
@@ -1919,6 +2042,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c8000 ",
         "Counter": "0,1,2,3",
@@ -1931,6 +2055,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084008000 ",
         "Counter": "0,1,2,3",
@@ -1943,6 +2068,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104008000 ",
         "Counter": "0,1,2,3",
@@ -1955,6 +2081,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204008000 ",
         "Counter": "0,1,2,3",
@@ -1967,6 +2094,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404008000 ",
         "Counter": "0,1,2,3",
@@ -1979,6 +2107,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004008000 ",
         "Counter": "0,1,2,3",
@@ -1991,6 +2120,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004008000 ",
         "Counter": "0,1,2,3",
@@ -2003,6 +2133,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84008000 ",
         "Counter": "0,1,2,3",
@@ -2015,6 +2146,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc008000 ",
         "Counter": "0,1,2,3",
@@ -2027,6 +2159,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c008000 ",
         "Counter": "0,1,2,3",
@@ -2039,6 +2172,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts any other requests that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c008000 ",
         "Counter": "0,1,2,3",
@@ -2051,6 +2185,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c008000 ",
         "Counter": "0,1,2,3",
@@ -2063,6 +2198,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020090 ",
         "Counter": "0,1,2,3",
@@ -2075,6 +2211,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0090 ",
         "Counter": "0,1,2,3",
@@ -2087,6 +2224,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000090 ",
         "Counter": "0,1,2,3",
@@ -2099,6 +2237,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000090 ",
         "Counter": "0,1,2,3",
@@ -2111,6 +2250,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000090 ",
         "Counter": "0,1,2,3",
@@ -2123,6 +2263,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000090 ",
         "Counter": "0,1,2,3",
@@ -2135,6 +2276,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000090 ",
         "Counter": "0,1,2,3",
@@ -2147,6 +2289,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000090 ",
         "Counter": "0,1,2,3",
@@ -2159,6 +2302,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000090 ",
         "Counter": "0,1,2,3",
@@ -2171,6 +2315,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000090 ",
         "Counter": "0,1,2,3",
@@ -2183,6 +2328,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000090 ",
         "Counter": "0,1,2,3",
@@ -2195,6 +2341,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000090 ",
         "Counter": "0,1,2,3",
@@ -2207,6 +2354,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000090 ",
         "Counter": "0,1,2,3",
@@ -2219,6 +2367,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020120 ",
         "Counter": "0,1,2,3",
@@ -2231,6 +2380,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0120 ",
         "Counter": "0,1,2,3",
@@ -2243,6 +2393,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000120 ",
         "Counter": "0,1,2,3",
@@ -2255,6 +2406,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000120 ",
         "Counter": "0,1,2,3",
@@ -2267,6 +2419,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000120 ",
         "Counter": "0,1,2,3",
@@ -2279,6 +2432,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000120 ",
         "Counter": "0,1,2,3",
@@ -2291,6 +2445,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000120 ",
         "Counter": "0,1,2,3",
@@ -2303,6 +2458,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000120 ",
         "Counter": "0,1,2,3",
@@ -2315,6 +2471,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000120 ",
         "Counter": "0,1,2,3",
@@ -2327,6 +2484,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000120 ",
         "Counter": "0,1,2,3",
@@ -2339,6 +2497,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000120 ",
         "Counter": "0,1,2,3",
@@ -2351,6 +2510,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000120 ",
         "Counter": "0,1,2,3",
@@ -2363,6 +2523,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000120 ",
         "Counter": "0,1,2,3",
@@ -2375,6 +2536,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020240 ",
         "Counter": "0,1,2,3",
@@ -2387,6 +2549,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0240 ",
         "Counter": "0,1,2,3",
@@ -2399,6 +2562,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000240 ",
         "Counter": "0,1,2,3",
@@ -2411,6 +2575,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000240 ",
         "Counter": "0,1,2,3",
@@ -2423,6 +2588,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000240 ",
         "Counter": "0,1,2,3",
@@ -2435,6 +2601,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000240 ",
         "Counter": "0,1,2,3",
@@ -2447,6 +2614,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000240 ",
         "Counter": "0,1,2,3",
@@ -2459,6 +2627,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000240 ",
         "Counter": "0,1,2,3",
@@ -2471,6 +2640,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000240 ",
         "Counter": "0,1,2,3",
@@ -2483,6 +2653,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000240 ",
         "Counter": "0,1,2,3",
@@ -2495,6 +2666,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000240 ",
         "Counter": "0,1,2,3",
@@ -2507,6 +2679,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000240 ",
         "Counter": "0,1,2,3",
@@ -2519,6 +2692,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000240 ",
         "Counter": "0,1,2,3",
@@ -2531,6 +2705,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020091 ",
         "Counter": "0,1,2,3",
@@ -2543,6 +2718,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0091 ",
         "Counter": "0,1,2,3",
@@ -2555,6 +2731,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000091 ",
         "Counter": "0,1,2,3",
@@ -2567,6 +2744,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000091 ",
         "Counter": "0,1,2,3",
@@ -2579,6 +2757,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000091 ",
         "Counter": "0,1,2,3",
@@ -2591,6 +2770,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000091 ",
         "Counter": "0,1,2,3",
@@ -2603,6 +2783,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000091 ",
         "Counter": "0,1,2,3",
@@ -2615,6 +2796,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000091 ",
         "Counter": "0,1,2,3",
@@ -2627,6 +2809,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000091 ",
         "Counter": "0,1,2,3",
@@ -2639,6 +2822,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000091 ",
         "Counter": "0,1,2,3",
@@ -2651,6 +2835,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000091 ",
         "Counter": "0,1,2,3",
@@ -2663,6 +2848,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000091 ",
         "Counter": "0,1,2,3",
@@ -2675,6 +2861,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000091 ",
         "Counter": "0,1,2,3",
@@ -2687,6 +2874,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2000020122 ",
         "Counter": "0,1,2,3",
@@ -2699,6 +2887,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x20003c0122 ",
         "Counter": "0,1,2,3",
@@ -2711,6 +2900,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000122 ",
         "Counter": "0,1,2,3",
@@ -2723,6 +2913,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000122 ",
         "Counter": "0,1,2,3",
@@ -2735,6 +2926,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000122 ",
         "Counter": "0,1,2,3",
@@ -2747,6 +2939,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000122 ",
         "Counter": "0,1,2,3",
@@ -2759,6 +2952,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000122 ",
         "Counter": "0,1,2,3",
@@ -2771,6 +2965,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x2004000122 ",
         "Counter": "0,1,2,3",
@@ -2783,6 +2978,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f84000122 ",
         "Counter": "0,1,2,3",
@@ -2795,6 +2991,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000122 ",
         "Counter": "0,1,2,3",
@@ -2807,6 +3004,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000122 ",
         "Counter": "0,1,2,3",
@@ -2819,6 +3017,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000122 ",
         "Counter": "0,1,2,3",
@@ -2831,6 +3030,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000122 ",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/other.json b/tools/perf/pmu-events/arch/x86/broadwell/other.json
index edf14f0d0eaf..4f829c5febbe 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/other.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/other.json
@@ -10,16 +10,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
-        "EventCode": "0x5C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPL_CYCLES.RING123",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PublicDescription": "This event counts when there is a transition from ring 1,2 or 3 to ring0.",
         "EventCode": "0x5C",
         "Counter": "0,1,2,3",
@@ -32,6 +22,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
+        "EventCode": "0x5C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPL_CYCLES.RING123",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts cycles in which the L1 and L2 are locked due to a UC lock or split lock. A lock is asserted in case of locked memory access, due to noncacheable memory, locked operation that spans two cache lines, or a page walk from the noncacheable page table. L1D and L2 locks have a very high performance penalty and it is highly recommended to avoid such access.",
         "EventCode": "0x63",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
index 78913ae87703..97c5d0784c6c 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
@@ -2,32 +2,42 @@
     {
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Core cycles when the thread is not in halt state",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:\n - preceding store conflicts with the load (incomplete overlap);\n - store forwarding is impossible due to u-arch limitations;\n - preceding lock RMW operations are not forwarded;\n - store has the no-forward bit set (uncacheable/page-split/masked stores);\n - all-blocking stores are used (mostly, fences and port I/O);\nand others.\nThe most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events.\nSee the table of not supported store forwards in the Optimization Guide.",
@@ -59,27 +69,38 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.",
+        "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.",
         "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "UMask": "0x3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.",
         "EventCode": "0x0D",
         "Counter": "0,1,2,3",
         "UMask": "0x3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "AnyThread": "1",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...)",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.",
+        "EventCode": "0x0D",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS).",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
@@ -90,6 +111,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "EventCode": "0x0E",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive\n added by GSR u-arch.",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
@@ -118,18 +151,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
-        "EventCode": "0x0E",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "This event counts the number of the divide operations executed. Uses edge-detect and a cmask value of 1 on ARITH.FPU_DIV_ACTIVE to get the number of the divide operations executed.",
         "EventCode": "0x14",
         "Counter": "0,1,2,3",
@@ -140,6 +161,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This is a fixed-frequency event programmed to general counters. It counts when the core is unhalted at 100 Mhz.",
         "EventCode": "0x3C",
         "Counter": "0,1,2,3",
@@ -150,6 +191,36 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x3c",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -159,6 +230,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by asm inspection of the nearby instructions.",
         "EventCode": "0x4c",
         "Counter": "0,1,2,3",
@@ -225,6 +305,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5E",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "EventCode": "0x87",
         "Counter": "0,1,2,3",
@@ -405,6 +497,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x89",
+        "Counter": "0,1,2,3",
+        "UMask": "0xa0",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts both taken and not taken speculative and retired mispredicted macro conditional branch instructions.",
         "EventCode": "0x89",
         "Counter": "0,1,2,3",
@@ -435,6 +536,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file.  The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*.  See the Broadwell Optimization Guide for more information.",
+        "EventCode": "0xA0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -445,6 +556,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -455,6 +586,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -465,6 +616,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -475,6 +646,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -485,6 +676,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -495,6 +706,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -505,6 +736,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -515,6 +766,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
         "EventCode": "0xA2",
         "Counter": "0,1,2,3",
@@ -566,15 +837,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts number of cycles the CPU has at least one pending  demand load request missing the L1 data cache.",
         "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "CounterMask": "8",
-        "CounterHTOff": "2"
+        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PublicDescription": "Counts number of cycles the CPU has at least one pending  demand load request (that is cycles with non-completed load waiting for its data from memory subsystem).",
@@ -588,17 +858,37 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PublicDescription": "Counts number of cycles nothing is executed on any execution port.",
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls",
+        "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.",
         "CounterMask": "4",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Total execution stalls.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts number of cycles nothing is executed on any execution port, while there was at least one pending demand* load request missing the L2 cache.(as a footprint) * includes also L1 HW prefetch requests that may or may not be required by demands.",
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
@@ -610,6 +900,16 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x5",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
+        "CounterMask": "5",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts number of cycles nothing is executed on any execution port, while there was at least one pending demand load request.",
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
@@ -621,6 +921,37 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x6",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts number of cycles the CPU has at least one pending  demand load request missing the L1 data cache.",
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "CounterMask": "8",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "CounterMask": "8",
+        "CounterHTOff": "2"
+    },
+    {
         "PublicDescription": "Counts number of cycles nothing is executed on any execution port, while there was at least one pending demand load request missing the L1 data cache.",
         "EventCode": "0xA3",
         "Counter": "2",
@@ -632,7 +963,16 @@
         "CounterHTOff": "2"
     },
     {
-        "PublicDescription": "Number of Uops delivered by the LSD. ",
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0xc",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "CounterMask": "12",
+        "CounterHTOff": "2"
+    },
+    {
         "EventCode": "0xA8",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -642,6 +982,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA8",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of uops to be executed per-thread each cycle.",
         "EventCode": "0xB1",
         "Counter": "0,1,2,3",
@@ -652,6 +1012,58 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "EventCode": "0xB1",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PublicDescription": "Number of uops executed from any thread.",
         "EventCode": "0xB1",
         "Counter": "0,1,2,3",
@@ -662,36 +1074,64 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
-        "EventCode": "0xB1",
-        "Invert": "1",
+        "EventCode": "0xb1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
-        "EventCode": "0xC0",
+        "EventCode": "0xb1",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "Errata": "BDM61",
-        "EventName": "INST_RETIRED.ANY_P",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "CounterMask": "2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
-        "EventCode": "0xC0",
+        "EventCode": "0xb1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "INST_RETIRED.X87",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "FP operations  retired. X87 FP operations that have no exceptions:",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "Errata": "BDM61",
+        "EventName": "INST_RETIRED.ANY_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -707,6 +1147,16 @@
         "CounterHTOff": "1"
     },
     {
+        "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "INST_RETIRED.X87",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "FP operations  retired. X87 FP operations that have no exceptions:",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
@@ -717,29 +1167,18 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
         "EventCode": "0xC2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.ALL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Actually retired uops.",
+        "BriefDescription": "Actually retired uops. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7",
         "Data_LA": "1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of retirement slots used.",
-        "EventCode": "0xC2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
@@ -763,6 +1202,17 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Retirement slots used. (Precise Event - PEBS)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts both thread-specific (TS) and all-thread (AT) nukes.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
@@ -773,6 +1223,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts self-modifying code (SMC) detected, which causes a machine clear.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
@@ -793,50 +1254,73 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts all (macro) branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Conditional branch instructions retired.",
+        "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts all (macro) branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
+        "UMask": "0x2",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PEBS": "2",
+        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "Errata": "BDW98",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Return instructions retired.",
+        "BriefDescription": "Return instructions retired. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "PublicDescription": "This event counts not taken branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -847,17 +1331,17 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Taken branch instructions retired.",
+        "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.",
+        "PublicDescription": "This event counts far branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
@@ -868,29 +1352,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "Errata": "BDW98",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.",
-        "EventCode": "0xC5",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted conditional branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PublicDescription": "This event counts all mispredicted macro branch instructions retired.",
         "EventCode": "0xC5",
         "Counter": "0,1,2,3",
@@ -902,13 +1363,13 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
         "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "BR_MISP_RETIRED.RET",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
+        "UMask": "0x1",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -923,164 +1384,36 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.",
-        "EventCode": "0xCC",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Count cases of saving new LBR",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Thread cycles when thread is not in halt state",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x89",
-        "Counter": "0,1,2,3",
-        "UMask": "0xa0",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "EventName": "BR_MISP_RETIRED.RET",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
         "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
+        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread.",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
+        "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.",
+        "EventCode": "0xCC",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "UMask": "0x20",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Count cases of saving new LBR",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xe6",
@@ -1090,328 +1423,5 @@
         "SampleAfterValue": "100003",
         "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "CounterMask": "8",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0xc",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
-        "CounterMask": "12",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
-        "CounterMask": "5",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x6",
-        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x5E",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 0",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 5",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 7",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file.  The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*.  See the Broadwell Optimization Guide for more information.",
-        "EventCode": "0xA0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x0D",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/virtual-memory.json b/tools/perf/pmu-events/arch/x86/broadwell/virtual-memory.json
index 4301e6fbc5eb..2a015e4c7e21 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/virtual-memory.json
@@ -44,6 +44,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "Errata": "BDM69",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
@@ -73,6 +83,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x60",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
@@ -117,6 +136,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "Errata": "BDM69",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
@@ -146,6 +175,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x60",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts cycles for an extended page table walk. The Extended Page directory cache differs from standard TLB caches by the operating system that use it. Virtual machine operating systems use the extended page directory cache, while guest operating systems use the standard TLB caches.",
         "EventCode": "0x4F",
         "Counter": "0,1,2,3",
@@ -200,6 +238,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "Errata": "BDM69",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of cycles while PMH is busy with the page walk.",
         "EventCode": "0x85",
         "Counter": "0,1,2,3",
@@ -229,6 +277,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x60",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
         "EventCode": "0xAE",
         "Counter": "0,1,2,3",
@@ -251,61 +308,61 @@
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x21",
+        "UMask": "0x12",
         "Errata": "BDM69, BDM98",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
+        "BriefDescription": "Number of DTLB page walker hits in the L2.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x12",
+        "UMask": "0x14",
         "Errata": "BDM69, BDM98",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of DTLB page walker hits in the L2.",
+        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x22",
+        "UMask": "0x18",
         "Errata": "BDM69, BDM98",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of ITLB page walker hits in the L2.",
+        "BriefDescription": "Number of DTLB page walker hits in Memory.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x14",
+        "UMask": "0x21",
         "Errata": "BDM69, BDM98",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
+        "BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
+        "UMask": "0x22",
         "Errata": "BDM69, BDM98",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
+        "BriefDescription": "Number of ITLB page walker hits in the L2.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
+        "UMask": "0x24",
         "Errata": "BDM69, BDM98",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of DTLB page walker hits in Memory.",
+        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -327,62 +384,5 @@
         "SampleAfterValue": "100007",
         "BriefDescription": "STLB flush attempts",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "Errata": "BDM69",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x60",
-        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "Errata": "BDM69",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "Counter": "0,1,2,3",
-        "UMask": "0x60",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "Errata": "BDM69",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x60",
-        "EventName": "ITLB_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
new file mode 100644
index 000000000000..49c5f123d811
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / INST_RETIRED.ANY / cycles",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / RS_EVENTS.EMPTY_END",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
index 36fe398029b9..bf243fe2a0ec 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
@@ -11,11 +11,28 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "UMask": "0x22",
+        "BriefDescription": "RFO requests that miss L2 cache.",
         "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x24",
+        "BriefDescription": "L2 cache misses when fetching instructions.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x27",
+        "BriefDescription": "Demand requests that miss L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -31,6 +48,43 @@
     },
     {
         "EventCode": "0x24",
+        "UMask": "0x3f",
+        "BriefDescription": "All requests that miss L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x41",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x42",
+        "BriefDescription": "RFO requests that hit L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x44",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
         "UMask": "0x50",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
         "Counter": "0,1,2,3",
@@ -71,6 +125,15 @@
     },
     {
         "EventCode": "0x24",
+        "UMask": "0xe7",
+        "BriefDescription": "Demand requests to L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
         "UMask": "0xf8",
         "BriefDescription": "Requests from L2 hardware prefetchers",
         "Counter": "0,1,2,3",
@@ -80,6 +143,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x24",
+        "UMask": "0xff",
+        "BriefDescription": "All L2 requests.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x27",
         "UMask": "0x50",
         "BriefDescription": "Not rejected writebacks that hit L2 cache",
@@ -131,6 +203,27 @@
         "CounterHTOff": "2"
     },
     {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "Counter": "2",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "AnyThread": "1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x51",
         "UMask": "0x1",
         "BriefDescription": "L1D data line replacements",
@@ -153,12 +246,35 @@
     },
     {
         "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "Errata": "BDM76",
+        "PublicDescription": "This event counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
+        "Errata": "BDM76",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
         "UMask": "0x2",
         "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
         "Errata": "BDM76",
-        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -175,24 +291,24 @@
     },
     {
         "EventCode": "0x60",
-        "UMask": "0x8",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "UMask": "0x4",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "CounterMask": "1",
         "Errata": "BDM76",
-        "PublicDescription": "This event counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "UMask": "0x8",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "CounterMask": "1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "Errata": "BDM76",
-        "PublicDescription": "This event counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "PublicDescription": "This event counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -209,18 +325,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x60",
-        "UMask": "0x4",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "CounterMask": "1",
-        "Errata": "BDM76",
-        "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x63",
         "UMask": "0x2",
         "BriefDescription": "Cycles when L1D is locked",
@@ -266,7 +370,7 @@
         "BriefDescription": "Demand and prefetch data reads",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
-        "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable \"Demands\" and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable Demands and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -281,26 +385,35 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load uops that miss the STLB.",
+        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store uops that miss the STLB.",
+        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -308,37 +421,37 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load uops with locked access.",
+        "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "Errata": "BDM35",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts load uops with locked access retired to the architected path.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -346,24 +459,24 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "All retired load uops. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
         "SampleAfterValue": "2000003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -371,69 +484,69 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "Errata": "BDM35",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
+        "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops misses in L1 cache as data sources.",
+        "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x10",
-        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x20",
-        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -445,77 +558,112 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x40",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.",
+        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x1",
-        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "Errata": "BDE70, BDM100",
-        "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).",
+        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x4",
+        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM",
+        "Errata": "BDE70",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x10",
+        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM",
+        "Errata": "BDE70",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x20",
+        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD",
+        "Errata": "BDE70",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -657,118 +805,5 @@
         "PublicDescription": "This event counts the number of split locks in the super queue.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x42",
-        "BriefDescription": "RFO requests that hit L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x22",
-        "BriefDescription": "RFO requests that miss L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x44",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x24",
-        "BriefDescription": "L2 cache misses when fetching instructions.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x27",
-        "BriefDescription": "Demand requests that miss L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0xe7",
-        "BriefDescription": "Demand requests to L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x3f",
-        "BriefDescription": "All requests that miss L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0xff",
-        "BriefDescription": "All L2 requests.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.REFERENCES",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x60",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "CounterMask": "6",
-        "Errata": "BDM76",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "Counter": "2",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "AnyThread": "1",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0x48",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "Counter": "0,1,2,3",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json
index 4ae1ea24f22f..d7b9d9c9c518 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json
@@ -6,7 +6,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
         "Errata": "BDM30",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
+        "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -17,7 +17,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
         "Errata": "BDM30",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
+        "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -25,7 +25,6 @@
         "EventCode": "0xC7",
         "UMask": "0x1",
         "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -35,7 +34,6 @@
         "EventCode": "0xC7",
         "UMask": "0x2",
         "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "SampleAfterValue": "2000003",
@@ -43,9 +41,17 @@
     },
     {
         "EventCode": "0xC7",
+        "UMask": "0x3",
+        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
         "UMask": "0x4",
         "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -55,7 +61,6 @@
         "EventCode": "0xC7",
         "UMask": "0x8",
         "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
@@ -65,19 +70,54 @@
         "EventCode": "0xC7",
         "UMask": "0x10",
         "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xC7",
+        "UMask": "0x15",
+        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
+        "SampleAfterValue": "2000006",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xc7",
+        "UMask": "0x20",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x2a",
+        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
+        "SampleAfterValue": "2000005",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x3c",
+        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.PACKED",
+        "SampleAfterValue": "2000004",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xCA",
         "UMask": "0x2",
         "BriefDescription": "Number of X87 assists due to output value.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.X87_OUTPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
+        "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -87,7 +127,7 @@
         "BriefDescription": "Number of X87 assists due to input value.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.X87_INPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
+        "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -97,7 +137,7 @@
         "BriefDescription": "Number of SIMD FP assists due to Output values",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.SIMD_OUTPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
+        "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -107,7 +147,7 @@
         "BriefDescription": "Number of SIMD FP assists due to input values",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.SIMD_INPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
+        "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -121,51 +161,5 @@
         "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xc7",
-        "UMask": "0x20",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x3",
-        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x3c",
-        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.PACKED",
-        "SampleAfterValue": "2000004",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x2a",
-        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
-        "SampleAfterValue": "2000005",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x15",
-        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
-        "SampleAfterValue": "2000006",
-        "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json b/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json
index 06bf0a40e568..72781e1e3362 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json
@@ -15,80 +15,49 @@
         "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x10",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_DSB_UOPS",
-        "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x20",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_MITE_UOPS",
-        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "EventName": "IDQ.MITE_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "UMask": "0x8",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MITE_CYCLES",
+        "EventName": "IDQ.DSB_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
+        "UMask": "0x10",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "EventName": "IDQ.MS_DSB_UOPS",
+        "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -99,7 +68,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MS_DSB_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -111,7 +80,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MS_DSB_OCCUR",
         "CounterMask": "1",
-        "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -122,7 +91,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
         "CounterMask": "4",
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -133,7 +102,17 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
         "CounterMask": "1",
-        "PublicDescription": "This event counts the number of cycles  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of cycles  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x20",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -144,7 +123,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
         "CounterMask": "4",
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -155,7 +134,39 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
         "CounterMask": "1",
-        "PublicDescription": "This event counts the number of cycles  uops were delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of cycles  uops were delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_SWITCHES",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -165,7 +176,7 @@
         "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MITE_ALL_UOPS",
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -205,7 +216,7 @@
         "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding ?4 ? x? when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -268,18 +279,7 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "Counter": "0,1,2,3",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0?2 cycles.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_SWITCHES",
-        "CounterMask": "1",
+        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/memory.json
index cfa1e5876ec3..e44f73c24ac8 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/memory.json
@@ -95,7 +95,6 @@
         "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.",
         "Counter": "0,1,2,3",
         "EventName": "TX_EXEC.MISC1",
-        "PublicDescription": "Unfriendly TSX abort triggered by  a flowmarker.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -171,11 +170,11 @@
     {
         "EventCode": "0xc8",
         "UMask": "0x4",
-        "BriefDescription": "Number of times HLE abort was triggered",
+        "BriefDescription": "Number of times HLE abort was triggered (PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED",
-        "PublicDescription": "Number of times HLE abort was triggered.",
+        "PublicDescription": "Number of times HLE abort was triggered (PEBS).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -252,11 +251,11 @@
     {
         "EventCode": "0xc9",
         "UMask": "0x4",
-        "BriefDescription": "Number of times RTM abort was triggered",
+        "BriefDescription": "Number of times RTM abort was triggered (PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Number of times RTM abort was triggered .",
+        "PublicDescription": "Number of times RTM abort was triggered (PEBS).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/other.json b/tools/perf/pmu-events/arch/x86/broadwellde/other.json
index 718fcb1db2ee..4475249ea9da 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/other.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/other.json
@@ -10,16 +10,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5C",
-        "UMask": "0x2",
-        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
-        "Counter": "0,1,2,3",
-        "EventName": "CPL_CYCLES.RING123",
-        "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EdgeDetect": "1",
         "EventCode": "0x5C",
         "UMask": "0x1",
@@ -32,6 +22,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5C",
+        "UMask": "0x2",
+        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "Counter": "0,1,2,3",
+        "EventName": "CPL_CYCLES.RING123",
+        "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x63",
         "UMask": "0x1",
         "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
index 02b4e1035f2d..920c89da9111 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
@@ -3,31 +3,41 @@
         "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x2",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "Fixed counter 1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "EventCode": "0x03",
@@ -60,22 +70,33 @@
     },
     {
         "EventCode": "0x0D",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread",
+        "UMask": "0x3",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
         "Counter": "0,1,2,3",
-        "EventName": "INT_MISC.RAT_STALL_CYCLES",
-        "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x0D",
         "UMask": "0x3",
-        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...)",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
         "Counter": "0,1,2,3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "AnyThread": "1",
         "CounterMask": "1",
-        "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -90,6 +111,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0x0E",
         "UMask": "0x10",
         "BriefDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive; added by GSR u-arch.",
@@ -118,18 +151,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
-        "EventCode": "0x0E",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "EventCode": "0x14",
         "UMask": "0x1",
         "BriefDescription": "Cycles when divider is busy executing divide operations",
@@ -141,6 +162,26 @@
     },
     {
         "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
         "UMask": "0x1",
         "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
         "Counter": "0,1,2,3",
@@ -150,6 +191,36 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x3c",
         "UMask": "0x2",
         "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
@@ -159,6 +230,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0x3C",
+        "UMask": "0x2",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x4c",
         "UMask": "0x1",
         "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch",
@@ -225,6 +305,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
+        "Invert": "1",
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "CounterMask": "1",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x87",
         "UMask": "0x1",
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
@@ -406,6 +498,15 @@
     },
     {
         "EventCode": "0x89",
+        "UMask": "0xa0",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x89",
         "UMask": "0xc1",
         "BriefDescription": "Speculative and retired mispredicted macro conditional branches",
         "Counter": "0,1,2,3",
@@ -435,6 +536,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA0",
+        "UMask": "0x3",
+        "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
+        "Counter": "0,1,2,3",
+        "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
+        "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file.  The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*.  See the Broadwell Optimization Guide for more information.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xA1",
         "UMask": "0x1",
         "BriefDescription": "Cycles per thread when uops are executed in port 0",
@@ -446,6 +557,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x2",
         "BriefDescription": "Cycles per thread when uops are executed in port 1",
         "Counter": "0,1,2,3",
@@ -456,6 +587,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x4",
         "BriefDescription": "Cycles per thread when uops are executed in port 2",
         "Counter": "0,1,2,3",
@@ -466,6 +617,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x8",
         "BriefDescription": "Cycles per thread when uops are executed in port 3",
         "Counter": "0,1,2,3",
@@ -476,6 +647,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x10",
         "BriefDescription": "Cycles per thread when uops are executed in port 4",
         "Counter": "0,1,2,3",
@@ -486,6 +677,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x20",
         "BriefDescription": "Cycles per thread when uops are executed in port 5",
         "Counter": "0,1,2,3",
@@ -496,6 +707,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x40",
         "BriefDescription": "Cycles per thread when uops are executed in port 6",
         "Counter": "0,1,2,3",
@@ -506,6 +737,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x80",
         "BriefDescription": "Cycles per thread when uops are executed in port 7",
         "Counter": "0,1,2,3",
@@ -515,6 +766,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xA2",
         "UMask": "0x1",
         "BriefDescription": "Resource-related stall cycles",
@@ -567,14 +838,13 @@
     },
     {
         "EventCode": "0xA3",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "Counter": "2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
-        "CounterMask": "8",
-        "PublicDescription": "Counts number of cycles the CPU has at least one pending  demand load request missing the L1 data cache.",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA3",
@@ -589,8 +859,18 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0x4",
-        "BriefDescription": "Total execution stalls",
+        "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.",
         "Counter": "0,1,2,3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE",
         "CounterMask": "4",
@@ -600,6 +880,16 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x4",
+        "BriefDescription": "Total execution stalls.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0x5",
         "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
@@ -611,6 +901,16 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x5",
+        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "CounterMask": "5",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0x6",
         "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
         "Counter": "0,1,2,3",
@@ -622,6 +922,37 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x6",
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "Counter": "2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "CounterMask": "8",
+        "PublicDescription": "Counts number of cycles the CPU has at least one pending  demand load request missing the L1 data cache.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "Counter": "2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "CounterMask": "8",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0xc",
         "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
         "Counter": "2",
@@ -632,12 +963,41 @@
         "CounterHTOff": "2"
     },
     {
+        "EventCode": "0xA3",
+        "UMask": "0xc",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "Counter": "2",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "CounterMask": "12",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
         "EventCode": "0xA8",
         "UMask": "0x1",
         "BriefDescription": "Number of Uops delivered by the LSD.",
         "Counter": "0,1,2,3",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Number of Uops delivered by the LSD. ",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_ACTIVE",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -652,6 +1012,58 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterMask": "3",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xB1",
         "UMask": "0x2",
         "BriefDescription": "Number of uops executed on the core.",
@@ -662,35 +1074,63 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC0",
-        "UMask": "0x0",
-        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "INST_RETIRED.ANY_P",
-        "Errata": "BDM61",
-        "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterMask": "2",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC0",
+        "EventCode": "0xb1",
         "UMask": "0x2",
-        "BriefDescription": "FP operations  retired. X87 FP operations that have no exceptions:",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "INST_RETIRED.X87",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "CounterMask": "3",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC0",
+        "UMask": "0x0",
+        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "Errata": "BDM61",
+        "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -707,6 +1147,16 @@
         "CounterHTOff": "1"
     },
     {
+        "EventCode": "0xC0",
+        "UMask": "0x2",
+        "BriefDescription": "FP operations  retired. X87 FP operations that have no exceptions:",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.X87",
+        "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC1",
         "UMask": "0x40",
         "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
@@ -718,23 +1168,12 @@
     {
         "EventCode": "0xC2",
         "UMask": "0x1",
-        "BriefDescription": "Actually retired uops.",
+        "BriefDescription": "Actually retired uops. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.ALL",
-        "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC2",
-        "UMask": "0x2",
-        "BriefDescription": "Retirement slots used.",
-        "PEBS": "1",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of retirement slots used.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -746,7 +1185,7 @@
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -763,6 +1202,17 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Retirement slots used. (Precise Event - PEBS)",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC3",
         "UMask": "0x1",
         "BriefDescription": "Cycles there was a Nuke. Account for both thread-specific and All Thread Nukes.",
@@ -773,6 +1223,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
+        "EventCode": "0xC3",
+        "UMask": "0x1",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "CounterMask": "1",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC3",
         "UMask": "0x4",
         "BriefDescription": "Self-modifying code (SMC) detected.",
@@ -794,44 +1255,67 @@
     },
     {
         "EventCode": "0xC4",
+        "UMask": "0x0",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "This event counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
         "UMask": "0x1",
-        "BriefDescription": "Conditional branch instructions retired.",
+        "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x2",
-        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
-        "UMask": "0x0",
-        "BriefDescription": "All (macro) branch instructions retired.",
+        "UMask": "0x2",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)",
+        "PEBS": "1",
         "Counter": "0,1,2,3",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "This event counts all (macro) branch instructions retired.",
-        "SampleAfterValue": "400009",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).",
+        "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
+        "UMask": "0x4",
+        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)",
+        "PEBS": "2",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "Errata": "BDW98",
+        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC4",
         "UMask": "0x8",
-        "BriefDescription": "Return instructions retired.",
+        "BriefDescription": "Return instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -841,18 +1325,18 @@
         "BriefDescription": "Not taken branch instructions retired.",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "PublicDescription": "This event counts not taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x20",
-        "BriefDescription": "Taken branch instructions retired.",
+        "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -863,34 +1347,11 @@
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "Errata": "BDW98",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.",
+        "PublicDescription": "This event counts far branch instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
-        "UMask": "0x4",
-        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)",
-        "PEBS": "2",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "Errata": "BDW98",
-        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
-        "SampleAfterValue": "400009",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC5",
-        "UMask": "0x1",
-        "BriefDescription": "Mispredicted conditional branch instructions retired.",
-        "PEBS": "1",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.",
-        "SampleAfterValue": "400009",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xC5",
         "UMask": "0x0",
         "BriefDescription": "All mispredicted macro branch instructions retired.",
@@ -902,13 +1363,13 @@
     },
     {
         "EventCode": "0xC5",
-        "UMask": "0x8",
-        "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
+        "UMask": "0x1",
+        "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
-        "SampleAfterValue": "100007",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -923,164 +1384,36 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xCC",
-        "UMask": "0x20",
-        "BriefDescription": "Count cases of saving new LBR",
-        "Counter": "0,1,2,3",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
-        "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x0",
-        "BriefDescription": "Thread cycles when thread is not in halt state",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x89",
-        "UMask": "0xa0",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
+        "EventCode": "0xC5",
         "UMask": "0x8",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x10",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x20",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x40",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x80",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)",
+        "PEBS": "1",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
+        "EventName": "BR_MISP_RETIRED.RET",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.",
+        "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC5",
         "UMask": "0x20",
-        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
+        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "CounterMask": "2",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "CounterMask": "3",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventCode": "0xCC",
+        "UMask": "0x20",
+        "BriefDescription": "Count cases of saving new LBR",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
-        "CounterMask": "4",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xe6",
@@ -1090,328 +1423,5 @@
         "EventName": "BACLEARS.ANY",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "Counter": "2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
-        "CounterMask": "8",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
-        "CounterMask": "2",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x4",
-        "BriefDescription": "Total execution stalls.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
-        "CounterMask": "4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0xc",
-        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
-        "Counter": "2",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
-        "CounterMask": "12",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x5",
-        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
-        "CounterMask": "5",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x6",
-        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
-        "CounterMask": "6",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "EventCode": "0xC3",
-        "UMask": "0x1",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "Counter": "0,1,2,3",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "CounterMask": "1",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_4_UOPS",
-        "CounterMask": "4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "Invert": "1",
-        "EventCode": "0x5E",
-        "UMask": "0x1",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "Counter": "0,1,2,3",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "CounterMask": "1",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_ACTIVE",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles per thread when uops are executed in port 0",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles per thread when uops are executed in port 1",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles per thread when uops are executed in port 2",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles per thread when uops are executed in port 3",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x10",
-        "BriefDescription": "Cycles per thread when uops are executed in port 4",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x20",
-        "BriefDescription": "Cycles per thread when uops are executed in port 5",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x40",
-        "BriefDescription": "Cycles per thread when uops are executed in port 6",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x80",
-        "BriefDescription": "Cycles per thread when uops are executed in port 7",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA0",
-        "UMask": "0x3",
-        "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
-        "Counter": "0,1,2,3",
-        "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
-        "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file.  The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*.  See the Broadwell Optimization Guide for more information.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x00",
-        "UMask": "0x2",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "Counter": "Fixed counter 2",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x0",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x0D",
-        "UMask": "0x3",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "Counter": "0,1,2,3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "AnyThread": "1",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "CounterMask": "2",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "CounterMask": "3",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "CounterMask": "4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "Invert": "1",
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x2",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/virtual-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/virtual-memory.json
index 5ce8b67ba076..7d79c707c6d1 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/virtual-memory.json
@@ -45,6 +45,16 @@
     },
     {
         "EventCode": "0x08",
+        "UMask": "0xe",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "Errata": "BDM69",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -73,6 +83,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x08",
+        "UMask": "0x60",
+        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x49",
         "UMask": "0x1",
         "BriefDescription": "Store misses in all DTLB levels that cause page walks",
@@ -118,6 +137,16 @@
     },
     {
         "EventCode": "0x49",
+        "UMask": "0xe",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "Errata": "BDM69",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -146,6 +175,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x49",
+        "UMask": "0x60",
+        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x4F",
         "UMask": "0x10",
         "BriefDescription": "Cycle count for an Extended Page table walk.",
@@ -201,6 +239,16 @@
     },
     {
         "EventCode": "0x85",
+        "UMask": "0xe",
+        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "Errata": "BDM69",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -229,6 +277,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x85",
+        "UMask": "0x60",
+        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xAE",
         "UMask": "0x1",
         "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
@@ -250,60 +307,60 @@
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x21",
-        "BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
+        "UMask": "0x12",
+        "BriefDescription": "Number of DTLB page walker hits in the L2.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x12",
-        "BriefDescription": "Number of DTLB page walker hits in the L2.",
+        "UMask": "0x14",
+        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x22",
-        "BriefDescription": "Number of ITLB page walker hits in the L2.",
+        "UMask": "0x18",
+        "BriefDescription": "Number of DTLB page walker hits in Memory.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x14",
-        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
+        "UMask": "0x21",
+        "BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x24",
-        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
+        "UMask": "0x22",
+        "BriefDescription": "Number of ITLB page walker hits in the L2.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L2",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x18",
-        "BriefDescription": "Number of DTLB page walker hits in Memory.",
+        "UMask": "0x24",
+        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
@@ -327,62 +384,5 @@
         "PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "UMask": "0xe",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "Errata": "BDM69",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "UMask": "0x60",
-        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "UMask": "0xe",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "Errata": "BDM69",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "UMask": "0x60",
-        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "UMask": "0xe",
-        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "Errata": "BDM69",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "UMask": "0x60",
-        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "ITLB_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
new file mode 100644
index 000000000000..5a7f1ec24200
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles))",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
index d1d043829b95..bf0c51272068 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
@@ -11,11 +11,28 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "UMask": "0x22",
+        "BriefDescription": "RFO requests that miss L2 cache.",
         "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x24",
+        "BriefDescription": "L2 cache misses when fetching instructions.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x27",
+        "BriefDescription": "Demand requests that miss L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -31,6 +48,43 @@
     },
     {
         "EventCode": "0x24",
+        "UMask": "0x3f",
+        "BriefDescription": "All requests that miss L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x41",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x42",
+        "BriefDescription": "RFO requests that hit L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x44",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
         "UMask": "0x50",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
         "Counter": "0,1,2,3",
@@ -71,6 +125,15 @@
     },
     {
         "EventCode": "0x24",
+        "UMask": "0xe7",
+        "BriefDescription": "Demand requests to L2 cache.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
         "UMask": "0xf8",
         "BriefDescription": "Requests from L2 hardware prefetchers",
         "Counter": "0,1,2,3",
@@ -80,6 +143,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x24",
+        "UMask": "0xff",
+        "BriefDescription": "All L2 requests.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x27",
         "UMask": "0x50",
         "BriefDescription": "Not rejected writebacks that hit L2 cache",
@@ -131,6 +203,27 @@
         "CounterHTOff": "2"
     },
     {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "Counter": "2",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "AnyThread": "1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x51",
         "UMask": "0x1",
         "BriefDescription": "L1D data line replacements",
@@ -153,12 +246,35 @@
     },
     {
         "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "Errata": "BDM76",
+        "PublicDescription": "This event counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
+        "Errata": "BDM76",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
         "UMask": "0x2",
         "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
         "Errata": "BDM76",
-        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -175,24 +291,24 @@
     },
     {
         "EventCode": "0x60",
-        "UMask": "0x8",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "UMask": "0x4",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "CounterMask": "1",
         "Errata": "BDM76",
-        "PublicDescription": "This event counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The Offcore outstanding state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "UMask": "0x8",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "CounterMask": "1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "Errata": "BDM76",
-        "PublicDescription": "This event counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "PublicDescription": "This event counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -209,18 +325,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x60",
-        "UMask": "0x4",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "CounterMask": "1",
-        "Errata": "BDM76",
-        "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The \"Offcore outstanding\" state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x63",
         "UMask": "0x2",
         "BriefDescription": "Cycles when L1D is locked",
@@ -266,7 +370,7 @@
         "BriefDescription": "Demand and prefetch data reads",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
-        "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable \"Demands\" and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable Demands and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -281,26 +385,35 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load uops that miss the STLB.",
+        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store uops that miss the STLB.",
+        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -308,37 +421,37 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load uops with locked access.",
+        "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "Errata": "BDM35",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts load uops with locked access retired to the architected path.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -346,24 +459,24 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "All retired load uops. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
         "SampleAfterValue": "2000003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -371,69 +484,69 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "Errata": "BDM35",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
+        "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops misses in L1 cache as data sources.",
+        "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x10",
-        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x20",
-        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -445,84 +558,83 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x40",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.",
+        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE",
         "Errata": "BDM100",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x1",
-        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "Errata": "BDE70, BDM100",
-        "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).",
+        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
+        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -534,7 +646,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
+        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -546,7 +658,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x20",
-        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
+        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -695,119 +807,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
-        "UMask": "0x42",
-        "BriefDescription": "RFO requests that hit L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x22",
-        "BriefDescription": "RFO requests that miss L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x44",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x24",
-        "BriefDescription": "L2 cache misses when fetching instructions.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x27",
-        "BriefDescription": "Demand requests that miss L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0xe7",
-        "BriefDescription": "Demand requests to L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x3f",
-        "BriefDescription": "All requests that miss L2 cache.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0xff",
-        "BriefDescription": "All L2 requests.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.REFERENCES",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x60",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "CounterMask": "6",
-        "Errata": "BDM76",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "Counter": "2",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "AnyThread": "1",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0x48",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "Counter": "0,1,2,3",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
@@ -816,6 +815,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -828,6 +828,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -840,6 +841,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -852,6 +854,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -864,6 +867,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -876,6 +880,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -888,6 +893,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -900,6 +906,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -912,6 +919,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -924,6 +932,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -936,6 +945,20 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3",
+        "MSRValue": "0x3f803c0002",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
index 4ae1ea24f22f..d7b9d9c9c518 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
@@ -6,7 +6,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
         "Errata": "BDM30",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
+        "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -17,7 +17,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
         "Errata": "BDM30",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
+        "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -25,7 +25,6 @@
         "EventCode": "0xC7",
         "UMask": "0x1",
         "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -35,7 +34,6 @@
         "EventCode": "0xC7",
         "UMask": "0x2",
         "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "SampleAfterValue": "2000003",
@@ -43,9 +41,17 @@
     },
     {
         "EventCode": "0xC7",
+        "UMask": "0x3",
+        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
         "UMask": "0x4",
         "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -55,7 +61,6 @@
         "EventCode": "0xC7",
         "UMask": "0x8",
         "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
@@ -65,19 +70,54 @@
         "EventCode": "0xC7",
         "UMask": "0x10",
         "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xC7",
+        "UMask": "0x15",
+        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
+        "SampleAfterValue": "2000006",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xc7",
+        "UMask": "0x20",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x2a",
+        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
+        "SampleAfterValue": "2000005",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x3c",
+        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.PACKED",
+        "SampleAfterValue": "2000004",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xCA",
         "UMask": "0x2",
         "BriefDescription": "Number of X87 assists due to output value.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.X87_OUTPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
+        "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -87,7 +127,7 @@
         "BriefDescription": "Number of X87 assists due to input value.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.X87_INPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
+        "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -97,7 +137,7 @@
         "BriefDescription": "Number of SIMD FP assists due to Output values",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.SIMD_OUTPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
+        "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -107,7 +147,7 @@
         "BriefDescription": "Number of SIMD FP assists due to input values",
         "Counter": "0,1,2,3",
         "EventName": "FP_ASSIST.SIMD_INPUT",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
+        "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -121,51 +161,5 @@
         "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xc7",
-        "UMask": "0x20",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "PEBS": "1",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x3",
-        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x3c",
-        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.PACKED",
-        "SampleAfterValue": "2000004",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x2a",
-        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
-        "SampleAfterValue": "2000005",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC7",
-        "UMask": "0x15",
-        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
-        "Counter": "0,1,2,3",
-        "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
-        "SampleAfterValue": "2000006",
-        "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json
index 06bf0a40e568..72781e1e3362 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json
@@ -15,80 +15,49 @@
         "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x10",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_DSB_UOPS",
-        "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x20",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_MITE_UOPS",
-        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "EventName": "IDQ.MITE_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "UMask": "0x8",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may \"bypass\" the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MITE_CYCLES",
+        "EventName": "IDQ.DSB_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
+        "UMask": "0x10",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "EventName": "IDQ.MS_DSB_UOPS",
+        "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -99,7 +68,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MS_DSB_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -111,7 +80,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MS_DSB_OCCUR",
         "CounterMask": "1",
-        "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -122,7 +91,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
         "CounterMask": "4",
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -133,7 +102,17 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
         "CounterMask": "1",
-        "PublicDescription": "This event counts the number of cycles  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may \"bypass\" the IDQ.",
+        "PublicDescription": "This event counts the number of cycles  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may bypass the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x20",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -144,7 +123,7 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
         "CounterMask": "4",
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -155,7 +134,39 @@
         "Counter": "0,1,2,3",
         "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
         "CounterMask": "1",
-        "PublicDescription": "This event counts the number of cycles  uops were delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of cycles  uops were delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_SWITCHES",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -165,7 +176,7 @@
         "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MITE_ALL_UOPS",
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may \"bypass\" the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may bypass the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -205,7 +216,7 @@
         "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding ?4 ? x? when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -268,18 +279,7 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "Counter": "0,1,2,3",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0?2 cycles.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_SWITCHES",
-        "CounterMask": "1",
+        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
index 1204ea8ff30d..d79a5cfea44b 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
@@ -95,7 +95,6 @@
         "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.",
         "Counter": "0,1,2,3",
         "EventName": "TX_EXEC.MISC1",
-        "PublicDescription": "Unfriendly TSX abort triggered by  a flowmarker.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -171,11 +170,11 @@
     {
         "EventCode": "0xc8",
         "UMask": "0x4",
-        "BriefDescription": "Number of times HLE abort was triggered",
+        "BriefDescription": "Number of times HLE abort was triggered (PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED",
-        "PublicDescription": "Number of times HLE abort was triggered.",
+        "PublicDescription": "Number of times HLE abort was triggered (PEBS).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -252,11 +251,11 @@
     {
         "EventCode": "0xc9",
         "UMask": "0x4",
-        "BriefDescription": "Number of times RTM abort was triggered",
+        "BriefDescription": "Number of times RTM abort was triggered (PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Number of times RTM abort was triggered .",
+        "PublicDescription": "Number of times RTM abort was triggered (PEBS).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -439,6 +438,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -451,6 +451,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -463,6 +464,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -475,6 +477,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -487,6 +490,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -499,6 +503,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -511,6 +516,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -523,6 +529,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -535,6 +542,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -547,6 +555,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -559,6 +568,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -571,6 +581,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -583,6 +594,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -595,6 +607,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -607,6 +620,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -619,6 +633,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -631,6 +646,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -643,6 +659,20 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
+        "MSRValue": "0x3fbfc00002",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/other.json b/tools/perf/pmu-events/arch/x86/broadwellx/other.json
index 718fcb1db2ee..4475249ea9da 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/other.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/other.json
@@ -10,16 +10,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5C",
-        "UMask": "0x2",
-        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
-        "Counter": "0,1,2,3",
-        "EventName": "CPL_CYCLES.RING123",
-        "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EdgeDetect": "1",
         "EventCode": "0x5C",
         "UMask": "0x1",
@@ -32,6 +22,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5C",
+        "UMask": "0x2",
+        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "Counter": "0,1,2,3",
+        "EventName": "CPL_CYCLES.RING123",
+        "PublicDescription": "This event counts unhalted core cycles during which the thread is in rings 1, 2, or 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x63",
         "UMask": "0x1",
         "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
index 02b4e1035f2d..920c89da9111 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
@@ -3,31 +3,41 @@
         "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x2",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "Fixed counter 1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "EventCode": "0x03",
@@ -60,22 +70,33 @@
     },
     {
         "EventCode": "0x0D",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread",
+        "UMask": "0x3",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
         "Counter": "0,1,2,3",
-        "EventName": "INT_MISC.RAT_STALL_CYCLES",
-        "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x0D",
         "UMask": "0x3",
-        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...)",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
         "Counter": "0,1,2,3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "AnyThread": "1",
         "CounterMask": "1",
-        "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -90,6 +111,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0x0E",
         "UMask": "0x10",
         "BriefDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive; added by GSR u-arch.",
@@ -118,18 +151,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
-        "EventCode": "0x0E",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "EventCode": "0x14",
         "UMask": "0x1",
         "BriefDescription": "Cycles when divider is busy executing divide operations",
@@ -141,6 +162,26 @@
     },
     {
         "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
         "UMask": "0x1",
         "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
         "Counter": "0,1,2,3",
@@ -150,6 +191,36 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x3c",
         "UMask": "0x2",
         "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
@@ -159,6 +230,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0x3C",
+        "UMask": "0x2",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x4c",
         "UMask": "0x1",
         "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch",
@@ -225,6 +305,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
+        "Invert": "1",
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "CounterMask": "1",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x87",
         "UMask": "0x1",
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
@@ -406,6 +498,15 @@
     },
     {
         "EventCode": "0x89",
+        "UMask": "0xa0",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x89",
         "UMask": "0xc1",
         "BriefDescription": "Speculative and retired mispredicted macro conditional branches",
         "Counter": "0,1,2,3",
@@ -435,6 +536,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA0",
+        "UMask": "0x3",
+        "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
+        "Counter": "0,1,2,3",
+        "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
+        "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file.  The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*.  See the Broadwell Optimization Guide for more information.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xA1",
         "UMask": "0x1",
         "BriefDescription": "Cycles per thread when uops are executed in port 0",
@@ -446,6 +557,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x2",
         "BriefDescription": "Cycles per thread when uops are executed in port 1",
         "Counter": "0,1,2,3",
@@ -456,6 +587,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x4",
         "BriefDescription": "Cycles per thread when uops are executed in port 2",
         "Counter": "0,1,2,3",
@@ -466,6 +617,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x8",
         "BriefDescription": "Cycles per thread when uops are executed in port 3",
         "Counter": "0,1,2,3",
@@ -476,6 +647,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x10",
         "BriefDescription": "Cycles per thread when uops are executed in port 4",
         "Counter": "0,1,2,3",
@@ -486,6 +677,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x20",
         "BriefDescription": "Cycles per thread when uops are executed in port 5",
         "Counter": "0,1,2,3",
@@ -496,6 +707,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x40",
         "BriefDescription": "Cycles per thread when uops are executed in port 6",
         "Counter": "0,1,2,3",
@@ -506,6 +737,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x80",
         "BriefDescription": "Cycles per thread when uops are executed in port 7",
         "Counter": "0,1,2,3",
@@ -515,6 +766,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7",
+        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xA2",
         "UMask": "0x1",
         "BriefDescription": "Resource-related stall cycles",
@@ -567,14 +838,13 @@
     },
     {
         "EventCode": "0xA3",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "Counter": "2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
-        "CounterMask": "8",
-        "PublicDescription": "Counts number of cycles the CPU has at least one pending  demand load request missing the L1 data cache.",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA3",
@@ -589,8 +859,18 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0x4",
-        "BriefDescription": "Total execution stalls",
+        "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.",
         "Counter": "0,1,2,3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE",
         "CounterMask": "4",
@@ -600,6 +880,16 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x4",
+        "BriefDescription": "Total execution stalls.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0x5",
         "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
@@ -611,6 +901,16 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x5",
+        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "CounterMask": "5",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0x6",
         "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
         "Counter": "0,1,2,3",
@@ -622,6 +922,37 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x6",
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "Counter": "2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "CounterMask": "8",
+        "PublicDescription": "Counts number of cycles the CPU has at least one pending  demand load request missing the L1 data cache.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "Counter": "2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "CounterMask": "8",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0xc",
         "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
         "Counter": "2",
@@ -632,12 +963,41 @@
         "CounterHTOff": "2"
     },
     {
+        "EventCode": "0xA3",
+        "UMask": "0xc",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "Counter": "2",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "CounterMask": "12",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
         "EventCode": "0xA8",
         "UMask": "0x1",
         "BriefDescription": "Number of Uops delivered by the LSD.",
         "Counter": "0,1,2,3",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Number of Uops delivered by the LSD. ",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_ACTIVE",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -652,6 +1012,58 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterMask": "3",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xB1",
         "UMask": "0x2",
         "BriefDescription": "Number of uops executed on the core.",
@@ -662,35 +1074,63 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC0",
-        "UMask": "0x0",
-        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "INST_RETIRED.ANY_P",
-        "Errata": "BDM61",
-        "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterMask": "2",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC0",
+        "EventCode": "0xb1",
         "UMask": "0x2",
-        "BriefDescription": "FP operations  retired. X87 FP operations that have no exceptions:",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "INST_RETIRED.X87",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "CounterMask": "3",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC0",
+        "UMask": "0x0",
+        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "Errata": "BDM61",
+        "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -707,6 +1147,16 @@
         "CounterHTOff": "1"
     },
     {
+        "EventCode": "0xC0",
+        "UMask": "0x2",
+        "BriefDescription": "FP operations  retired. X87 FP operations that have no exceptions:",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.X87",
+        "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC1",
         "UMask": "0x40",
         "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
@@ -718,23 +1168,12 @@
     {
         "EventCode": "0xC2",
         "UMask": "0x1",
-        "BriefDescription": "Actually retired uops.",
+        "BriefDescription": "Actually retired uops. (Precise Event - PEBS)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.ALL",
-        "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC2",
-        "UMask": "0x2",
-        "BriefDescription": "Retirement slots used.",
-        "PEBS": "1",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of retirement slots used.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -746,7 +1185,7 @@
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -763,6 +1202,17 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Retirement slots used. (Precise Event - PEBS)",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC3",
         "UMask": "0x1",
         "BriefDescription": "Cycles there was a Nuke. Account for both thread-specific and All Thread Nukes.",
@@ -773,6 +1223,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
+        "EventCode": "0xC3",
+        "UMask": "0x1",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "CounterMask": "1",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC3",
         "UMask": "0x4",
         "BriefDescription": "Self-modifying code (SMC) detected.",
@@ -794,44 +1255,67 @@
     },
     {
         "EventCode": "0xC4",
+        "UMask": "0x0",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "This event counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
         "UMask": "0x1",
-        "BriefDescription": "Conditional branch instructions retired.",
+        "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x2",
-        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
-        "UMask": "0x0",
-        "BriefDescription": "All (macro) branch instructions retired.",
+        "UMask": "0x2",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)",
+        "PEBS": "1",
         "Counter": "0,1,2,3",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "This event counts all (macro) branch instructions retired.",
-        "SampleAfterValue": "400009",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).",
+        "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
+        "UMask": "0x4",
+        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)",
+        "PEBS": "2",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "Errata": "BDW98",
+        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC4",
         "UMask": "0x8",
-        "BriefDescription": "Return instructions retired.",
+        "BriefDescription": "Return instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -841,18 +1325,18 @@
         "BriefDescription": "Not taken branch instructions retired.",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "PublicDescription": "This event counts not taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x20",
-        "BriefDescription": "Taken branch instructions retired.",
+        "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -863,34 +1347,11 @@
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "Errata": "BDW98",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.",
+        "PublicDescription": "This event counts far branch instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
-        "UMask": "0x4",
-        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS)",
-        "PEBS": "2",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "Errata": "BDW98",
-        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
-        "SampleAfterValue": "400009",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC5",
-        "UMask": "0x1",
-        "BriefDescription": "Mispredicted conditional branch instructions retired.",
-        "PEBS": "1",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.",
-        "SampleAfterValue": "400009",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xC5",
         "UMask": "0x0",
         "BriefDescription": "All mispredicted macro branch instructions retired.",
@@ -902,13 +1363,13 @@
     },
     {
         "EventCode": "0xC5",
-        "UMask": "0x8",
-        "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
+        "UMask": "0x1",
+        "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)",
         "PEBS": "1",
         "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
-        "SampleAfterValue": "100007",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -923,164 +1384,36 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xCC",
-        "UMask": "0x20",
-        "BriefDescription": "Count cases of saving new LBR",
-        "Counter": "0,1,2,3",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
-        "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x0",
-        "BriefDescription": "Thread cycles when thread is not in halt state",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x89",
-        "UMask": "0xa0",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
+        "EventCode": "0xC5",
         "UMask": "0x8",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x10",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x20",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x40",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x80",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)",
+        "PEBS": "1",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
+        "EventName": "BR_MISP_RETIRED.RET",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.",
+        "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC5",
         "UMask": "0x20",
-        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
+        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "CounterMask": "2",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "CounterMask": "3",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventCode": "0xCC",
+        "UMask": "0x20",
+        "BriefDescription": "Count cases of saving new LBR",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
-        "CounterMask": "4",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "PublicDescription": "This event counts cases of saving new LBR records by hardware. This assumes proper enabling of LBRs and takes into account LBR filtering done by the LBR_SELECT register.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xe6",
@@ -1090,328 +1423,5 @@
         "EventName": "BACLEARS.ANY",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "Counter": "2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
-        "CounterMask": "8",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
-        "CounterMask": "2",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x4",
-        "BriefDescription": "Total execution stalls.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
-        "CounterMask": "4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0xc",
-        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
-        "Counter": "2",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
-        "CounterMask": "12",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x5",
-        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
-        "CounterMask": "5",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "UMask": "0x6",
-        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
-        "Counter": "0,1,2,3",
-        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
-        "CounterMask": "6",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "EventCode": "0xC3",
-        "UMask": "0x1",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "Counter": "0,1,2,3",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "CounterMask": "1",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_4_UOPS",
-        "CounterMask": "4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "Invert": "1",
-        "EventCode": "0x5E",
-        "UMask": "0x1",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "Counter": "0,1,2,3",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "CounterMask": "1",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_ACTIVE",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles per thread when uops are executed in port 0",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles per thread when uops are executed in port 1",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles per thread when uops are executed in port 2",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles per thread when uops are executed in port 3",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x10",
-        "BriefDescription": "Cycles per thread when uops are executed in port 4",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x20",
-        "BriefDescription": "Cycles per thread when uops are executed in port 5",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x40",
-        "BriefDescription": "Cycles per thread when uops are executed in port 6",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x80",
-        "BriefDescription": "Cycles per thread when uops are executed in port 7",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7",
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA0",
-        "UMask": "0x3",
-        "BriefDescription": "Micro-op dispatches cancelled due to insufficient SIMD physical register file read ports",
-        "Counter": "0,1,2,3",
-        "EventName": "UOP_DISPATCHES_CANCELLED.SIMD_PRF",
-        "PublicDescription": "This event counts the number of micro-operations cancelled after they were dispatched from the scheduler to the execution units when the total number of physical register read ports across all dispatch ports exceeds the read bandwidth of the physical register file.  The SIMD_PRF subevent applies to the following instructions: VDPPS, DPPS, VPCMPESTRI, PCMPESTRI, VPCMPESTRM, PCMPESTRM, VFMADD*, VFMADDSUB*, VFMSUB*, VMSUBADD*, VFNMADD*, VFNMSUB*.  See the Broadwell Optimization Guide for more information.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x00",
-        "UMask": "0x2",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "Counter": "Fixed counter 2",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x0",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x0D",
-        "UMask": "0x3",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "Counter": "0,1,2,3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "AnyThread": "1",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "CounterMask": "2",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "CounterMask": "3",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "CounterMask": "4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "Invert": "1",
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x2",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json
index 5ce8b67ba076..7d79c707c6d1 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/virtual-memory.json
@@ -45,6 +45,16 @@
     },
     {
         "EventCode": "0x08",
+        "UMask": "0xe",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "Errata": "BDM69",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -73,6 +83,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x08",
+        "UMask": "0x60",
+        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x49",
         "UMask": "0x1",
         "BriefDescription": "Store misses in all DTLB levels that cause page walks",
@@ -118,6 +137,16 @@
     },
     {
         "EventCode": "0x49",
+        "UMask": "0xe",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "Errata": "BDM69",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -146,6 +175,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x49",
+        "UMask": "0x60",
+        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x4F",
         "UMask": "0x10",
         "BriefDescription": "Cycle count for an Extended Page table walk.",
@@ -201,6 +239,16 @@
     },
     {
         "EventCode": "0x85",
+        "UMask": "0xe",
+        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "Errata": "BDM69",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -229,6 +277,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x85",
+        "UMask": "0x60",
+        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xAE",
         "UMask": "0x1",
         "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
@@ -250,60 +307,60 @@
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x21",
-        "BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
+        "UMask": "0x12",
+        "BriefDescription": "Number of DTLB page walker hits in the L2.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x12",
-        "BriefDescription": "Number of DTLB page walker hits in the L2.",
+        "UMask": "0x14",
+        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x22",
-        "BriefDescription": "Number of ITLB page walker hits in the L2.",
+        "UMask": "0x18",
+        "BriefDescription": "Number of DTLB page walker hits in Memory.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x14",
-        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP.",
+        "UMask": "0x21",
+        "BriefDescription": "Number of ITLB page walker hits in the L1+FB.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x24",
-        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
+        "UMask": "0x22",
+        "BriefDescription": "Number of ITLB page walker hits in the L2.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L2",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x18",
-        "BriefDescription": "Number of DTLB page walker hits in Memory.",
+        "UMask": "0x24",
+        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
         "Errata": "BDM69, BDM98",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
@@ -327,62 +384,5 @@
         "PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "UMask": "0xe",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "Errata": "BDM69",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "UMask": "0x60",
-        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "UMask": "0xe",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "Errata": "BDM69",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "UMask": "0x60",
-        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "UMask": "0xe",
-        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "Errata": "BDM69",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "UMask": "0x60",
-        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
-        "Counter": "0,1,2,3",
-        "EventName": "ITLB_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/cache.json b/tools/perf/pmu-events/arch/x86/goldmont/cache.json
index 4e02e1e5e70d..f8bbe087b0f8 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/cache.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/cache.json
@@ -1,6 +1,26 @@
 [
     {
         "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts memory requests originating from the core that miss in the L2 cache.",
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache request misses"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts memory requests originating from the core that reference a cache line in the L2 cache.",
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4f",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache requests"
+    },
+    {
+        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of demand and prefetch transactions that the L2 XQ rejects due to a full or near full condition which likely indicates back pressure from the intra-die interconnect (IDI) fabric. The XQ may reject transactions from the L2Q (non-cacheable requests), L2 misses and L2 write-back victims.",
         "EventCode": "0x30",
         "Counter": "0,1,2,3",
@@ -11,120 +31,119 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand and L1 prefetcher requests rejected by the L2Q due to a full or nearly full condition which likely indicates back pressure from L2Q. It also counts requests that would have gone directly to the XQ, but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link. The L2Q may also reject transactions from a core to insure fairness between cores, or to delay a core's dirty eviction when the address conflicts with incoming external snoops.",
+        "PublicDescription": "Counts the number of demand and L1 prefetcher requests rejected by the L2Q due to a full or nearly full condition which likely indicates back pressure from L2Q. It also counts requests that would have gone directly to the XQ, but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link. The L2Q may also reject transactions from a core to ensure fairness between cores, or to delay a core's dirty eviction when the address conflicts with incoming external snoops.",
         "EventCode": "0x31",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
         "EventName": "CORE_REJECT_L2Q.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Requests rejected by the L2Q "
+        "BriefDescription": "Requests rejected by the L2Q"
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts memory requests originating from the core that reference a cache line in the L2 cache.",
-        "EventCode": "0x2E",
+        "PublicDescription": "Counts when a modified (dirty) cache line is evicted from the data L1 cache and needs to be written back to memory.  No count will occur if the evicted line is clean, and hence does not require a writeback.",
+        "EventCode": "0x51",
         "Counter": "0,1,2,3",
-        "UMask": "0x4f",
-        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "UMask": "0x1",
+        "EventName": "DL1.DIRTY_EVICTION",
         "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache requests"
+        "BriefDescription": "L1 Cache evictions for dirty data"
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts memory requests originating from the core that miss in the L2 cache.",
-        "EventCode": "0x2E",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.",
+        "EventCode": "0x86",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "UMask": "0x2",
+        "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache request misses"
+        "BriefDescription": "Cycles code-fetch stalled due to an outstanding ICache miss."
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts cycles that an ICache miss is outstanding, and instruction fetch is stalled.  That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes, while an Icache miss outstanding.  Note this event is not the same as cycles to retrieve an instruction due to an Icache miss.  Rather, it is the part of the Instruction Cache (ICache) miss time where no bytes are available for the decoder.",
-        "EventCode": "0x86",
+        "EventCode": "0xB7",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Cycles where code-fetch is stalled and an ICache miss is outstanding.  This is not the same as an ICache Miss."
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts the number of load uops retired.",
+        "PublicDescription": "Counts locked memory uops retired.  This includes regular locks and bus locks. (To specifically count bus locks only, see the Offcore response event.)  A locked access is one with a lock prefix, or an exchange to memory.  See the SDM for a complete description of which memory load accesses are locks.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "UMask": "0x21",
+        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired (Precise event capable)"
+        "BriefDescription": "Locked load uops retired (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts the number of store uops retired.",
+        "PublicDescription": "Counts load uops retired where the data requested spans a 64 byte cache line boundary.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "UMask": "0x41",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired (Precise event capable)"
+        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts the number of memory uops retired that is either a loads or a store or both.",
+        "PublicDescription": "Counts store uops retired where the data requested spans a 64 byte cache line boundary.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x83",
-        "EventName": "MEM_UOPS_RETIRED.ALL",
+        "UMask": "0x42",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired (Precise event capable)"
+        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts locked memory uops retired.  This includes \"regular\" locks and bus locks. (To specifically count bus locks only, see the Offcore response event.)  A locked access is one with a lock prefix, or an exchange to memory.  See the SDM for a complete description of which memory load accesses are locks.",
+        "PublicDescription": "Counts memory uops retired where the data requested spans a 64 byte cache line boundary.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x21",
-        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "UMask": "0x43",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Locked load uops retired (Precise event capable)"
+        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts load uops retired where the data requested spans a 64 byte cache line boundary.",
+        "PublicDescription": "Counts the number of load uops retired.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "UMask": "0x81",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Load uops retired (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts store uops retired where the data requested spans a 64 byte cache line boundary.",
+        "PublicDescription": "Counts the number of store uops retired.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
+        "UMask": "0x82",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Store uops retired (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts memory uops retired where the data requested spans a 64 byte cache line boundary.",
+        "PublicDescription": "Counts the number of memory uops retired that is either a loads or a store or both.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x43",
-        "EventName": "MEM_UOPS_RETIRED.SPLIT",
+        "UMask": "0x83",
+        "EventName": "MEM_UOPS_RETIRED.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Memory uops retired (Precise event capable)"
     },
     {
         "PEBS": "2",
@@ -140,24 +159,24 @@
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts load uops retired that miss the L1 data cache.",
+        "PublicDescription": "Counts load uops retired that hit in the L2 cache.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "UMask": "0x2",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts load uops retired that hit in the L2 cache.",
+        "PublicDescription": "Counts load uops retired that miss the L1 data cache.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "UMask": "0x8",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
     },
     {
         "PEBS": "2",
@@ -205,24 +224,20 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts when a modified (dirty) cache line is evicted from the data L1 cache and needs to be written back to memory.  No count will occur if the evicted line is clean, and hence does not require a writeback.",
-        "EventCode": "0x51",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "DL1.DIRTY_EVICTION",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L1 Cache evictions for dirty data"
-    },
-    {
-        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
+        "MSRValue": "0x40000032b7 ",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
+        "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)"
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x36000032b7 ",
         "Counter": "0,1,2,3",
@@ -234,6 +249,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x10000032b7 ",
         "Counter": "0,1,2,3",
@@ -245,6 +262,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x04000032b7 ",
         "Counter": "0,1,2,3",
@@ -256,6 +275,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x02000032b7 ",
         "Counter": "0,1,2,3",
@@ -267,6 +288,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x00000432b7 ",
         "Counter": "0,1,2,3",
@@ -278,6 +301,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x00000132b7 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000022 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000022 ",
         "Counter": "0,1,2,3",
@@ -289,6 +340,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000000022 ",
         "Counter": "0,1,2,3",
@@ -300,6 +353,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000022 ",
         "Counter": "0,1,2,3",
@@ -311,6 +366,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000022 ",
         "Counter": "0,1,2,3",
@@ -322,6 +379,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040022 ",
         "Counter": "0,1,2,3",
@@ -333,6 +392,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010022 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600003091",
         "Counter": "0,1,2,3",
@@ -344,6 +431,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000003091",
         "Counter": "0,1,2,3",
@@ -355,6 +444,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400003091",
         "Counter": "0,1,2,3",
@@ -366,6 +457,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200003091",
         "Counter": "0,1,2,3",
@@ -377,6 +470,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000043091",
         "Counter": "0,1,2,3",
@@ -388,6 +483,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000013091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000003010 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600003010 ",
         "Counter": "0,1,2,3",
@@ -399,6 +522,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000003010 ",
         "Counter": "0,1,2,3",
@@ -410,6 +535,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400003010 ",
         "Counter": "0,1,2,3",
@@ -421,6 +548,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200003010 ",
         "Counter": "0,1,2,3",
@@ -432,6 +561,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000043010 ",
         "Counter": "0,1,2,3",
@@ -443,6 +574,47 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000013010 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000008000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x3600008000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.ANY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000008000 ",
         "Counter": "0,1,2,3",
@@ -454,6 +626,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400008000 ",
         "Counter": "0,1,2,3",
@@ -465,6 +639,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200008000 ",
         "Counter": "0,1,2,3",
@@ -476,6 +652,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000048000 ",
         "Counter": "0,1,2,3",
@@ -487,6 +665,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000018000 ",
         "Counter": "0,1,2,3",
@@ -498,6 +678,21 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000004800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600004800 ",
         "Counter": "0,1,2,3",
@@ -509,6 +704,47 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000004800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0400004800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200004800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000044800 ",
         "Counter": "0,1,2,3",
@@ -520,6 +756,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000014800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000004000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600004000 ",
         "Counter": "0,1,2,3",
@@ -531,6 +795,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000004000 ",
         "Counter": "0,1,2,3",
@@ -542,6 +808,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400004000 ",
         "Counter": "0,1,2,3",
@@ -553,6 +821,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200004000 ",
         "Counter": "0,1,2,3",
@@ -564,6 +834,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000044000 ",
         "Counter": "0,1,2,3",
@@ -575,6 +847,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000014000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000002000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600002000 ",
         "Counter": "0,1,2,3",
@@ -586,6 +886,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000002000 ",
         "Counter": "0,1,2,3",
@@ -597,6 +899,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400002000 ",
         "Counter": "0,1,2,3",
@@ -608,6 +912,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200002000 ",
         "Counter": "0,1,2,3",
@@ -619,6 +925,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000042000 ",
         "Counter": "0,1,2,3",
@@ -630,6 +938,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000012000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000001000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600001000 ",
         "Counter": "0,1,2,3",
@@ -641,6 +977,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000001000 ",
         "Counter": "0,1,2,3",
@@ -652,6 +990,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400001000 ",
         "Counter": "0,1,2,3",
@@ -663,6 +1003,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200001000 ",
         "Counter": "0,1,2,3",
@@ -674,6 +1016,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000041000 ",
         "Counter": "0,1,2,3",
@@ -685,6 +1029,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000011000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000800 ",
         "Counter": "0,1,2,3",
@@ -696,6 +1068,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000000800 ",
         "Counter": "0,1,2,3",
@@ -707,6 +1081,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000800 ",
         "Counter": "0,1,2,3",
@@ -718,6 +1094,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000800 ",
         "Counter": "0,1,2,3",
@@ -729,6 +1107,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040800 ",
         "Counter": "0,1,2,3",
@@ -740,6 +1120,99 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000400 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x3600000400 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.ANY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000400 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0400000400 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000400 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040400 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests that hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000010400 ",
         "Counter": "0,1,2,3",
@@ -751,6 +1224,112 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x3600000200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.ANY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0400000200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000100 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000100 ",
         "Counter": "0,1,2,3",
@@ -762,6 +1341,86 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000100 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0400000100 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000100 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040100 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010100 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000080 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000080 ",
         "Counter": "0,1,2,3",
@@ -773,6 +1432,86 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000080 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0400000080 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000080 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040080 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010080 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000020 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000020 ",
         "Counter": "0,1,2,3",
@@ -784,6 +1523,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000000020 ",
         "Counter": "0,1,2,3",
@@ -795,6 +1536,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000020 ",
         "Counter": "0,1,2,3",
@@ -806,6 +1549,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000020 ",
         "Counter": "0,1,2,3",
@@ -817,6 +1562,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040020 ",
         "Counter": "0,1,2,3",
@@ -828,6 +1575,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010020 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000010 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000010 ",
         "Counter": "0,1,2,3",
@@ -839,6 +1614,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000000010 ",
         "Counter": "0,1,2,3",
@@ -850,6 +1627,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000010 ",
         "Counter": "0,1,2,3",
@@ -861,6 +1640,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000010 ",
         "Counter": "0,1,2,3",
@@ -872,6 +1653,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040010 ",
         "Counter": "0,1,2,3",
@@ -883,6 +1666,34 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010010 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000008 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000008 ",
         "Counter": "0,1,2,3",
@@ -894,6 +1705,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000000008 ",
         "Counter": "0,1,2,3",
@@ -905,6 +1718,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000008 ",
         "Counter": "0,1,2,3",
@@ -916,6 +1731,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000008 ",
         "Counter": "0,1,2,3",
@@ -927,6 +1744,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040008 ",
         "Counter": "0,1,2,3",
@@ -938,6 +1757,21 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010008 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x4000000004 ",
         "Counter": "0,1,2,3",
@@ -949,6 +1783,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000004 ",
         "Counter": "0,1,2,3",
@@ -960,6 +1796,21 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000004 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000004 ",
         "Counter": "0,1,2,3",
@@ -971,6 +1822,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000004 ",
         "Counter": "0,1,2,3",
@@ -982,6 +1835,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040004 ",
         "Counter": "0,1,2,3",
@@ -993,6 +1848,21 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010004 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x4000000002 ",
         "Counter": "0,1,2,3",
@@ -1004,6 +1874,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000002 ",
         "Counter": "0,1,2,3",
@@ -1015,6 +1887,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000000002 ",
         "Counter": "0,1,2,3",
@@ -1026,6 +1900,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000002 ",
         "Counter": "0,1,2,3",
@@ -1037,6 +1913,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000002 ",
         "Counter": "0,1,2,3",
@@ -1048,6 +1926,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040002 ",
         "Counter": "0,1,2,3",
@@ -1059,6 +1939,21 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010002 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x4000000001 ",
         "Counter": "0,1,2,3",
@@ -1070,6 +1965,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600000001 ",
         "Counter": "0,1,2,3",
@@ -1081,6 +1978,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x1000000001 ",
         "Counter": "0,1,2,3",
@@ -1092,6 +1991,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0400000001 ",
         "Counter": "0,1,2,3",
@@ -1103,6 +2004,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0200000001 ",
         "Counter": "0,1,2,3",
@@ -1114,6 +2017,8 @@
         "Offcore": "1"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x0000040001 ",
         "Counter": "0,1,2,3",
@@ -1123,5 +2028,18 @@
         "SampleAfterValue": "100007",
         "BriefDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache.",
         "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010001 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/memory.json b/tools/perf/pmu-events/arch/x86/goldmont/memory.json
index ac8b0d365a19..690cebd12a94 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/memory.json
@@ -1,15 +1,5 @@
 [
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts machine clears due to memory ordering issues.  This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved - as another core is in the process of modifying the data.",
-        "EventCode": "0xC3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Machine clears due to memory ordering issue"
-    },
-    {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
         "PublicDescription": "Counts when a memory load of a uop spans a page boundary (a split) is retired.",
@@ -30,5 +20,275 @@
         "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "Store uops that split a page (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears due to memory ordering issues.  This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved as another core is in the process of modifying the data.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Machine clears due to memory ordering issue"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x20000032b7 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000022 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000003010 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000008000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000004800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000004000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000002000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000001000 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000800 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000400 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000200 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000100 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000080 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000020 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000010 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000008 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000004 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000002 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x2000000001 ",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address.",
+        "Offcore": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/other.json b/tools/perf/pmu-events/arch/x86/goldmont/other.json
index df25ca9542f1..959cadd7cb0e 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/other.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/other.json
@@ -1,23 +1,23 @@
 [
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend.  Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable.   Note that uops must be available for consumption in order for this event to fire.  If a uop is not available (Instruction Queue is empty), this event will not count.",
-        "EventCode": "0xCA",
+        "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events.",
+        "EventCode": "0x86",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
+        "UMask": "0x0",
+        "EventName": "FETCH_STALL.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend"
+        "BriefDescription": "Cycles code-fetch stalled due to any reason."
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows).   Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
-        "EventCode": "0xCA",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss.  Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
+        "EventCode": "0x86",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
+        "UMask": "0x1",
+        "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Unfilled issue slots per cycle to recover"
+        "BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss."
     },
     {
         "CollectPEBSRecord": "1",
@@ -30,14 +30,44 @@
         "BriefDescription": "Unfilled issue slots per cycle"
     },
     {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend.  Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable.   Note that uops must be available for consumption in order for this event to fire.  If a uop is not available (Instruction Queue is empty), this event will not count.",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows).   Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle to recover"
+    },
+    {
         "CollectPEBSRecord": "2",
         "PublicDescription": "Counts hardware interrupts received by the processor.",
         "EventCode": "0xCB",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "HW_INTERRUPTS.RECEIVED",
+        "SampleAfterValue": "203",
+        "BriefDescription": "Hardware interrupts received"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of core cycles during which interrupts are masked (disabled). Increments by 1 each core cycle that EFLAGS.IF is 0, regardless of whether interrupts are pending or not.",
+        "EventCode": "0xCB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "HW_INTERRUPTS.MASKED",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Hardware interrupts received (Precise event capable)"
+        "BriefDescription": "Cycles hardware interrupts are masked"
     },
     {
         "CollectPEBSRecord": "2",
@@ -47,6 +77,6 @@
         "UMask": "0x4",
         "EventName": "HW_INTERRUPTS.PENDING_AND_MASKED",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Cycles pending interrupts are masked (Precise event capable)"
+        "BriefDescription": "Cycles pending interrupts are masked"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
index 07f00041f56f..254788af8ab6 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
@@ -1,168 +1,136 @@
 [
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts branch instructions retired for all branch types.  This is an architectural performance event.",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired branch instructions (Precise event capable)"
-    },
-    {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x7e",
-        "EventName": "BR_INST_RETIRED.JCC",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired conditional branch instructions (Precise event capable)"
+        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 0",
+        "UMask": "0x1",
+        "EventName": "INST_RETIRED.ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired (Fixed event)"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0xfe",
-        "EventName": "BR_INST_RETIRED.TAKEN_JCC",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)"
+        "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when core is not halted  (Fixed event)"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts near CALL branch instructions retired.",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0xf9",
-        "EventName": "BR_INST_RETIRED.CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired near call instructions (Precise event capable)"
+        "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 2",
+        "UMask": "0x3",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when core is not halted  (Fixed event)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts near relative CALL branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time.  The forward might occur subsequently when the data is available.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0xfd",
-        "EventName": "BR_INST_RETIRED.REL_CALL",
+        "UMask": "0x1",
+        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired near relative call instructions (Precise event capable)"
+        "BriefDescription": "Loads blocked due to store data not ready (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts near indirect CALL branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0xfb",
-        "EventName": "BR_INST_RETIRED.IND_CALL",
+        "UMask": "0x2",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired near indirect call instructions (Precise event capable)"
+        "BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts near return branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0xf7",
-        "EventName": "BR_INST_RETIRED.RETURN",
+        "UMask": "0x4",
+        "EventName": "LD_BLOCKS.4K_ALIAS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired near return instructions (Precise event capable)"
+        "BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0xeb",
-        "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "UMask": "0x8",
+        "EventName": "LD_BLOCKS.UTLB_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)"
+        "BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts far branch instructions retired.  This includes far jump, far call and return, and Interrupt call and return.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0xbf",
-        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "UMask": "0x10",
+        "EventName": "LD_BLOCKS.ALL_BLOCK",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired far branch instructions (Precise event capable)"
+        "BriefDescription": "Loads blocked (Precise event capable)"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
-        "EventCode": "0xC5",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine.  This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
+        "EventCode": "0x0E",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired mispredicted branch instructions (Precise event capable)"
-    },
-    {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
-        "EventCode": "0xC5",
-        "Counter": "0,1,2,3",
-        "UMask": "0x7e",
-        "EventName": "BR_MISP_RETIRED.JCC",
+        "EventName": "UOPS_ISSUED.ANY",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)"
+        "BriefDescription": "Uops issued to the back end per cycle"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
-        "EventCode": "0xC5",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Core cycles when core is not halted.  This event uses a (_P)rogrammable general purpose performance counter.",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xfe",
-        "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)"
+        "UMask": "0x0",
+        "EventName": "CPU_CLK_UNHALTED.CORE_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when core is not halted"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
-        "EventCode": "0xC5",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Reference cycles when core is not halted.  This event uses a programmable general purpose performance counter.",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xfb",
-        "EventName": "BR_MISP_RETIRED.IND_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)"
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when core is not halted"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
-        "EventCode": "0xC5",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound.  When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources.  When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks.  However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all.  Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots.  These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots.  A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock.  The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
+        "EventCode": "0x9C",
         "Counter": "0,1,2,3",
-        "UMask": "0xf7",
-        "EventName": "BR_MISP_RETIRED.RETURN",
+        "UMask": "0x0",
+        "EventName": "UOPS_NOT_DELIVERED.ANY",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired mispredicted near return instructions (Precise event capable)"
+        "BriefDescription": "Uops requested but not-delivered to the back-end per cycle"
     },
     {
         "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
-        "EventCode": "0xC5",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers.  This is an architectural performance event.  This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable:  The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event.  Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
+        "EventCode": "0xC0",
         "Counter": "0,1,2,3",
-        "UMask": "0xeb",
-        "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call. (Precise event capable)"
+        "UMask": "0x0",
+        "EventName": "INST_RETIRED.ANY_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired (Precise event capable)"
     },
     {
         "PEBS": "2",
@@ -187,8 +155,40 @@
         "BriefDescription": "MS uops retired (Precise event capable)"
     },
     {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of floating point divide uops retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "UOPS_RETIRED.FPDIV",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Floating point divide uops retired. (Precise Event Capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of integer divide uops retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "UOPS_RETIRED.IDIV",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Integer divide uops retired. (Precise Event Capable)"
+    },
+    {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel? architecture processors.",
+        "PublicDescription": "Counts machine clears for any reason.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "MACHINE_CLEARS.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "All machine clears"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -217,217 +217,239 @@
         "BriefDescription": "Machine clears due to memory disambiguation"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts machine clears for any reason.",
-        "EventCode": "0xC3",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts branch instructions retired for all branch types.  This is an architectural performance event.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
-        "EventName": "MACHINE_CLEARS.ALL",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "All machine clears"
+        "BriefDescription": "Retired branch instructions (Precise event capable)"
     },
     {
         "PEBS": "2",
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers.  This is an architectural performance event.  This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable:  The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event.  Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
-        "EventCode": "0xC0",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "INST_RETIRED.ANY_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Instructions retired (Precise event capable)"
+        "UMask": "0x7e",
+        "EventName": "BR_INST_RETIRED.JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired conditional branch instructions (Precise event capable)"
     },
     {
+        "PEBS": "2",
         "CollectPEBSRecord": "1",
-        "PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound.  When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources.  When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks.  However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all.  Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots.  These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots.  A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock.  The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
-        "EventCode": "0x9C",
+        "PublicDescription": "Counts the number of taken branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "UOPS_NOT_DELIVERED.ANY",
+        "UMask": "0x80",
+        "EventName": "BR_INST_RETIRED.ALL_TAKEN_BRANCHES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Uops requested but not-delivered to the back-end per cycle"
+        "BriefDescription": "Retired taken branch instructions (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine.  This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
-        "EventCode": "0x0E",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts far branch instructions retired.  This includes far jump, far call and return, and Interrupt call and return.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "UOPS_ISSUED.ANY",
+        "UMask": "0xbf",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Uops issued to the back end per cycle"
+        "BriefDescription": "Retired far branch instructions (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts core cycles if either divide unit is busy.",
-        "EventCode": "0xCD",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "CYCLES_DIV_BUSY.ALL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles a divider is busy"
+        "UMask": "0xeb",
+        "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts core cycles the integer divide unit is busy.",
-        "EventCode": "0xCD",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near return branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLES_DIV_BUSY.IDIV",
+        "UMask": "0xf7",
+        "EventName": "BR_INST_RETIRED.RETURN",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Cycles the integer divide unit is busy"
+        "BriefDescription": "Retired near return instructions (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts core cycles the floating point divide unit is busy.",
-        "EventCode": "0xCD",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near CALL branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CYCLES_DIV_BUSY.FPDIV",
+        "UMask": "0xf9",
+        "EventName": "BR_INST_RETIRED.CALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Cycles the FP divide unit is busy"
+        "BriefDescription": "Retired near call instructions (Precise event capable)"
     },
     {
-        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
-        "UMask": "0x1",
-        "EventName": "INST_RETIRED.ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Instructions retired (Fixed event)"
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near indirect CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfb",
+        "EventName": "BR_INST_RETIRED.IND_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near indirect call instructions (Precise event capable)"
     },
     {
-        "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when core is not halted  (Fixed event)"
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near relative CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfd",
+        "EventName": "BR_INST_RETIRED.REL_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near relative call instructions (Precise event capable)"
     },
     {
-        "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
-        "UMask": "0x3",
-        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when core is not halted  (Fixed event)"
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfe",
+        "EventName": "BR_INST_RETIRED.TAKEN_JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Core cycles when core is not halted.  This event uses a (_P)rogrammable general purpose performance counter.",
-        "EventCode": "0x3C",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
-        "EventName": "CPU_CLK_UNHALTED.CORE_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when core is not halted"
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted branch instructions (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Reference cycles when core is not halted.  This event uses a (_P)rogrammable general purpose performance counter.",
-        "EventCode": "0x3C",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when core is not halted"
+        "UMask": "0x7e",
+        "EventName": "BR_MISP_RETIRED.JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call,  Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
-        "EventCode": "0xE6",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BACLEARS.ALL",
+        "UMask": "0xeb",
+        "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
         "SampleAfterValue": "200003",
-        "BriefDescription": "BACLEARs asserted for any branch type"
+        "BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call. (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts BACLEARS on return instructions.",
-        "EventCode": "0xE6",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "BACLEARS.RETURN",
+        "UMask": "0xf7",
+        "EventName": "BR_MISP_RETIRED.RETURN",
         "SampleAfterValue": "200003",
-        "BriefDescription": "BACLEARs asserted for return branch"
+        "BriefDescription": "Retired mispredicted near return instructions (Precise event capable)"
     },
     {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
-        "EventCode": "0xE6",
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "BACLEARS.COND",
+        "UMask": "0xfb",
+        "EventName": "BR_MISP_RETIRED.IND_CALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "BACLEARs asserted for conditional branch"
+        "BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)"
     },
     {
         "PEBS": "2",
         "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
-        "EventCode": "0x03",
+        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "LD_BLOCKS.ALL_BLOCK",
+        "UMask": "0xfe",
+        "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads blocked (Precise event capable)"
+        "BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
-        "EventCode": "0x03",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles if either divide unit is busy.",
+        "EventCode": "0xCD",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "LD_BLOCKS.UTLB_MISS",
+        "UMask": "0x0",
+        "EventName": "CYCLES_DIV_BUSY.ALL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles a divider is busy"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles the integer divide unit is busy.",
+        "EventCode": "0xCD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CYCLES_DIV_BUSY.IDIV",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)"
+        "BriefDescription": "Cycles the integer divide unit is busy"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
-        "EventCode": "0x03",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles the floating point divide unit is busy.",
+        "EventCode": "0xCD",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "EventName": "CYCLES_DIV_BUSY.FPDIV",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)"
+        "BriefDescription": "Cycles the FP divide unit is busy"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time.  The forward might occur subsequently when the data is available.",
-        "EventCode": "0x03",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call,  Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
+        "EventCode": "0xE6",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "EventName": "BACLEARS.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads blocked due to store data not ready (Precise event capable)"
+        "BriefDescription": "BACLEARs asserted for any branch type"
     },
     {
-        "PEBS": "2",
-        "CollectPEBSRecord": "2",
-        "PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
-        "EventCode": "0x03",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts BACLEARS on return instructions.",
+        "EventCode": "0xE6",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "LD_BLOCKS.4K_ALIAS",
+        "UMask": "0x8",
+        "EventName": "BACLEARS.RETURN",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)"
+        "BriefDescription": "BACLEARs asserted for return branch"
     },
     {
-        "PEBS": "2",
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of taken branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
+        "EventCode": "0xE6",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "BR_INST_RETIRED.ALL_TAKEN_BRANCHES",
+        "UMask": "0x10",
+        "EventName": "BACLEARS.COND",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Retired taken branch instructions (Precise event capable)"
+        "BriefDescription": "BACLEARs asserted for conditional branch"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
index 3202c4478836..9805198d3f5f 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
@@ -1,6 +1,36 @@
 [
     {
         "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts every core cycle when a Data-side (walks due to a data operation) page walk is in progress.",
+        "EventCode": "0x05",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "PAGE_WALKS.D_SIDE_CYCLES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Duration of D-side page-walks in cycles"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts every core cycle when a Instruction-side (walks due to an instruction fetch) page walk is in progress.",
+        "EventCode": "0x05",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "PAGE_WALKS.I_SIDE_CYCLES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Duration of I-side pagewalks in cycles"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts every core cycle a page-walk is in progress due to either a data memory operation or an instruction fetch.",
+        "EventCode": "0x05",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "EventName": "PAGE_WALKS.CYCLES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Duration of page-walks in cycles"
+    },
+    {
+        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) for a linear address of an instruction fetch.  It counts when new translation are filled into the ITLB.  The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
         "EventCode": "0x81",
         "Counter": "0,1,2,3",
@@ -41,35 +71,5 @@
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "SampleAfterValue": "200003",
         "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts every core cycle when a Data-side (walks due to a data operation) page walk is in progress.",
-        "EventCode": "0x05",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "PAGE_WALKS.D_SIDE_CYCLES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Duration of D-side page-walks in cycles"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts every core cycle when a Instruction-side (walks due to an instruction fetch) page walk is in progress.",
-        "EventCode": "0x05",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "PAGE_WALKS.I_SIDE_CYCLES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Duration of I-side pagewalks in cycles"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts every core cycle a page-walk is in progress due to either a data memory operation or an instruction fetch.",
-        "EventCode": "0x05",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "PAGE_WALKS.CYCLES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Duration of page-walks in cycles"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
new file mode 100644
index 000000000000..b4791b443a66
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
@@ -0,0 +1,1453 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts memory requests originating from the core that miss in the L2 cache.",
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache request misses"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts memory requests originating from the core that reference a cache line in the L2 cache.",
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4f",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache requests"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand and prefetch transactions that the L2 XQ rejects due to a full or near full condition which likely indicates back pressure from the intra-die interconnect (IDI) fabric. The XQ may reject transactions from the L2Q (non-cacheable requests), L2 misses and L2 write-back victims.",
+        "EventCode": "0x30",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "L2_REJECT_XQ.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests rejected by the XQ"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of demand and L1 prefetcher requests rejected by the L2Q due to a full or nearly full condition which likely indicates back pressure from L2Q. It also counts requests that would have gone directly to the XQ, but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link. The L2Q may also reject transactions from a core to insure fairness between cores, or to delay a core's dirty eviction when the address conflicts with incoming external snoops.",
+        "EventCode": "0x31",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CORE_REJECT_L2Q.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests rejected by the L2Q"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts when a modified (dirty) cache line is evicted from the data L1 cache and needs to be written back to memory.  No count will occur if the evicted line is clean, and hence does not require a writeback.",
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DL1.REPLACEMENT",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L1 Cache evictions for dirty data"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.",
+        "EventCode": "0x86",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to an outstanding ICache miss."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "EventCode": "0xB7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts locked memory uops retired.  This includes regular locks and bus locks. (To specifically count bus locks only, see the Offcore response event.)  A locked access is one with a lock prefix, or an exchange to memory.  See the SDM for a complete description of which memory load accesses are locks.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x21",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Locked load uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired where the data requested spans a 64 byte cache line boundary.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts store uops retired where the data requested spans a 64 byte cache line boundary.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x42",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts memory uops retired where the data requested spans a 64 byte cache line boundary.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x43",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of load uops retired.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x81",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of store uops retired.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x82",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Store uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of memory uops retired that is either a loads or a store or both.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x83",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that hit the L1 data cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that hit in the L2 cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that miss the L1 data cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that miss in the L2 cache.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired where the cache line containing the data was in the modified state of another core or modules cache (HITM).  More specifically, this means that when the load address was checked by other caching agents (typically another processor) in the system, one of those caching agents indicated that they had a dirty copy of the data.  Loads that obtain a HITM response incur greater latency than most is typical for a load.  In addition, since HITM indicates that some other processor had this data in its cache, it implies that the data was shared between processors, or potentially was a lock or semaphore value.  This event is useful for locating sharing, false sharing, and contended locks.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts memory load uops retired where the data is retrieved from the WCB (or fill buffer), indicating that the load found its data while that data was in the process of being brought into the L1 cache.  Typically a load will receive this indication when some other load or prefetch missed the L1 cache and was in the process of retrieving the cache line containing the data, but that process had not yet finished (and written the data back to the cache). For example, consider load X and Y, both referencing the same cache line that is not in the L1 cache.  If load X misses cache first, it obtains and WCB (or fill buffer) and begins the process of requesting the data.  When load Y requests the data, it will either hit the WCB, or the L1 cache, depending on exactly what time the request to Y occurs.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts memory load uops retired where the data is retrieved from DRAM.  Event is counted at retirement, so the speculative loads are ignored.  A memory load can hit (or miss) the L1 cache, hit (or miss) the L2 cache, hit DRAM, hit in the WCB or receive a HITM response.",
+        "EventCode": "0xD1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand cacheable data reads of full cache lines outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000008",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000020",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts bus lock and split lock requests outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000400",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts bus lock and split lock requests outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000011000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000041000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200001000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000001000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache lines requests by software prefetch instructions outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000001000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000012000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000042000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200002000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000002000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000002000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000014800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000044800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200004800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000004800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000004800",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000018000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the uncore subsystem outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts requests to the uncore subsystem outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000013010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000043010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200003010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000003010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000003010",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000013091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000043091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data reads (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000003091",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data reads (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000010022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0000040022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x0200000022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x1000000022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x4000000022",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x00000132b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) have any transaction responses from the uncore subsystem.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x00000432b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) hit the L2 cache.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x02000032b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x10000032b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HITM_OTHER_CORE",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
+        "Offcore": "1"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
+        "EventCode": "0xB7",
+        "MSRValue": "0x40000032b7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
+        "PDIR_COUNTER": "na",
+        "MSRIndex": "0x1a6",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) outstanding, per cycle, from the time of the L2 miss to when any response is received.",
+        "Offcore": "1"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/frontend.json b/tools/perf/pmu-events/arch/x86/goldmontplus/frontend.json
new file mode 100644
index 000000000000..a7878965ceab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/frontend.json
@@ -0,0 +1,62 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line and that cache line is in the ICache (hit).  The event strives to count on a cache line basis, so that multiple accesses which hit in a single cache line count as one ICACHE.HIT.  Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.HIT",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "References per ICache line that are available in the ICache (hit). This event counts differently than Intel processors based on Silvermont microarchitecture"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache)  for one or more bytes in an ICache Line and that cache line is not in the ICache (miss).  The event strives to count on a cache line basis, so that multiple accesses which miss in a single cache line count as one ICACHE.MISS.  Specifically, the event counts when straight line code crosses the cache line boundary, or when a branch target is to a new line, and that cache line is not in the ICache. This event counts differently than Intel processors based on Silvermont microarchitecture.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.MISSES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "References per ICache line that are not available in the ICache (miss). This event counts differently than Intel processors based on Silvermont microarchitecture"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts requests to the Instruction Cache (ICache) for one or more bytes in an ICache Line.  The event strives to count on a cache line basis, so that multiple fetches to a single cache line count as one ICACHE.ACCESS.  Specifically, the event counts when accesses from straight line code crosses the cache line boundary, or when a branch target is to a new line.\r\nThis event counts differently than Intel processors based on Silvermont microarchitecture.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ICACHE.ACCESSES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "References per ICache line. This event counts differently than Intel processors based on Silvermont microarchitecture"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times the Microcode Sequencer (MS) starts a flow of uops from the MSROM. It does not count every time a uop is read from the MSROM.  The most common case that this counts is when a micro-coded instruction is encountered by the front end of the machine.  Other cases include when an instruction encounters a fault, trap, or microcode assist of any sort that initiates a flow of uops.  The event will count MS startups for uops that are speculative, and subsequently cleared by branch mispredict or a machine clear.",
+        "EventCode": "0xE7",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MS_DECODED.MS_ENTRY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "MS decode starts"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times the prediction (from the predecode cache) for instruction length is incorrect.",
+        "EventCode": "0xE9",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DECODE_RESTRICTION.PREDECODE_WRONG",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Decode restrictions due to predicting wrong instruction length"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/memory.json
new file mode 100644
index 000000000000..91e0815f3ffb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/memory.json
@@ -0,0 +1,38 @@
+[
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts when a memory load of a uop spans a page boundary (a split) is retired.",
+        "EventCode": "0x13",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops that split a page (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts when a memory store of a uop spans a page boundary (a split) is retired.",
+        "EventCode": "0x13",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Store uops that split a page (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears due to memory ordering issues.  This occurs when a snoop request happens and the machine is uncertain if memory ordering will be preserved - as another core is in the process of modifying the data.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machine clears due to memory ordering issue"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/other.json b/tools/perf/pmu-events/arch/x86/goldmontplus/other.json
new file mode 100644
index 000000000000..b860374418ab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/other.json
@@ -0,0 +1,98 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events.",
+        "EventCode": "0x86",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "FETCH_STALL.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to any reason."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss.  Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
+        "EventCode": "0x86",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles the code-fetch stalls and an ITLB miss is outstanding."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend due to either a full resource  in the backend (RESOURCE_FULL) or due to the processor recovering from some event (RECOVERY).",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed because of a full resource in the backend.  Including but not limited to resources such as the Re-order Buffer (ROB), reservation stations (RS), load/store buffers, physical registers, or any other needed machine resource that is currently unavailable.   Note that uops must be available for consumption in order for this event to fire.  If a uop is not available (Instruction Queue is empty), this event will not count.",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RESOURCE_FULL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle because of a full resource in the backend"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of issue slots per core cycle that were not consumed by the backend because allocation is stalled waiting for a mispredicted jump to retire or other branch-like conditions (e.g. the event is relevant during certain microcode flows).   Counts all issue slots blocked while within this window including slots where uops were not available in the Instruction Queue.",
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ISSUE_SLOTS_NOT_CONSUMED.RECOVERY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Unfilled issue slots per cycle to recover"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts hardware interrupts received by the processor.",
+        "EventCode": "0xCB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.RECEIVED",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "203",
+        "BriefDescription": "Hardware interrupts received"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of core cycles during which interrupts are masked (disabled). Increments by 1 each core cycle that EFLAGS.IF is 0, regardless of whether interrupts are pending or not.",
+        "EventCode": "0xCB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.MASKED",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles hardware interrupts are masked"
+    },
+    {
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts core cycles during which there are pending interrupts, but interrupts are masked (EFLAGS.IF = 0).",
+        "EventCode": "0xCB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.PENDING_AND_MASKED",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles pending interrupts are masked"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
new file mode 100644
index 000000000000..ccf1aed69197
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
@@ -0,0 +1,544 @@
+[
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 0",
+        "UMask": "0x1",
+        "PEBScounters": "32",
+        "EventName": "INST_RETIRED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired (Fixed event)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "PEBScounters": "33",
+        "EventName": "CPU_CLK_UNHALTED.CORE",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when core is not halted  (Fixed event)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 2",
+        "UMask": "0x3",
+        "PEBScounters": "34",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when core is not halted  (Fixed event)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts a load blocked from using a store forward, but did not occur because the store data was not available at the right time.  The forward might occur subsequently when the data is available.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked due to store data not ready (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts a load blocked from using a store forward because of an address/size mismatch, only one of the loads blocked from each store will be counted.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked due to store forward restriction (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts loads that block because their address modulo 4K matches a pending store.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.4K_ALIAS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked because address has 4k partial address false dependence (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts loads blocked because they are unable to find their physical address in the micro TLB (UTLB).",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.UTLB_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked because address in not in the UTLB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts anytime a load that retires is blocked for any reason.",
+        "EventCode": "0x03",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "LD_BLOCKS.ALL_BLOCK",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Loads blocked (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts uops issued by the front end and allocated into the back end of the machine.  This event counts uops that retire as well as uops that were speculatively executed but didn't retire. The sort of speculative uops that might be counted includes, but is not limited to those uops issued in the shadow of a miss-predicted branch, those uops that are inserted during an assist (such as for a denormal floating point result), and (previously allocated) uops that might be canceled during a machine clear.",
+        "EventCode": "0x0E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Uops issued to the back end per cycle"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Core cycles when core is not halted.  This event uses a (_P)rogrammable general purpose performance counter.",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.CORE_P",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when core is not halted"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Reference cycles when core is not halted.  This event uses a (_P)rogrammable general purpose performance counter.",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when core is not halted"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "This event used to measure front-end inefficiencies. I.e. when front-end of the machine is not delivering uops to the back-end and the back-end has is not stalled. This event can be used to identify if the machine is truly front-end bound.  When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into uops in machine understandable format and putting them into a uop queue to be consumed by back end. The back-end then takes these uops, allocates the required resources.  When all resources are ready, uops are executed. If the back-end is not ready to accept uops from the front-end, then we do not want to count these as front-end bottlenecks.  However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more uops. This event counts only when back-end is requesting more uops and front-end is not able to provide them. When 3 uops are requested and no uops are delivered, the event counts 3. When 3 are requested, and only 1 is delivered, the event counts 2. When only 2 are delivered, the event counts 1. Alternatively stated, the event will not count if 3 uops are delivered, or if the back end is stalled and not requesting any uops at all.  Counts indicate missed opportunities for the front-end to deliver a uop to the back end. Some examples of conditions that cause front-end efficiencies are: ICache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth. Known Issues: Some uops require multiple allocation slots.  These uops will not be charged as a front end 'not delivered' opportunity, and will be regarded as a back end problem. For example, the INC instruction has one uop that requires 2 issue slots.  A stream of INC instructions will not count as UOPS_NOT_DELIVERED, even though only one instruction can be issued per clock.  The low uop issue rate for a stream of INC instructions is considered to be a back end issue.",
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_NOT_DELIVERED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Uops requested but not-delivered to the back-end per cycle"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The event continues counting during hardware interrupts, traps, and inside interrupt handlers.  This is an architectural performance event.  This event uses a (_P)rogrammable general purpose performance counter. *This event is Precise Event capable:  The EventingRIP field in the PEBS record is precise to the address of the instruction which caused the event.  Note: Because PEBS records can be collected only on IA32_PMC0, only one event can use the PEBS facility at a time.",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts INST_RETIRED.ANY using the Reduced Skid PEBS feature that reduces the shadow in which events aren't counted allowing for a more unbiased distribution of samples across instructions retired.",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "INST_RETIRED.PREC_DIST",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Instructions retired - using Reduced Skid PEBS feature"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts uops which retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts uops retired that are from the complex flows issued by the micro-sequencer (MS).  Counts both the uops from a micro-coded instruction, and the uops that might be generated from a micro-coded assist.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.MS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "MS uops retired (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of floating point divide uops retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.FPDIV",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Floating point divide uops retired (Precise Event Capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of integer divide uops retired.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.IDIV",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Integer divide uops retired (Precise Event Capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears for any reason.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "All machine clears"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Self-Modifying Code detected"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears due to floating point (FP) operations needing assists.  For instance, if the result was a floating point denormal, the hardware clears the pipeline and reissues uops to produce the correct IEEE compliant denormal result.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.FP_ASSIST",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machine clears due to FP assists"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts machine clears due to memory disambiguation.  Memory disambiguation happens when a load which has been issued conflicts with a previous unretired store in the pipeline whose address was not known at issue time, but is later resolved to be the same as the load address.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.DISAMBIGUATION",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machine clears due to memory disambiguation"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times that the machines clears due to a page fault. Covers both I-side and D-side(Loads/Stores) page faults. A page fault occurs when either page is not present, or an access violation",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.PAGE_FAULT",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "Machines clear due to a page fault"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts branch instructions retired for all branch types.  This is an architectural performance event.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was taken and when it was not taken.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x7e",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired conditional branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts the number of taken branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_TAKEN_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired taken branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts far branch instructions retired.  This includes far jump, far call and return, and Interrupt call and return.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xbf",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired far branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near indirect call or near indirect jmp branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xeb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired instructions of near indirect Jmp or call (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near return branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf7",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near return instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf9",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near indirect CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.IND_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near indirect call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts near relative CALL branch instructions retired.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfd",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.REL_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired near relative call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were taken and does not count when the Jcc branch instruction were not taken.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfe",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.TAKEN_JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired conditional branch instructions that were taken (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted branch instructions retired including all branch types.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired, including both when the branch was supposed to be taken and when it was not supposed to be taken (but the processor predicted the opposite condition).",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x7e",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted conditional branch instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted branch instructions retired that were near indirect call or near indirect jmp, where the target address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xeb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted instructions of near indirect Jmp or near indirect call (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted near RET branch instructions retired, where the return address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf7",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted near return instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted near indirect CALL branch instructions retired, where the target address taken was not what the processor predicted.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfb",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.IND_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted near indirect call instructions (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts mispredicted retired Jcc (Jump on Conditional Code/Jump if Condition is Met) branch instructions retired that were supposed to be taken but the processor predicted that it would not be taken.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0xfe",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Retired mispredicted conditional branch instructions that were taken (Precise event capable)"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles if either divide unit is busy.",
+        "EventCode": "0xCD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CYCLES_DIV_BUSY.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles a divider is busy"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles the integer divide unit is busy.",
+        "EventCode": "0xCD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CYCLES_DIV_BUSY.IDIV",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles the integer divide unit is busy"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts core cycles the floating point divide unit is busy.",
+        "EventCode": "0xCD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "CYCLES_DIV_BUSY.FPDIV",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles the FP divide unit is busy"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times a BACLEAR is signaled for any reason, including, but not limited to indirect branch/call,  Jcc (Jump on Conditional Code/Jump if Condition is Met) branch, unconditional branch/call, and returns.",
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BACLEARS.ALL",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "BACLEARs asserted for any branch type"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts BACLEARS on return instructions.",
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BACLEARS.RETURN",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "BACLEARs asserted for return branch"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts BACLEARS on Jcc (Jump on Conditional Code/Jump if Condition is Met) branches.",
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "BACLEARS.COND",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "BACLEARs asserted for conditional branch"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
new file mode 100644
index 000000000000..0b53a3b0dfb8
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
@@ -0,0 +1,218 @@
+[
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 4K page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 2M or 4M page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data loads (including SW prefetches) whose address translations missed in all TLB levels and were mapped to 1GB pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1GB",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walk completed due to a demand load to a 1GB page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk occurring due to a load (demand data loads or SW prefetches). Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to a demand load every cycle."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 4K page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 2M or 4M page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1GB pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1GB",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to a demand data store to a 1GB page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk occurring due to a demand data store. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to a demand data store every cycle."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk only while traversing the Extended Page Table (EPT), and does not count during the rest of the translation.  The EPT is used for translating Guest-Physical Addresses to Physical Addresses for Virtual Machine Monitors (VMMs).  Average cycles per walk can be calculated by dividing the count by number of walks.",
+        "EventCode": "0x4F",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "EPT.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to walking the EPT every cycle"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) for a linear address of an instruction fetch.  It counts when new translation are filled into the ITLB.  The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
+        "EventCode": "0x81",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB.MISS",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "ITLB misses"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 4K page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 2M or 4M pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 2M or 4M page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts page walks completed due to instruction fetches whose address translations missed in the TLB and were mapped to 1GB pages.  The page walks can end with or without a page fault.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_1GB",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Page walk completed due to an instruction fetch in a 1GB page"
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts once per cycle for each page walk occurring due to an instruction fetch. Includes cycles spent traversing the Extended Page Table (EPT). Average cycles per walk can be calculated by dividing by the number of walks.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_PENDING",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Page walks outstanding due to an instruction fetch every cycle."
+    },
+    {
+        "CollectPEBSRecord": "1",
+        "PublicDescription": "Counts STLB flushes.  The TLBs are flushed on instructions like INVLPG and MOV to CR3.",
+        "EventCode": "0xBD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "TLB_FLUSHES.STLB_ANY",
+        "PDIR_COUNTER": "na",
+        "SampleAfterValue": "20003",
+        "BriefDescription": "STLB flushes"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts load uops retired that caused a DTLB miss.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x11",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts store uops retired that caused a DTLB miss.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x12",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+    },
+    {
+        "PEBS": "2",
+        "CollectPEBSRecord": "2",
+        "PublicDescription": "Counts uops retired that had a DTLB miss on load, store or either.  Note that when two distinct memory operations to the same page miss the DTLB, only one of them will be recorded as a DTLB miss.",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x13",
+        "PEBScounters": "0,1,2,3",
+        "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json
index bfb5ebf48c54..da4d6ddd4f92 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json
@@ -11,14 +11,34 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
+        "UMask": "0x22",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests that miss L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of instruction fetches that missed the L2 cache.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x24",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache misses when fetching instructions",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Demand requests that miss L2 cache.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x27",
         "Errata": "HSD78",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "BriefDescription": "Demand requests that miss L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -32,6 +52,48 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "All requests that missed L2.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3f",
+        "Errata": "HSD78",
+        "EventName": "L2_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "All requests that miss L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "Errata": "HSD78",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x42",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests that hit L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x44",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -73,6 +135,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Demand requests to L2 cache.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe7",
+        "Errata": "HSD78",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand requests to L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts all L2 HW prefetcher requests.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -83,6 +156,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "All requests to L2 cache.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0xff",
+        "Errata": "HSD78",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "All L2 requests",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Not rejected writebacks that hit L2 cache.",
         "EventCode": "0x27",
         "Counter": "0,1,2,3",
@@ -124,6 +208,27 @@
     },
     {
         "EventCode": "0x48",
+        "Counter": "2",
+        "UMask": "0x1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
+        "CounterMask": "1",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
+        "Counter": "2",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "CounterMask": "1",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "L1D_PEND_MISS.REQUEST_FB_FULL",
@@ -133,13 +238,13 @@
     },
     {
         "EventCode": "0x48",
-        "Counter": "2",
-        "UMask": "0x1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding.",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
         "CounterMask": "1",
-        "CounterHTOff": "2"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PublicDescription": "This event counts when new data lines are brought into the L1 Data cache, which cause other lines to be evicted from the cache.",
@@ -163,6 +268,28 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "Errata": "HSD78, HSD62, HSD61",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "Errata": "HSD78, HSD62, HSD61",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Offcore outstanding Demand code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
@@ -185,46 +312,35 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
+        "UMask": "0x4",
         "Errata": "HSD62, HSD61",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "HSD78, HSD62, HSD61",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "Errata": "HSD62, HSD61",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
-        "CounterMask": "1",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
+        "UMask": "0x8",
         "Errata": "HSD62, HSD61",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -289,6 +405,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xB7, 0xBB",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PEBS": "1",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
@@ -296,7 +421,7 @@
         "Errata": "HSD29, HSM30",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that miss the STLB.",
+        "BriefDescription": "Retired load uops that miss the STLB. (precise Event)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -308,7 +433,7 @@
         "Errata": "HSD29, HSM30",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that miss the STLB.",
+        "BriefDescription": "Retired store uops that miss the STLB. (precise Event)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1",
         "L1_Hit_Indication": "1"
@@ -321,31 +446,33 @@
         "Errata": "HSD76, HSD29, HSM30",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops with locked access.",
+        "BriefDescription": "Retired load uops with locked access. (precise Event)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x41",
         "Errata": "HSD29, HSM30",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x42",
         "Errata": "HSD29, HSM30",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1",
         "L1_Hit_Indication": "1"
@@ -358,19 +485,20 @@
         "Errata": "HSD29, HSM30",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "All retired load uops. (precise Event)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "This event counts all store uops retired. This is a precise event.",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x82",
         "Errata": "HSD29, HSM30",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "All retired store uops. (precise Event)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1",
         "L1_Hit_Indication": "1"
@@ -401,20 +529,20 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops with L3 cache hits as data sources.",
+        "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
+        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops missed L1 cache as data sources.",
+        "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
@@ -427,20 +555,18 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "Errata": "HSD29, HSM30",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops with L2 cache misses as data sources.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -477,25 +603,27 @@
     },
     {
         "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -513,14 +641,13 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.",
+        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
         "EventCode": "0xD3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "Errata": "HSD74, HSD29, HSD25, HSM30",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -665,6 +792,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "",
         "EventCode": "0xf4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -674,131 +802,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that hit L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x22",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that miss L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x44",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of instruction fetches that missed the L2 cache.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache misses when fetching instructions",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Demand requests that miss L2 cache.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x27",
-        "Errata": "HSD78",
-        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand requests that miss L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Demand requests to L2 cache.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe7",
-        "Errata": "HSD78",
-        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand requests to L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "All requests that missed L2.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3f",
-        "Errata": "HSD78",
-        "EventName": "L2_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "All requests that miss L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "All requests to L2 cache.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xff",
-        "Errata": "HSD78",
-        "EventName": "L2_RQSTS.REFERENCES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "All L2 requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "HSD78, HSD62, HSD61",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "2",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
+        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c8fff",
         "Counter": "0,1,2,3",
@@ -811,6 +815,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c07f7",
         "Counter": "0,1,2,3",
@@ -823,6 +828,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c07f7",
         "Counter": "0,1,2,3",
@@ -835,6 +841,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0244",
         "Counter": "0,1,2,3",
@@ -847,6 +854,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0122",
         "Counter": "0,1,2,3",
@@ -859,6 +867,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0122",
         "Counter": "0,1,2,3",
@@ -871,6 +880,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0091",
         "Counter": "0,1,2,3",
@@ -883,6 +893,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0091",
         "Counter": "0,1,2,3",
@@ -895,6 +906,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0200",
         "Counter": "0,1,2,3",
@@ -907,6 +919,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0100",
         "Counter": "0,1,2,3",
@@ -919,6 +932,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0080",
         "Counter": "0,1,2,3",
@@ -931,6 +945,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0040",
         "Counter": "0,1,2,3",
@@ -943,6 +958,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0020",
         "Counter": "0,1,2,3",
@@ -955,6 +971,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0010",
         "Counter": "0,1,2,3",
@@ -967,6 +984,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0004",
         "Counter": "0,1,2,3",
@@ -979,6 +997,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0004",
         "Counter": "0,1,2,3",
@@ -991,6 +1010,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0002",
         "Counter": "0,1,2,3",
@@ -1003,6 +1023,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0002",
         "Counter": "0,1,2,3",
@@ -1015,6 +1036,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0001",
         "Counter": "0,1,2,3",
@@ -1027,6 +1049,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04003c0001",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
index 1732fa49c6d2..f9843e5a9b42 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
@@ -20,6 +20,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.",
+        "EventCode": "0xC6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x7",
+        "EventName": "AVX_INSTS.ALL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores.  May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of X87 FP assists due to output values.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
@@ -69,15 +79,5 @@
         "BriefDescription": "Cycles with any input/output SSE or FP assist",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.",
-        "EventCode": "0xC6",
-        "Counter": "0,1,2,3",
-        "UMask": "0x7",
-        "EventName": "AVX_INSTS.ALL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores.  May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswell/frontend.json b/tools/perf/pmu-events/arch/x86/haswell/frontend.json
index 57a1ce46971f..c0a5bedcc15c 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/frontend.json
@@ -21,74 +21,43 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "IDQ.MS_MITE_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
+        "UMask": "0x4",
+        "EventName": "IDQ.MITE_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
+        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterMask": "1",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_CYCLES",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
-        "CounterMask": "1",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -135,6 +104,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
@@ -157,6 +136,38 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_SWITCHES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of uops delivered to IDQ from any path.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
@@ -195,6 +206,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "ICACHE.IFDATA_STALL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event count the number of undelivered (unallocated) uops from the Front-end to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. The Front-end can allocate up to 4 uops per cycle so this event can increment 0-4 times per cycle depending on the number of unallocated uops. This event is counted on a per-core basis.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
@@ -270,25 +290,5 @@
         "SampleAfterValue": "2000003",
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x80",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ICACHE.IFDATA_STALL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
new file mode 100644
index 000000000000..5ab5c78fe580
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
@@ -0,0 +1,158 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json
index aab981b42339..e5f9fa6655b3 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json
@@ -401,6 +401,7 @@
         "CounterHTOff": "3"
     },
     {
+        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc08fff",
         "Counter": "0,1,2,3",
@@ -413,6 +414,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01004007f7",
         "Counter": "0,1,2,3",
@@ -425,6 +427,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc007f7",
         "Counter": "0,1,2,3",
@@ -437,6 +440,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400244",
         "Counter": "0,1,2,3",
@@ -449,6 +453,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00244",
         "Counter": "0,1,2,3",
@@ -461,6 +466,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400122",
         "Counter": "0,1,2,3",
@@ -473,6 +479,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00122",
         "Counter": "0,1,2,3",
@@ -485,6 +492,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400091",
         "Counter": "0,1,2,3",
@@ -497,6 +505,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00091",
         "Counter": "0,1,2,3",
@@ -509,6 +518,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00200",
         "Counter": "0,1,2,3",
@@ -521,6 +531,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00100",
         "Counter": "0,1,2,3",
@@ -533,6 +544,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00080",
         "Counter": "0,1,2,3",
@@ -545,6 +557,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00040",
         "Counter": "0,1,2,3",
@@ -557,6 +570,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00020",
         "Counter": "0,1,2,3",
@@ -569,6 +583,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00010",
         "Counter": "0,1,2,3",
@@ -581,6 +596,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400004",
         "Counter": "0,1,2,3",
@@ -593,6 +609,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00004",
         "Counter": "0,1,2,3",
@@ -605,6 +622,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400002",
         "Counter": "0,1,2,3",
@@ -617,6 +635,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00002",
         "Counter": "0,1,2,3",
@@ -629,6 +648,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400001",
         "Counter": "0,1,2,3",
@@ -641,6 +661,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00001",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/haswell/other.json b/tools/perf/pmu-events/arch/x86/haswell/other.json
index 85d6a14baf9d..8a4d898d76c1 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/other.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/other.json
@@ -10,16 +10,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
-        "EventCode": "0x5C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPL_CYCLES.RING123",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x5C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -31,6 +21,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
+        "EventCode": "0x5C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPL_CYCLES.RING123",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
         "EventCode": "0x63",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
index 0099848607ad..a4dcfce4a512 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
@@ -2,33 +2,43 @@
     {
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "Errata": "HSD140, HSD143",
         "EventName": "INST_RETIRED.ANY",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. The penalty for blocked store forwarding is that the load must wait for the store to write its value to the cache before it can be issued.",
@@ -67,7 +77,19 @@
         "UMask": "0x3",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...)",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "EventCode": "0x0D",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "AnyThread": "1",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke)",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -82,6 +104,29 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x0E",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0x0E",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PublicDescription": "Number of flags-merge uops allocated. Such uops add delay.",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
@@ -112,35 +157,32 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0E",
-        "Invert": "1",
+        "EventCode": "0x14",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "UMask": "0x2",
+        "EventName": "ARITH.DIVIDER_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0E",
-        "Invert": "1",
+        "PublicDescription": "Counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+        "UMask": "0x0",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x14",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ARITH.DIVIDER_UOPS",
+        "UMask": "0x0",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -154,6 +196,38 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x3c",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -163,6 +237,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for S/W prefetch.",
         "EventCode": "0x4c",
         "Counter": "0,1,2,3",
@@ -233,6 +316,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5E",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts cycles where the decoder is stalled on an instruction with a length changing prefix (LCP).",
         "EventCode": "0x87",
         "Counter": "0,1,2,3",
@@ -409,6 +504,15 @@
     {
         "EventCode": "0x89",
         "Counter": "0,1,2,3",
+        "UMask": "0xa0",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x89",
+        "Counter": "0,1,2,3",
         "UMask": "0xc1",
         "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL",
         "SampleAfterValue": "200003",
@@ -445,6 +549,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles per core when uops are exectuted in port 0.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are executed in port 0.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles which a uop is dispatched on port 1 in this thread.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -455,6 +579,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles per core when uops are exectuted in port 1.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are executed in port 1.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles which a uop is dispatched on port 2 in this thread.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -465,6 +609,25 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles which a uop is dispatched on port 3 in this thread.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -475,6 +638,25 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles which a uop is dispatched on port 4 in this thread.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -485,6 +667,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles per core when uops are exectuted in port 4.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are executed in port 4.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles which a uop is dispatched on port 5 in this thread.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -495,6 +697,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles per core when uops are exectuted in port 5.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are executed in port 5.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles which a uop is dispatched on port 6 in this thread.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -505,6 +727,26 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles per core when uops are exectuted in port 6.",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are executed in port 6.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles which a uop is dispatched on port 7 in this thread.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
@@ -515,6 +757,25 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "AnyThread": "1",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles allocation is stalled due to resource related reason.",
         "EventCode": "0xA2",
         "Counter": "0,1,2,3",
@@ -566,17 +827,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.",
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with pending L1 cache miss loads.",
-        "CounterMask": "8",
-        "CounterHTOff": "2"
-    },
-    {
         "PublicDescription": "Cycles with pending memory loads. Set Cmask=2 to count cycle.",
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
@@ -594,7 +844,7 @@
         "UMask": "0x4",
         "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls",
+        "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.",
         "CounterMask": "4",
         "CounterHTOff": "0,1,2,3"
     },
@@ -621,6 +871,17 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.",
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with pending L1 cache miss loads.",
+        "CounterMask": "8",
+        "CounterHTOff": "2"
+    },
+    {
         "PublicDescription": "Execution stalls due to L1 data cache miss loads. Set Cmask=0CH.",
         "EventCode": "0xA3",
         "Counter": "2",
@@ -642,14 +903,23 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts total number of uops to be executed per-core each cycle.",
-        "EventCode": "0xB1",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CORE",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of uops executed on the core.",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -665,24 +935,127 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of instructions at retirement.",
-        "EventCode": "0xC0",
+        "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "Errata": "HSD11, HSD140",
-        "EventName": "INST_RETIRED.ANY_P",
+        "UMask": "0x1",
+        "Errata": "HSD144, HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "Errata": "HSD144, HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "Errata": "HSD144, HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "Errata": "HSD144, HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts total number of uops to be executed per-core each cycle.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "Errata": "HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of uops executed on the core.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
-        "EventCode": "0xC0",
+        "EventCode": "0xb1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "INST_RETIRED.X87",
+        "Errata": "HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions: Counts also flows that have several X87 or flows that use X87 uops in the exception handling.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "Errata": "HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "Errata": "HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "Errata": "HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "Errata": "HSD30, HSM31",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of instructions at retirement.",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "Errata": "HSD11, HSD140",
+        "EventName": "INST_RETIRED.ANY_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -698,6 +1071,16 @@
         "CounterHTOff": "1"
     },
     {
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "EventCode": "0xC0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "INST_RETIRED.X87",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions: Counts also flows that have several X87 or flows that use X87 uops in the exception handling.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
@@ -709,7 +1092,6 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.",
         "EventCode": "0xC2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -720,17 +1102,6 @@
         "Data_LA": "1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.",
-        "EventCode": "0xC2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
@@ -765,6 +1136,16 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Retirement slots used.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -774,6 +1155,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear.  Machine clears can have a significant performance impact if they are happening frequently.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
@@ -793,8 +1185,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Branch instructions at retirement.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of conditional branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -814,18 +1215,27 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Branch instructions at retirement.",
+        "PEBS": "1",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "UMask": "0x2",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PEBS": "2",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
         "SampleAfterValue": "400009",
         "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of near return instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
@@ -846,7 +1256,6 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of near taken branches retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -866,14 +1275,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "EventCode": "0xC4",
+        "PublicDescription": "Mispredicted branch instructions at retirement.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "UMask": "0x0",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
         "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
@@ -886,16 +1295,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Mispredicted branch instructions at retirement.",
-        "EventCode": "0xC5",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All mispredicted macro branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PEBS": "2",
         "PublicDescription": "This event counts all mispredicted branch instructions retired. This is a precise event.",
         "EventCode": "0xC5",
@@ -903,121 +1302,11 @@
         "UMask": "0x4",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted macro branch instructions retired. ",
+        "BriefDescription": "Mispredicted macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Count cases of saving new LBR records by hardware.",
-        "EventCode": "0xCC",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Count cases of saving new LBR",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Thread cycles when thread is not in halt state",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x89",
-        "Counter": "0,1,2,3",
-        "UMask": "0xa0",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "AnyThread": "1",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PEBS": "1",
-        "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.",
         "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -1027,51 +1316,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "HSD144, HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "HSD144, HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "HSD144, HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
+        "PublicDescription": "Count cases of saving new LBR records by hardware.",
+        "EventCode": "0xCC",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "HSD144, HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "UMask": "0x20",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Count cases of saving new LBR",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PublicDescription": "Number of front end re-steers due to BPU misprediction.",
@@ -1082,248 +1334,5 @@
         "SampleAfterValue": "100003",
         "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x5E",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 0.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 1.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 2.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 3.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 4.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 5.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 6.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 7.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "EventCode": "0x0D",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke)",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "HSD30, HSM31",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json b/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json
index ce80a08d0f08..777b500a5c9f 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json
@@ -39,6 +39,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts cycles when the  page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
@@ -69,6 +79,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Number of cache load STLB hits. No page walk.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x60",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
@@ -118,6 +138,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts cycles when the  page miss handler (PMH) is servicing page walks caused by DTLB store misses.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
@@ -148,6 +178,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x60",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "DTLB store misses with low part of linear-to-physical address translation missed.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
@@ -206,6 +246,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Completed page walks in ITLB of any page size.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Misses in all ITLB levels that cause completed page walks",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts cycles when the  page miss handler (PMH) is servicing page walks caused by ITLB misses.",
         "EventCode": "0x85",
         "Counter": "0,1,2,3",
@@ -236,6 +286,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "ITLB misses that hit STLB. No page walk.",
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x60",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.",
         "EventCode": "0xae",
         "Counter": "0,1,2,3",
@@ -256,41 +316,45 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.",
+        "PublicDescription": "Number of DTLB page walker loads that hit in the L2.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x21",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
+        "UMask": "0x12",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of ITLB page walker hits in the L1+FB",
+        "BriefDescription": "Number of DTLB page walker hits in the L2",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Number of DTLB page walker loads that hit in the L3.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1",
+        "UMask": "0x14",
+        "Errata": "HSD25",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
+        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Number of DTLB page walker loads from memory.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1",
+        "UMask": "0x18",
+        "Errata": "HSD25",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
+        "BriefDescription": "Number of DTLB page walker hits in Memory",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of DTLB page walker loads that hit in the L2.",
+        "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x12",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
+        "UMask": "0x21",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of DTLB page walker hits in the L2",
+        "BriefDescription": "Number of ITLB page walker hits in the L1+FB",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -304,43 +368,43 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Number of ITLB page walker loads that hit in the L3.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2",
+        "UMask": "0x24",
+        "Errata": "HSD25",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
+        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Number of ITLB page walker loads from memory.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2",
+        "UMask": "0x28",
+        "Errata": "HSD25",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
+        "BriefDescription": "Number of ITLB page walker hits in Memory",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of DTLB page walker loads that hit in the L3.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x14",
-        "Errata": "HSD25",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
+        "UMask": "0x41",
+        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of ITLB page walker loads that hit in the L3.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "Errata": "HSD25",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
+        "UMask": "0x42",
+        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -355,41 +419,37 @@
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x84",
-        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3",
+        "UMask": "0x48",
+        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of DTLB page walker loads from memory.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "Errata": "HSD25",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
+        "UMask": "0x81",
+        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of DTLB page walker hits in Memory",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of ITLB page walker loads from memory.",
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x28",
-        "Errata": "HSD25",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
+        "UMask": "0x82",
+        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of ITLB page walker hits in Memory",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
         "Counter": "0,1,2,3",
-        "UMask": "0x48",
-        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY",
+        "UMask": "0x84",
+        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -420,65 +480,5 @@
         "SampleAfterValue": "100003",
         "BriefDescription": "STLB flush attempts",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of cache load STLB hits. No page walk.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x60",
-        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
-        "EventCode": "0x49",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
-        "EventCode": "0x49",
-        "Counter": "0,1,2,3",
-        "UMask": "0x60",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Completed page walks in ITLB of any page size.",
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Misses in all ITLB levels that cause completed page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "ITLB misses that hit STLB. No page walk.",
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x60",
-        "EventName": "ITLB_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/cache.json b/tools/perf/pmu-events/arch/x86/haswellx/cache.json
index f1bae0817a6f..b2fbd617306a 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/cache.json
@@ -12,12 +12,32 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "UMask": "0x22",
+        "BriefDescription": "RFO requests that miss L2 cache",
         "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x24",
+        "BriefDescription": "L2 cache misses when fetching instructions",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "PublicDescription": "Number of instruction fetches that missed the L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x27",
+        "BriefDescription": "Demand requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
         "Errata": "HSD78",
-        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "PublicDescription": "Demand requests that miss L2 cache.",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -33,6 +53,48 @@
     },
     {
         "EventCode": "0x24",
+        "UMask": "0x3f",
+        "BriefDescription": "All requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.MISS",
+        "Errata": "HSD78",
+        "PublicDescription": "All requests that missed L2.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x41",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "Errata": "HSD78",
+        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x42",
+        "BriefDescription": "RFO requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x44",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
         "UMask": "0x50",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
         "Counter": "0,1,2,3",
@@ -74,6 +136,17 @@
     },
     {
         "EventCode": "0x24",
+        "UMask": "0xe7",
+        "BriefDescription": "Demand requests to L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "Errata": "HSD78",
+        "PublicDescription": "Demand requests to L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
         "UMask": "0xf8",
         "BriefDescription": "Requests from L2 hardware prefetchers",
         "Counter": "0,1,2,3",
@@ -83,6 +156,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x24",
+        "UMask": "0xff",
+        "BriefDescription": "All L2 requests",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "Errata": "HSD78",
+        "PublicDescription": "All requests to L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x27",
         "UMask": "0x50",
         "BriefDescription": "Not rejected writebacks that hit L2 cache",
@@ -124,6 +208,27 @@
     },
     {
         "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
+        "Counter": "2",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "Counter": "2",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "AnyThread": "1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
         "UMask": "0x2",
         "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch. HWP are e.",
         "Counter": "0,1,2,3",
@@ -133,13 +238,13 @@
     },
     {
         "EventCode": "0x48",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles with L1D load Misses outstanding.",
-        "Counter": "2",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
         "CounterMask": "1",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x51",
@@ -164,6 +269,28 @@
     },
     {
         "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "Errata": "HSD78, HSD62, HSD61",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
+        "Errata": "HSD78, HSD62, HSD61",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
         "UMask": "0x2",
         "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "Counter": "0,1,2,3",
@@ -186,23 +313,23 @@
     },
     {
         "EventCode": "0x60",
-        "UMask": "0x8",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "UMask": "0x4",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "CounterMask": "1",
         "Errata": "HSD62, HSD61",
-        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "UMask": "0x8",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "CounterMask": "1",
-        "Errata": "HSD78, HSD62, HSD61",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "Errata": "HSD62, HSD61",
+        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -218,17 +345,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x60",
-        "UMask": "0x4",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "CounterMask": "1",
-        "Errata": "HSD62, HSD61",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x63",
         "UMask": "0x2",
         "BriefDescription": "Cycles when L1D is locked",
@@ -289,9 +405,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load uops that miss the STLB.",
+        "BriefDescription": "Retired load uops that miss the STLB. (precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -303,20 +428,20 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store uops that miss the STLB.",
+        "BriefDescription": "Retired store uops that miss the STLB. (precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
         "Errata": "HSD29, HSM30",
-        "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
+        "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load uops with locked access.",
+        "BriefDescription": "Retired load uops with locked access. (precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -328,32 +453,34 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "Errata": "HSD29, HSM30",
+        "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "Errata": "HSD29, HSM30",
-        "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
+        "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
+        "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "All retired load uops. (precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -365,14 +492,15 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "All retired store uops. (precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "Errata": "HSD29, HSM30",
-        "SampleAfterValue": "2000003",
         "L1_Hit_Indication": "1",
+        "PublicDescription": "This event counts all store uops retired. This is a precise event.",
+        "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -402,13 +530,13 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
+        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "Retired load uops with L3 cache hits as data sources.",
+        "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
@@ -421,20 +549,19 @@
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "Errata": "HSM30",
-        "PublicDescription": "Retired load uops missed L1 cache as data sources.",
+        "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x10",
-        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops with L2 cache misses as data sources.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "Errata": "HSD29, HSM30",
-        "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
@@ -447,7 +574,6 @@
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS",
         "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -478,24 +604,26 @@
     {
         "EventCode": "0xD2",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
+        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
+        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
@@ -514,20 +642,19 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x1",
-        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "Errata": "HSD74, HSD29, HSD25, HSM30",
-        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.",
+        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
+        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -539,7 +666,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
+        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -551,7 +678,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x20",
-        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
+        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -706,135 +833,11 @@
         "BriefDescription": "Split locks in SQ",
         "Counter": "0,1,2,3",
         "EventName": "SQ_MISC.SPLIT_LOCK",
+        "PublicDescription": "",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
-        "UMask": "0x42",
-        "BriefDescription": "RFO requests that hit L2 cache",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x22",
-        "BriefDescription": "RFO requests that miss L2 cache",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x44",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x24",
-        "BriefDescription": "L2 cache misses when fetching instructions",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Number of instruction fetches that missed the L2 cache.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x27",
-        "BriefDescription": "Demand requests that miss L2 cache",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "Errata": "HSD78",
-        "PublicDescription": "Demand requests that miss L2 cache.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0xe7",
-        "BriefDescription": "Demand requests to L2 cache",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "Errata": "HSD78",
-        "PublicDescription": "Demand requests to L2 cache.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0x3f",
-        "BriefDescription": "All requests that miss L2 cache",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.MISS",
-        "Errata": "HSD78",
-        "PublicDescription": "All requests that missed L2.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "UMask": "0xff",
-        "BriefDescription": "All L2 requests",
-        "Counter": "0,1,2,3",
-        "EventName": "L2_RQSTS.REFERENCES",
-        "Errata": "HSD78",
-        "PublicDescription": "All requests to L2 cache.",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x60",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "CounterMask": "6",
-        "Errata": "HSD78, HSD62, HSD61",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "Counter": "2",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "AnyThread": "1",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0x48",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "Counter": "0,1,2,3",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
@@ -843,6 +846,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -855,6 +859,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -867,6 +872,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -879,6 +885,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -891,6 +898,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -903,6 +911,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -915,6 +924,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -927,6 +937,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -939,6 +950,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -951,6 +963,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -963,6 +976,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -975,6 +989,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -987,6 +1002,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -999,6 +1015,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1011,6 +1028,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1023,6 +1041,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1035,6 +1054,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1047,6 +1067,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1059,6 +1080,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1071,6 +1093,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json b/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json
index 6282aed6e090..bc08cc1f2f7e 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json
@@ -20,6 +20,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xC6",
+        "UMask": "0x7",
+        "BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores.  May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.",
+        "Counter": "0,1,2,3",
+        "EventName": "AVX_INSTS.ALL",
+        "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xCA",
         "UMask": "0x2",
         "BriefDescription": "Number of X87 assists due to output value.",
@@ -69,15 +79,5 @@
         "PublicDescription": "Cycles with any input/output SSE* or FP assists.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xC6",
-        "UMask": "0x7",
-        "BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores.  May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.",
-        "Counter": "0,1,2,3",
-        "EventName": "AVX_INSTS.ALL",
-        "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/frontend.json b/tools/perf/pmu-events/arch/x86/haswellx/frontend.json
index 2d0c7aac1e61..a4d9f1fcf940 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/frontend.json
@@ -22,72 +22,41 @@
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x10",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_DSB_UOPS",
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x20",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_MITE_UOPS",
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
+        "EventName": "IDQ.MITE_CYCLES",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "UMask": "0x8",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MITE_CYCLES",
+        "EventName": "IDQ.DSB_CYCLES",
         "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+        "UMask": "0x10",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_CYCLES",
-        "CounterMask": "1",
+        "EventName": "IDQ.MS_DSB_UOPS",
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -136,6 +105,16 @@
     },
     {
         "EventCode": "0x79",
+        "UMask": "0x20",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
         "UMask": "0x24",
         "BriefDescription": "Cycles MITE is delivering 4 Uops",
         "Counter": "0,1,2,3",
@@ -158,6 +137,38 @@
     },
     {
         "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_SWITCHES",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
         "UMask": "0x3c",
         "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
@@ -195,6 +206,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x80",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE.IFDATA_STALL",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x9C",
         "UMask": "0x1",
         "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
@@ -270,25 +290,5 @@
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "EventCode": "0x79",
-        "UMask": "0x30",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_SWITCHES",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x80",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.",
-        "Counter": "0,1,2,3",
-        "EventName": "ICACHE.IFDATA_STALL",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
new file mode 100644
index 000000000000..5ab5c78fe580
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -0,0 +1,158 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/memory.json b/tools/perf/pmu-events/arch/x86/haswellx/memory.json
index 0886cc000d22..56b0f24b8029 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/memory.json
@@ -409,6 +409,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -421,6 +422,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -433,6 +435,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -445,6 +448,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -457,6 +461,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -469,6 +474,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -481,6 +487,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -493,6 +500,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -505,6 +513,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -517,6 +526,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -529,6 +539,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -541,6 +552,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -553,6 +565,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -565,6 +578,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -577,6 +591,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -589,6 +604,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -601,6 +617,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -613,6 +630,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -625,6 +643,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -637,6 +656,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -649,6 +669,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -661,6 +682,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -673,6 +695,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -685,6 +708,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -697,6 +721,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -709,6 +734,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -721,6 +747,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -733,6 +760,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/other.json b/tools/perf/pmu-events/arch/x86/haswellx/other.json
index 4e1b6ce96ca3..800e65df31bc 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/other.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/other.json
@@ -10,16 +10,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5C",
-        "UMask": "0x2",
-        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
-        "Counter": "0,1,2,3",
-        "EventName": "CPL_CYCLES.RING123",
-        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EdgeDetect": "1",
         "EventCode": "0x5C",
         "UMask": "0x1",
@@ -31,6 +21,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5C",
+        "UMask": "0x2",
+        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "Counter": "0,1,2,3",
+        "EventName": "CPL_CYCLES.RING123",
+        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x63",
         "UMask": "0x1",
         "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
index c3a163d34bd7..8a18bfe9e3e4 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
@@ -3,32 +3,42 @@
         "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
         "Errata": "HSD140, HSD143",
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x2",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "Fixed counter 1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "EventCode": "0x03",
@@ -63,7 +73,7 @@
     {
         "EventCode": "0x0D",
         "UMask": "0x3",
-        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...)",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
         "Counter": "0,1,2,3",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
         "CounterMask": "1",
@@ -72,6 +82,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x0D",
+        "UMask": "0x3",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke)",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "AnyThread": "1",
+        "CounterMask": "1",
+        "PublicDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x0E",
         "UMask": "0x1",
         "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
@@ -82,6 +104,29 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+        "AnyThread": "1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0x0E",
         "UMask": "0x10",
         "BriefDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive; added by GSR u-arch.",
@@ -112,34 +157,31 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
-        "EventCode": "0x0E",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
+        "EventCode": "0x14",
+        "UMask": "0x2",
+        "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
-        "CounterMask": "1",
+        "EventName": "ARITH.DIVIDER_UOPS",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
-        "EventCode": "0x0E",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
-        "AnyThread": "1",
-        "CounterMask": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "PublicDescription": "Counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x14",
-        "UMask": "0x2",
-        "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)",
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "0,1,2,3",
-        "EventName": "ARITH.DIVIDER_UOPS",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "AnyThread": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -154,6 +196,38 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x3c",
         "UMask": "0x2",
         "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
@@ -163,6 +237,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0x3C",
+        "UMask": "0x2",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x4c",
         "UMask": "0x1",
         "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch",
@@ -233,6 +316,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
+        "Invert": "1",
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "CounterMask": "1",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x87",
         "UMask": "0x1",
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
@@ -408,6 +503,15 @@
     },
     {
         "EventCode": "0x89",
+        "UMask": "0xa0",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x89",
         "UMask": "0xc1",
         "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
         "Counter": "0,1,2,3",
@@ -446,6 +550,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per core when uops are executed in port 0.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
+        "AnyThread": "1",
+        "PublicDescription": "Cycles per core when uops are exectuted in port 0.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x2",
         "BriefDescription": "Cycles per thread when uops are executed in port 1",
         "Counter": "0,1,2,3",
@@ -456,6 +580,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per core when uops are executed in port 1.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
+        "AnyThread": "1",
+        "PublicDescription": "Cycles per core when uops are exectuted in port 1.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x4",
         "BriefDescription": "Cycles per thread when uops are executed in port 2",
         "Counter": "0,1,2,3",
@@ -466,6 +610,25 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x8",
         "BriefDescription": "Cycles per thread when uops are executed in port 3",
         "Counter": "0,1,2,3",
@@ -476,6 +639,25 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x10",
         "BriefDescription": "Cycles per thread when uops are executed in port 4",
         "Counter": "0,1,2,3",
@@ -486,6 +668,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per core when uops are executed in port 4.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
+        "AnyThread": "1",
+        "PublicDescription": "Cycles per core when uops are exectuted in port 4.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x20",
         "BriefDescription": "Cycles per thread when uops are executed in port 5",
         "Counter": "0,1,2,3",
@@ -496,6 +698,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per core when uops are executed in port 5.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
+        "AnyThread": "1",
+        "PublicDescription": "Cycles per core when uops are exectuted in port 5.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x40",
         "BriefDescription": "Cycles per thread when uops are executed in port 6",
         "Counter": "0,1,2,3",
@@ -506,6 +728,26 @@
     },
     {
         "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per core when uops are executed in port 6.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
+        "AnyThread": "1",
+        "PublicDescription": "Cycles per core when uops are exectuted in port 6.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
         "UMask": "0x80",
         "BriefDescription": "Cycles per thread when uops are executed in port 7",
         "Counter": "0,1,2,3",
@@ -515,6 +757,25 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xA2",
         "UMask": "0x1",
         "BriefDescription": "Resource-related stall cycles",
@@ -567,17 +828,6 @@
     },
     {
         "EventCode": "0xA3",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles with pending L1 cache miss loads.",
-        "Counter": "2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
-        "CounterMask": "8",
-        "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
         "UMask": "0x2",
         "BriefDescription": "Cycles with pending memory loads.",
         "Counter": "0,1,2,3",
@@ -590,7 +840,7 @@
     {
         "EventCode": "0xA3",
         "UMask": "0x4",
-        "BriefDescription": "Total execution stalls",
+        "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.",
         "Counter": "0,1,2,3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE",
         "CounterMask": "4",
@@ -622,6 +872,17 @@
     },
     {
         "EventCode": "0xA3",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles with pending L1 cache miss loads.",
+        "Counter": "2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "CounterMask": "8",
+        "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
         "UMask": "0xc",
         "BriefDescription": "Execution stalls due to L1 data cache misses",
         "Counter": "2",
@@ -642,13 +903,22 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "UMask": "0x2",
-        "BriefDescription": "Number of uops executed on the core.",
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE",
-        "Errata": "HSD30, HSM31",
-        "PublicDescription": "Counts total number of uops to be executed per-core each cycle.",
+        "EventName": "LSD.CYCLES_ACTIVE",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterMask": "4",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -665,23 +935,126 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xC0",
-        "UMask": "0x0",
-        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
         "Counter": "0,1,2,3",
-        "EventName": "INST_RETIRED.ANY_P",
-        "Errata": "HSD11, HSD140",
-        "PublicDescription": "Number of instructions at retirement.",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "CounterMask": "1",
+        "Errata": "HSD144, HSD30, HSM31",
+        "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "CounterMask": "2",
+        "Errata": "HSD144, HSD30, HSM31",
+        "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterMask": "3",
+        "Errata": "HSD144, HSD30, HSM31",
+        "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "CounterMask": "4",
+        "Errata": "HSD144, HSD30, HSM31",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Number of uops executed on the core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE",
+        "Errata": "HSD30, HSM31",
+        "PublicDescription": "Counts total number of uops to be executed per-core each cycle.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC0",
+        "EventCode": "0xb1",
         "UMask": "0x2",
-        "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions: Counts also flows that have several X87 or flows that use X87 uops in the exception handling.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "INST_RETIRED.X87",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
+        "CounterMask": "1",
+        "Errata": "HSD30, HSM31",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterMask": "2",
+        "Errata": "HSD30, HSM31",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "CounterMask": "3",
+        "Errata": "HSD30, HSM31",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "CounterMask": "4",
+        "Errata": "HSD30, HSM31",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xb1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "Errata": "HSD30, HSM31",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC0",
+        "UMask": "0x0",
+        "BriefDescription": "Number of instructions retired. General Counter   - architectural event",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "Errata": "HSD11, HSD140",
+        "PublicDescription": "Number of instructions at retirement.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -698,6 +1071,16 @@
         "CounterHTOff": "1"
     },
     {
+        "EventCode": "0xC0",
+        "UMask": "0x2",
+        "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions: Counts also flows that have several X87 or flows that use X87 uops in the exception handling.",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.X87",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC1",
         "UMask": "0x40",
         "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
@@ -715,18 +1098,6 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.ALL",
-        "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC2",
-        "UMask": "0x2",
-        "BriefDescription": "Retirement slots used.",
-        "PEBS": "1",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -765,6 +1136,16 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Retirement slots used.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC3",
         "UMask": "0x1",
         "BriefDescription": "Cycles there was a Nuke. Account for both thread-specific and All Thread Nukes.",
@@ -774,6 +1155,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
+        "EventCode": "0xC3",
+        "UMask": "0x1",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "CounterMask": "1",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xC3",
         "UMask": "0x4",
         "BriefDescription": "Self-modifying code (SMC) detected.",
@@ -794,12 +1186,21 @@
     },
     {
         "EventCode": "0xC4",
+        "UMask": "0x0",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Branch instructions at retirement.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
         "UMask": "0x1",
         "BriefDescription": "Conditional branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "PublicDescription": "Counts the number of conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -815,13 +1216,23 @@
     },
     {
         "EventCode": "0xC4",
-        "UMask": "0x0",
+        "UMask": "0x2",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x4",
         "BriefDescription": "All (macro) branch instructions retired.",
+        "PEBS": "2",
         "Counter": "0,1,2,3",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Branch instructions at retirement.",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
         "SampleAfterValue": "400009",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xC4",
@@ -830,7 +1241,6 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts the number of near return instructions retired.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -851,7 +1261,6 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Number of near taken branches retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -866,14 +1275,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
-        "UMask": "0x4",
-        "BriefDescription": "All (macro) branch instructions retired.",
-        "PEBS": "2",
+        "EventCode": "0xC5",
+        "UMask": "0x0",
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
         "Counter": "0,1,2,3",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Mispredicted branch instructions at retirement.",
         "SampleAfterValue": "400009",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC5",
@@ -887,18 +1296,8 @@
     },
     {
         "EventCode": "0xC5",
-        "UMask": "0x0",
-        "BriefDescription": "All mispredicted macro branch instructions retired.",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Mispredicted branch instructions at retirement.",
-        "SampleAfterValue": "400009",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC5",
         "UMask": "0x4",
-        "BriefDescription": "Mispredicted macro branch instructions retired. ",
+        "BriefDescription": "Mispredicted macro branch instructions retired.",
         "PEBS": "2",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
@@ -907,171 +1306,24 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xCC",
-        "UMask": "0x20",
-        "BriefDescription": "Count cases of saving new LBR",
-        "Counter": "0,1,2,3",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
-        "PublicDescription": "Count cases of saving new LBR records by hardware.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x0",
-        "BriefDescription": "Thread cycles when thread is not in halt state",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "Counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x89",
-        "UMask": "0xa0",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
-        "Counter": "0,1,2,3",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 0.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 1.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 2.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 3.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x10",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 4.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x20",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 5.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x40",
-        "BriefDescription": "Cycles per core when uops are exectuted in port 6.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x80",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 7.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xC5",
         "UMask": "0x20",
         "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "CounterMask": "1",
-        "Errata": "HSD144, HSD30, HSM31",
-        "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "CounterMask": "2",
-        "Errata": "HSD144, HSD30, HSM31",
-        "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "CounterMask": "3",
-        "Errata": "HSD144, HSD30, HSM31",
-        "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventCode": "0xCC",
+        "UMask": "0x20",
+        "BriefDescription": "Count cases of saving new LBR",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
-        "CounterMask": "4",
-        "Errata": "HSD144, HSD30, HSM31",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "PublicDescription": "Count cases of saving new LBR records by hardware.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xe6",
@@ -1082,248 +1334,5 @@
         "PublicDescription": "Number of front end re-steers due to BPU misprediction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "EventCode": "0xC3",
-        "UMask": "0x1",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "Counter": "0,1,2,3",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "CounterMask": "1",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_ACTIVE",
-        "CounterMask": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA8",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_4_UOPS",
-        "CounterMask": "4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EdgeDetect": "1",
-        "Invert": "1",
-        "EventCode": "0x5E",
-        "UMask": "0x1",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "Counter": "0,1,2,3",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "CounterMask": "1",
-        "SampleAfterValue": "200003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles per thread when uops are executed in port 0.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles per thread when uops are executed in port 1.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x4",
-        "BriefDescription": "Cycles per thread when uops are executed in port 2.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x8",
-        "BriefDescription": "Cycles per thread when uops are executed in port 3.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x10",
-        "BriefDescription": "Cycles per thread when uops are executed in port 4.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x20",
-        "BriefDescription": "Cycles per thread when uops are executed in port 5.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x40",
-        "BriefDescription": "Cycles per thread when uops are executed in port 6.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA1",
-        "UMask": "0x80",
-        "BriefDescription": "Cycles per thread when uops are executed in port 7.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x00",
-        "UMask": "0x2",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "Counter": "Fixed counter 2",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x0",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "AnyThread": "1",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
-        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x0D",
-        "UMask": "0x3",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke)",
-        "Counter": "0,1,2,3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "AnyThread": "1",
-        "CounterMask": "1",
-        "PublicDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "CounterMask": "1",
-        "Errata": "HSD30, HSM31",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "CounterMask": "2",
-        "Errata": "HSD30, HSM31",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "CounterMask": "3",
-        "Errata": "HSD30, HSM31",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "CounterMask": "4",
-        "Errata": "HSD30, HSM31",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "Invert": "1",
-        "EventCode": "0xb1",
-        "UMask": "0x2",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "Errata": "HSD30, HSM31",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x1",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
-        "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "UMask": "0x2",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
-        "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json
index 9c00f8ef6a07..168df552b1a8 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json
@@ -40,6 +40,16 @@
     },
     {
         "EventCode": "0x08",
+        "UMask": "0xe",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -70,6 +80,16 @@
     },
     {
         "EventCode": "0x08",
+        "UMask": "0x60",
+        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "PublicDescription": "Number of cache load STLB hits. No page walk.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
         "UMask": "0x80",
         "BriefDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed",
         "Counter": "0,1,2,3",
@@ -119,6 +139,16 @@
     },
     {
         "EventCode": "0x49",
+        "UMask": "0xe",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -149,6 +179,16 @@
     },
     {
         "EventCode": "0x49",
+        "UMask": "0x60",
+        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
         "UMask": "0x80",
         "BriefDescription": "DTLB store misses with low part of linear-to-physical address translation missed",
         "Counter": "0,1,2,3",
@@ -207,6 +247,16 @@
     },
     {
         "EventCode": "0x85",
+        "UMask": "0xe",
+        "BriefDescription": "Misses in all ITLB levels that cause completed page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Completed page walks in ITLB of any page size.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
         "UMask": "0x10",
         "BriefDescription": "Cycles when PMH is busy with page walks",
         "Counter": "0,1,2,3",
@@ -236,6 +286,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x85",
+        "UMask": "0x60",
+        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "PublicDescription": "ITLB misses that hit STLB. No page walk.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xae",
         "UMask": "0x1",
         "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
@@ -257,39 +317,43 @@
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x21",
-        "BriefDescription": "Number of ITLB page walker hits in the L1+FB",
+        "UMask": "0x12",
+        "BriefDescription": "Number of DTLB page walker hits in the L2",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
-        "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
+        "PublicDescription": "Number of DTLB page walker loads that hit in the L2.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x41",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
+        "UMask": "0x14",
+        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
+        "Errata": "HSD25",
+        "PublicDescription": "Number of DTLB page walker loads that hit in the L3.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x81",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
+        "UMask": "0x18",
+        "BriefDescription": "Number of DTLB page walker hits in Memory",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1",
+        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
+        "Errata": "HSD25",
+        "PublicDescription": "Number of DTLB page walker loads from memory.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x12",
-        "BriefDescription": "Number of DTLB page walker hits in the L2",
+        "UMask": "0x21",
+        "BriefDescription": "Number of ITLB page walker hits in the L1+FB",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L2",
-        "PublicDescription": "Number of DTLB page walker loads that hit in the L2.",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L1",
+        "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -305,41 +369,41 @@
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x42",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
+        "UMask": "0x24",
+        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
+        "Errata": "HSD25",
+        "PublicDescription": "Number of ITLB page walker loads that hit in the L3.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x82",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
+        "UMask": "0x28",
+        "BriefDescription": "Number of ITLB page walker hits in Memory",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2",
+        "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
+        "Errata": "HSD25",
+        "PublicDescription": "Number of ITLB page walker loads from memory.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x14",
-        "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP",
+        "UMask": "0x41",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_L3",
-        "Errata": "HSD25",
-        "PublicDescription": "Number of DTLB page walker loads that hit in the L3.",
+        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x24",
-        "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP",
+        "UMask": "0x42",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_L3",
-        "Errata": "HSD25",
-        "PublicDescription": "Number of ITLB page walker loads that hit in the L3.",
+        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -354,41 +418,37 @@
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x84",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
+        "UMask": "0x48",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3",
+        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x18",
-        "BriefDescription": "Number of DTLB page walker hits in Memory",
+        "UMask": "0x81",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY",
-        "Errata": "HSD25",
-        "PublicDescription": "Number of DTLB page walker loads from memory.",
+        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x28",
-        "BriefDescription": "Number of ITLB page walker hits in Memory",
+        "UMask": "0x82",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY",
-        "Errata": "HSD25",
-        "PublicDescription": "Number of ITLB page walker loads from memory.",
+        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xBC",
-        "UMask": "0x48",
-        "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.",
+        "UMask": "0x84",
+        "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.",
         "Counter": "0,1,2,3",
-        "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY",
+        "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -420,65 +480,5 @@
         "PublicDescription": "Count number of STLB flush attempts.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "UMask": "0xe",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x08",
-        "UMask": "0x60",
-        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Number of cache load STLB hits. No page walk.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "UMask": "0xe",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x49",
-        "UMask": "0x60",
-        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks",
-        "Counter": "0,1,2,3",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "UMask": "0xe",
-        "BriefDescription": "Misses in all ITLB levels that cause completed page walks",
-        "Counter": "0,1,2,3",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Completed page walks in ITLB of any page size.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "UMask": "0x60",
-        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks",
-        "Counter": "0,1,2,3",
-        "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "ITLB misses that hit STLB. No page walk.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
index f1ee6d4853c5..999a01bc6467 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
@@ -10,6 +10,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "RFO requests that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -30,6 +40,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts all L2 store RFO requests.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0xc",
+        "EventName": "L2_RQSTS.ALL_RFO",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests to L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -50,6 +70,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts all L2 code requests.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 code requests",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -70,36 +100,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts all L2 store RFO requests.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "L2_RQSTS.ALL_RFO",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests to L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts all L2 code requests.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 code requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PublicDescription": "Counts all L2 HW prefetcher requests.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -219,6 +219,29 @@
         "CounterHTOff": "2"
     },
     {
+        "PublicDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "EventCode": "0x48",
+        "Counter": "2",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core",
+        "CounterMask": "1",
+        "CounterHTOff": "2"
+    },
+    {
+        "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "EventCode": "0x48",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts the number of lines brought into the L1 data cache.",
         "EventCode": "0x51",
         "Counter": "0,1,2,3",
@@ -239,76 +262,87 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding Demand Code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
+        "PublicDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.",
+        "PublicDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue",
+        "CounterMask": "6",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
+        "PublicDescription": "Offcore outstanding Demand Code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "UMask": "0x2",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "PublicDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "UMask": "0x2",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore",
-        "CounterMask": "1",
+        "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+        "PublicDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "UMask": "0x8",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -379,7 +413,7 @@
         "UMask": "0x11",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that miss the STLB.",
+        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -389,7 +423,7 @@
         "UMask": "0x12",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that miss the STLB.",
+        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -399,7 +433,7 @@
         "UMask": "0x21",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops with locked access.",
+        "BriefDescription": "Retired load uops with locked access. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -409,7 +443,7 @@
         "UMask": "0x41",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -419,7 +453,7 @@
         "UMask": "0x42",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -429,7 +463,7 @@
         "UMask": "0x81",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "All retired load uops. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -439,67 +473,61 @@
         "UMask": "0x82",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "All retired store uops. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops with L1 cache hits as data sources.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources. ",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops with L2 cache hits as data sources.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources. ",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was LLC hit with no snoop required.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required. ",
+        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source followed an L1 miss.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources following L1 data-cache miss",
+        "BriefDescription": "Retired load uops which data sources following L1 data-cache miss.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops that missed L2, excluding unknown sources.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops with L2 cache misses as data sources.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source is LLC miss.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -510,61 +538,56 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. ",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was an on-package core cache LLC hit and cross-core snoop missed.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was an on-package LLC hit and cross-core snoop hits.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was an on-package core cache with HitM responses.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC. ",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was LLC hit with no snoop required.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required. ",
+        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI)",
+        "PublicDescription": "Retired load uops whose data source was local memory (cross-socket snoop not needed or missed).",
         "EventCode": "0xD3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -753,50 +776,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Retired load uops whose data source was local memory (cross-socket snoop not needed or missed).",
-        "EventCode": "0xD3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops which data sources missed LLC but serviced from local dram.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PublicDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "EventCode": "0x48",
-        "Counter": "2",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core",
-        "CounterMask": "1",
-        "CounterHTOff": "2"
-    },
-    {
-        "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3f803c0244",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json b/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json
index de72b84b3536..efaa949ead31 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json
@@ -20,76 +20,45 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "IDQ.MS_MITE_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.",
+        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
+        "UMask": "0x4",
+        "EventName": "IDQ.MITE_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterMask": "1",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_CYCLES",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
-        "CounterMask": "1",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -138,6 +107,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
@@ -160,6 +139,39 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_SWITCHES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of uops delivered to IDQ from any path.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
@@ -206,7 +218,7 @@
         "UMask": "0x1",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled ",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -289,17 +301,5 @@
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
new file mode 100644
index 000000000000..7c2679514efb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/memory.json b/tools/perf/pmu-events/arch/x86/ivybridge/memory.json
index e1c6a1d4a4d5..a74d54f56192 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/memory.json
@@ -39,18 +39,6 @@
     },
     {
         "PEBS": "2",
-        "EventCode": "0xCD",
-        "Counter": "3",
-        "UMask": "0x2",
-        "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only.",
-        "PRECISE_STORE": "1",
-        "TakenAlone": "1",
-        "CounterHTOff": "3"
-    },
-    {
-        "PEBS": "2",
         "PublicDescription": "Loads with latency value being above 4.",
         "EventCode": "0xCD",
         "MSRValue": "0x4",
@@ -162,6 +150,18 @@
         "CounterHTOff": "3"
     },
     {
+        "PEBS": "2",
+        "EventCode": "0xCD",
+        "Counter": "3",
+        "UMask": "0x2",
+        "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only.",
+        "PRECISE_STORE": "1",
+        "TakenAlone": "1",
+        "CounterHTOff": "3"
+    },
+    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x300400244",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/other.json b/tools/perf/pmu-events/arch/x86/ivybridge/other.json
index 9c2dd0511a32..4eb83ee40412 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/other.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/other.json
@@ -10,16 +10,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
-        "EventCode": "0x5C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPL_CYCLES.RING123",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PublicDescription": "Number of intervals between processor halts while thread is in ring 0.",
         "EventCode": "0x5C",
         "Counter": "0,1,2,3",
@@ -32,6 +22,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
+        "EventCode": "0x5C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPL_CYCLES.RING123",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
         "EventCode": "0x63",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
index 2145c28193f7..0afbfd95ea30 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
@@ -1,30 +1,41 @@
 [
     {
         "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
     },
     {
+        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "PublicDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded.",
@@ -78,6 +89,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x0D",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "AnyThread": "1",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Increments each cycle the # of Uops issued by the RAT to RS. Set Cmask = 1, Inv = 1, Any= 1to count stalled cycles of this core.",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
@@ -175,6 +197,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Increments at the frequency of XCLK (100 MHz) when not halted.",
         "EventCode": "0x3C",
         "Counter": "0,1,2,3",
@@ -187,6 +220,36 @@
     {
         "EventCode": "0x3C",
         "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
         "SampleAfterValue": "2000003",
@@ -194,6 +257,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for S/W prefetch.",
         "EventCode": "0x4C",
         "Counter": "0,1,2,3",
@@ -216,37 +288,37 @@
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MOVE_ELIMINATION.INT_NOT_ELIMINATED",
+        "UMask": "0x1",
+        "EventName": "MOVE_ELIMINATION.INT_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of integer Move Elimination candidate uops that were not eliminated.",
+        "BriefDescription": "Number of integer Move Elimination candidate uops that were eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
+        "UMask": "0x2",
+        "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
+        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MOVE_ELIMINATION.INT_ELIMINATED",
+        "UMask": "0x4",
+        "EventName": "MOVE_ELIMINATION.INT_NOT_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of integer Move Elimination candidate uops that were eliminated.",
+        "BriefDescription": "Number of integer Move Elimination candidate uops that were not eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
+        "UMask": "0x8",
+        "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
+        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -260,6 +332,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5E",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x87",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -498,118 +582,118 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 1.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 0.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 1",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 0",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 4.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 1.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "UMask": "0x2",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 4",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 5.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 1.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 5",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 0.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 2.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
+        "UMask": "0xc",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 0",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 1.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
+        "UMask": "0xc",
         "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 1",
+        "BriefDescription": "Uops dispatched to port 2, loads and stores per core (speculative and retired).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 4.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 3.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
+        "UMask": "0x30",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 4",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 5.",
+        "PublicDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
+        "UMask": "0x30",
         "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 5",
+        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 2.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 4.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "UMask": "0x40",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 3.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 4.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "UMask": "0x40",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles which a Uop is dispatched on port 5.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
+        "UMask": "0x80",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops dispatched to port 2, loads and stores per core (speculative and retired).",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 5",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 5.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
+        "UMask": "0x80",
         "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 5",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -662,15 +746,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles with pending L1 cache miss loads. Set AnyThread to count per core.",
         "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with pending L1 cache miss loads.",
-        "CounterMask": "8",
-        "CounterHTOff": "2"
+        "BriefDescription": "Cycles while L2 cache miss load* is outstanding.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PublicDescription": "Cycles with pending memory loads. Set AnyThread to count per core.",
@@ -684,13 +767,33 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PublicDescription": "Total execution stalls.",
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls",
+        "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Total execution stalls.",
         "CounterMask": "4",
         "CounterHTOff": "0,1,2,3"
     },
@@ -708,6 +811,16 @@
     {
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
+        "UMask": "0x5",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while L2 cache miss load* is outstanding.",
+        "CounterMask": "5",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
         "UMask": "0x6",
         "EventName": "CYCLE_ACTIVITY.STALLS_LDM_PENDING",
         "SampleAfterValue": "2000003",
@@ -716,6 +829,37 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x6",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Cycles with pending L1 cache miss loads. Set AnyThread to count per core.",
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with pending L1 cache miss loads.",
+        "CounterMask": "8",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "CounterMask": "8",
+        "CounterHTOff": "2"
+    },
+    {
         "PublicDescription": "Execution stalls due to L1 data cache miss loads. Set Cmask=0CH.",
         "EventCode": "0xA3",
         "Counter": "2",
@@ -727,6 +871,16 @@
         "CounterHTOff": "2"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0xc",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "CounterMask": "12",
+        "CounterHTOff": "2"
+    },
+    {
         "EventCode": "0xA8",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -747,6 +901,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "EventCode": "0xA8",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts total number of uops to be executed per-thread each cycle. Set Cmask = 1, INV =1 to count stall cycles.",
         "EventCode": "0xB1",
         "Counter": "0,1,2,3",
@@ -757,6 +922,61 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xB1",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts total number of uops to be executed per-core each cycle.",
         "EventCode": "0xB1",
         "Counter": "0,1,2,3",
@@ -767,15 +987,59 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "EventCode": "0xB1",
-        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PublicDescription": "Number of instructions at retirement.",
@@ -809,24 +1073,12 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of micro-ops retired, Use cmask=1 and invert to count active cycles or stalled cycles.",
         "EventCode": "0xC2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.ALL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Actually retired uops. ",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Counts the number of retirement slots used each cycle.",
-        "EventCode": "0xC2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used. ",
+        "BriefDescription": "Retired uops.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -864,6 +1116,27 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Retirement slots used.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of self-modifying-code machine clears detected.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
@@ -880,50 +1153,67 @@
         "UMask": "0x20",
         "EventName": "MACHINE_CLEARS.MASKMOV",
         "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0. ",
+        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Branch instructions at retirement.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of conditional branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Conditional branch instructions retired. ",
+        "BriefDescription": "Conditional branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Direct and indirect near call instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect near call instructions retired. ",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Branch instructions at retirement.",
+        "PEBS": "1",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "UMask": "0x2",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PEBS": "2",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
         "SampleAfterValue": "400009",
         "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of near return instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Return instructions retired. ",
+        "BriefDescription": "Return instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -933,18 +1223,17 @@
         "UMask": "0x10",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired. ",
+        "BriefDescription": "Not taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of near taken branches retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Taken branch instructions retired. ",
+        "BriefDescription": "Taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -954,28 +1243,7 @@
         "UMask": "0x40",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Far branch instructions retired. ",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PEBS": "2",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Mispredicted conditional branch instructions retired.",
-        "EventCode": "0xC5",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted conditional branch instructions retired. ",
+        "BriefDescription": "Far branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -990,13 +1258,12 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Mispredicted taken branch instructions retired.",
         "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "UMask": "0x1",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
         "SampleAfterValue": "400009",
-        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. ",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1010,6 +1277,16 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Count cases of saving new LBR records by hardware.",
         "EventCode": "0xCC",
         "Counter": "0,1,2,3",
@@ -1028,280 +1305,5 @@
         "SampleAfterValue": "100003",
         "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x5E",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "EventCode": "0xA8",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "CounterMask": "8",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L2 cache miss load* is outstanding.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0xc",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
-        "CounterMask": "12",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L2 cache miss load* is outstanding.",
-        "CounterMask": "5",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x6",
-        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x0D",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json
index f036f5398906..f243551b4d12 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json
@@ -1,5 +1,35 @@
 [
     {
+        "PublicDescription": "Misses in all TLB levels that cause a page walk of any page size from demand loads.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x81",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes an page walk of any page size.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Misses in all TLB levels that caused page walk completed of any size by demand loads.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x82",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycle PMH is busy with a walk due to demand loads.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x84",
+        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Demand load cycles page miss handler (PMH) is busy with this walk.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x88",
@@ -146,35 +176,5 @@
         "SampleAfterValue": "100007",
         "BriefDescription": "STLB flush attempts",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Misses in all TLB levels that cause a page walk of any page size from demand loads.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes an page walk of any page size.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Misses in all TLB levels that caused page walk completed of any size by demand loads.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycle PMH is busy with a walk due to demand loads.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x84",
-        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Demand load cycles page miss handler (PMH) is busy with this walk.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/cache.json b/tools/perf/pmu-events/arch/x86/ivytown/cache.json
index ff27a620edd8..6dad3ad6b102 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/cache.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/cache.json
@@ -10,6 +10,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "RFO requests that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -30,6 +40,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts all L2 store RFO requests.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0xc",
+        "EventName": "L2_RQSTS.ALL_RFO",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests to L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -50,6 +70,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts all L2 code requests.",
+        "EventCode": "0x24",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 code requests",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -70,36 +100,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts all L2 store RFO requests.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "L2_RQSTS.ALL_RFO",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests to L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts all L2 code requests.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 code requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PublicDescription": "Counts all L2 HW prefetcher requests.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
@@ -219,6 +219,29 @@
         "CounterHTOff": "2"
     },
     {
+        "PublicDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "EventCode": "0x48",
+        "Counter": "2",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core",
+        "CounterMask": "1",
+        "CounterHTOff": "2"
+    },
+    {
+        "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "EventCode": "0x48",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts the number of lines brought into the L1 data cache.",
         "EventCode": "0x51",
         "Counter": "0,1,2,3",
@@ -239,76 +262,87 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding Demand Code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
+        "PublicDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.",
+        "PublicDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue",
+        "CounterMask": "6",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
+        "PublicDescription": "Offcore outstanding Demand Code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "UMask": "0x2",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "PublicDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "UMask": "0x2",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore",
-        "CounterMask": "1",
+        "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+        "PublicDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+        "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.",
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "UMask": "0x8",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -379,7 +413,7 @@
         "UMask": "0x11",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that miss the STLB.",
+        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -389,7 +423,7 @@
         "UMask": "0x12",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that miss the STLB.",
+        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -399,7 +433,7 @@
         "UMask": "0x21",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops with locked access.",
+        "BriefDescription": "Retired load uops with locked access. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -409,7 +443,7 @@
         "UMask": "0x41",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -419,7 +453,7 @@
         "UMask": "0x42",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -429,7 +463,7 @@
         "UMask": "0x81",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load uops.",
+        "BriefDescription": "All retired load uops. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -439,67 +473,61 @@
         "UMask": "0x82",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store uops.",
+        "BriefDescription": "All retired store uops. (Precise Event)",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops with L1 cache hits as data sources.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources. ",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops with L2 cache hits as data sources.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources. ",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was LLC hit with no snoop required.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required. ",
+        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source followed an L1 miss.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources following L1 data-cache miss",
+        "BriefDescription": "Retired load uops which data sources following L1 data-cache miss.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops that missed L2, excluding unknown sources.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops with L2 cache misses as data sources.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source is LLC miss.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -510,67 +538,61 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. ",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was an on-package core cache LLC hit and cross-core snoop missed.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was an on-package LLC hit and cross-core snoop hits.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was an on-package core cache with HitM responses.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC. ",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Retired load uops whose data source was LLC hit with no snoop required.",
         "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required. ",
+        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "EventCode": "0xD3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "UMask": "0x3",
         "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops which data sources missed LLC but serviced from local dram.",
+        "BriefDescription": "Retired load uops whose data source was local DRAM (Snoop not needed, Snoop Miss, or Snoop Hit data not forwarded).",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -780,40 +802,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "EventCode": "0x48",
-        "Counter": "2",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core",
-        "CounterMask": "1",
-        "CounterHTOff": "2"
-    },
-    {
-        "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x4003c0091",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/frontend.json b/tools/perf/pmu-events/arch/x86/ivytown/frontend.json
index de72b84b3536..efaa949ead31 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/frontend.json
@@ -20,76 +20,45 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "IDQ.MS_MITE_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.",
+        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
+        "UMask": "0x4",
+        "EventName": "IDQ.MITE_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterMask": "1",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_CYCLES",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
-        "CounterMask": "1",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -138,6 +107,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
@@ -160,6 +139,39 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x30",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_SWITCHES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of uops delivered to IDQ from any path.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
@@ -206,7 +218,7 @@
         "UMask": "0x1",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled ",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -289,17 +301,5 @@
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
new file mode 100644
index 000000000000..7c2679514efb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/memory.json b/tools/perf/pmu-events/arch/x86/ivytown/memory.json
index 437d98f3e344..3a7b86af8816 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/memory.json
@@ -30,18 +30,6 @@
     },
     {
         "PEBS": "2",
-        "EventCode": "0xCD",
-        "Counter": "3",
-        "UMask": "0x2",
-        "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only.",
-        "PRECISE_STORE": "1",
-        "TakenAlone": "1",
-        "CounterHTOff": "3"
-    },
-    {
-        "PEBS": "2",
         "PublicDescription": "Loads with latency value being above 4.",
         "EventCode": "0xCD",
         "MSRValue": "0x4",
@@ -153,6 +141,18 @@
         "CounterHTOff": "3"
     },
     {
+        "PEBS": "2",
+        "EventCode": "0xCD",
+        "Counter": "3",
+        "UMask": "0x2",
+        "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only.",
+        "PRECISE_STORE": "1",
+        "TakenAlone": "1",
+        "CounterHTOff": "3"
+    },
+    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fffc00244",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/other.json b/tools/perf/pmu-events/arch/x86/ivytown/other.json
index 9c2dd0511a32..4eb83ee40412 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/other.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/other.json
@@ -10,16 +10,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
-        "EventCode": "0x5C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPL_CYCLES.RING123",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PublicDescription": "Number of intervals between processor halts while thread is in ring 0.",
         "EventCode": "0x5C",
         "Counter": "0,1,2,3",
@@ -32,6 +22,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.",
+        "EventCode": "0x5C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPL_CYCLES.RING123",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.",
         "EventCode": "0x63",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
index 2145c28193f7..0afbfd95ea30 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
@@ -1,30 +1,41 @@
 [
     {
         "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
     },
     {
+        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "PublicDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded.",
@@ -78,6 +89,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x0D",
+        "Counter": "0,1,2,3",
+        "UMask": "0x3",
+        "AnyThread": "1",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Increments each cycle the # of Uops issued by the RAT to RS. Set Cmask = 1, Inv = 1, Any= 1to count stalled cycles of this core.",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
@@ -175,6 +197,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Increments at the frequency of XCLK (100 MHz) when not halted.",
         "EventCode": "0x3C",
         "Counter": "0,1,2,3",
@@ -187,6 +220,36 @@
     {
         "EventCode": "0x3C",
         "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
         "SampleAfterValue": "2000003",
@@ -194,6 +257,15 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for S/W prefetch.",
         "EventCode": "0x4C",
         "Counter": "0,1,2,3",
@@ -216,37 +288,37 @@
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MOVE_ELIMINATION.INT_NOT_ELIMINATED",
+        "UMask": "0x1",
+        "EventName": "MOVE_ELIMINATION.INT_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of integer Move Elimination candidate uops that were not eliminated.",
+        "BriefDescription": "Number of integer Move Elimination candidate uops that were eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
+        "UMask": "0x2",
+        "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
+        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MOVE_ELIMINATION.INT_ELIMINATED",
+        "UMask": "0x4",
+        "EventName": "MOVE_ELIMINATION.INT_NOT_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of integer Move Elimination candidate uops that were eliminated.",
+        "BriefDescription": "Number of integer Move Elimination candidate uops that were not eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x58",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED",
+        "UMask": "0x8",
+        "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED",
         "SampleAfterValue": "1000003",
-        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.",
+        "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -260,6 +332,18 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5E",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x87",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -498,118 +582,118 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 1.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 0.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 1",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 0",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 4.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 1.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "UMask": "0x2",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 4",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 5.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 1.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 5",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 0.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 2.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
+        "UMask": "0xc",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 0",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 1.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
+        "UMask": "0xc",
         "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 1",
+        "BriefDescription": "Uops dispatched to port 2, loads and stores per core (speculative and retired).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 4.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 3.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
+        "UMask": "0x30",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 4",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when uops are dispatched to port 5.",
+        "PublicDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
+        "UMask": "0x30",
         "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 5",
+        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 2.",
+        "PublicDescription": "Cycles which a Uop is dispatched on port 4.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "UMask": "0x40",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles which a Uop is dispatched on port 3.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 4.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "UMask": "0x40",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles which a Uop is dispatched on port 5.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
+        "UMask": "0x80",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops dispatched to port 2, loads and stores per core (speculative and retired).",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 5",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+        "PublicDescription": "Cycles per core when uops are dispatched to port 5.",
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
+        "UMask": "0x80",
         "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 5",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -662,15 +746,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles with pending L1 cache miss loads. Set AnyThread to count per core.",
         "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with pending L1 cache miss loads.",
-        "CounterMask": "8",
-        "CounterHTOff": "2"
+        "BriefDescription": "Cycles while L2 cache miss load* is outstanding.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PublicDescription": "Cycles with pending memory loads. Set AnyThread to count per core.",
@@ -684,13 +767,33 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "PublicDescription": "Total execution stalls.",
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls",
+        "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Total execution stalls.",
         "CounterMask": "4",
         "CounterHTOff": "0,1,2,3"
     },
@@ -708,6 +811,16 @@
     {
         "EventCode": "0xA3",
         "Counter": "0,1,2,3",
+        "UMask": "0x5",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while L2 cache miss load* is outstanding.",
+        "CounterMask": "5",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
         "UMask": "0x6",
         "EventName": "CYCLE_ACTIVITY.STALLS_LDM_PENDING",
         "SampleAfterValue": "2000003",
@@ -716,6 +829,37 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x6",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Cycles with pending L1 cache miss loads. Set AnyThread to count per core.",
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with pending L1 cache miss loads.",
+        "CounterMask": "8",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "CounterMask": "8",
+        "CounterHTOff": "2"
+    },
+    {
         "PublicDescription": "Execution stalls due to L1 data cache miss loads. Set Cmask=0CH.",
         "EventCode": "0xA3",
         "Counter": "2",
@@ -727,6 +871,16 @@
         "CounterHTOff": "2"
     },
     {
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0xc",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "CounterMask": "12",
+        "CounterHTOff": "2"
+    },
+    {
         "EventCode": "0xA8",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -747,6 +901,17 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "EventCode": "0xA8",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts total number of uops to be executed per-thread each cycle. Set Cmask = 1, INV =1 to count stall cycles.",
         "EventCode": "0xB1",
         "Counter": "0,1,2,3",
@@ -757,6 +922,61 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xB1",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts total number of uops to be executed per-core each cycle.",
         "EventCode": "0xB1",
         "Counter": "0,1,2,3",
@@ -767,15 +987,59 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "EventCode": "0xB1",
-        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "EventCode": "0xB1",
+        "Invert": "1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PublicDescription": "Number of instructions at retirement.",
@@ -809,24 +1073,12 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of micro-ops retired, Use cmask=1 and invert to count active cycles or stalled cycles.",
         "EventCode": "0xC2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.ALL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Actually retired uops. ",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Counts the number of retirement slots used each cycle.",
-        "EventCode": "0xC2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used. ",
+        "BriefDescription": "Retired uops.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -864,6 +1116,27 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Retirement slots used.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Number of self-modifying-code machine clears detected.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
@@ -880,50 +1153,67 @@
         "UMask": "0x20",
         "EventName": "MACHINE_CLEARS.MASKMOV",
         "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0. ",
+        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Branch instructions at retirement.",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x0",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of conditional branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Conditional branch instructions retired. ",
+        "BriefDescription": "Conditional branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Direct and indirect near call instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect near call instructions retired. ",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Branch instructions at retirement.",
+        "PEBS": "1",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "UMask": "0x2",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PEBS": "2",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
         "SampleAfterValue": "400009",
         "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts the number of near return instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Return instructions retired. ",
+        "BriefDescription": "Return instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -933,18 +1223,17 @@
         "UMask": "0x10",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired. ",
+        "BriefDescription": "Not taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of near taken branches retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Taken branch instructions retired. ",
+        "BriefDescription": "Taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -954,28 +1243,7 @@
         "UMask": "0x40",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Far branch instructions retired. ",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PEBS": "2",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Mispredicted conditional branch instructions retired.",
-        "EventCode": "0xC5",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted conditional branch instructions retired. ",
+        "BriefDescription": "Far branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -990,13 +1258,12 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Mispredicted taken branch instructions retired.",
         "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "UMask": "0x1",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
         "SampleAfterValue": "400009",
-        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. ",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1010,6 +1277,16 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Count cases of saving new LBR records by hardware.",
         "EventCode": "0xCC",
         "Counter": "0,1,2,3",
@@ -1028,280 +1305,5 @@
         "SampleAfterValue": "100003",
         "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x5E",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "EventCode": "0xA8",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "CounterMask": "8",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L2 cache miss load* is outstanding.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0xc",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
-        "CounterMask": "12",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L2 cache miss load* is outstanding.",
-        "CounterMask": "5",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x6",
-        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x0D",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "EventCode": "0xB1",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)",
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json
index c8de548b78fa..4645e9d3f460 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json
@@ -1,5 +1,15 @@
 [
     {
+        "PublicDescription": "Misses in all TLB levels that cause a page walk of any page size from demand loads.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x81",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes an page walk of any page size.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x82",
@@ -9,6 +19,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Misses in all TLB levels that caused page walk completed of any size by demand loads.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x82",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x84",
@@ -18,6 +38,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycle PMH is busy with a walk due to demand loads.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x84",
+        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Demand load cycles page miss handler (PMH) is busy with this walk.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x88",
@@ -164,35 +194,5 @@
         "SampleAfterValue": "100007",
         "BriefDescription": "STLB flush attempts",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Misses in all TLB levels that cause a page walk of any page size from demand loads.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes an page walk of any page size.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Misses in all TLB levels that caused page walk completed of any size by demand loads.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Cycle PMH is busy with a walk due to demand loads.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x84",
-        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Demand load cycles page miss handler (PMH) is busy with this walk.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
new file mode 100644
index 000000000000..fd7d7c438226
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
@@ -0,0 +1,140 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 4ea068366c3e..93656f2fd53a 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -9,6 +9,7 @@ GenuineIntel-6-27,v4,bonnell,core
 GenuineIntel-6-36,v4,bonnell,core
 GenuineIntel-6-35,v4,bonnell,core
 GenuineIntel-6-5C,v8,goldmont,core
+GenuineIntel-6-7A,v1,goldmontplus,core
 GenuineIntel-6-3C,v24,haswell,core
 GenuineIntel-6-45,v24,haswell,core
 GenuineIntel-6-46,v24,haswell,core
@@ -22,10 +23,7 @@ GenuineIntel-6-1E,v2,nehalemep,core
 GenuineIntel-6-1F,v2,nehalemep,core
 GenuineIntel-6-1A,v2,nehalemep,core
 GenuineIntel-6-2E,v2,nehalemex,core
-GenuineIntel-6-4E,v24,skylake,core
-GenuineIntel-6-5E,v24,skylake,core
-GenuineIntel-6-8E,v24,skylake,core
-GenuineIntel-6-9E,v24,skylake,core
+GenuineIntel-6-[4589]E,v24,skylake,core
 GenuineIntel-6-37,v13,silvermont,core
 GenuineIntel-6-4D,v13,silvermont,core
 GenuineIntel-6-4C,v13,silvermont,core
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
new file mode 100644
index 000000000000..fd7d7c438226
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
@@ -0,0 +1,140 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/silvermont/cache.json b/tools/perf/pmu-events/arch/x86/silvermont/cache.json
index 0bd1bc5302de..82be7d1b8b81 100644
--- a/tools/perf/pmu-events/arch/x86/silvermont/cache.json
+++ b/tools/perf/pmu-events/arch/x86/silvermont/cache.json
@@ -36,12 +36,13 @@
         "BriefDescription": "L2 cache request misses"
     },
     {
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events. \r\n",
         "EventCode": "0x86",
         "Counter": "0,1",
         "UMask": "0x4",
         "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of cycles the NIP stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses."
+        "BriefDescription": "Cycles code-fetch stalled due to an outstanding ICache miss."
     },
     {
         "PEBS": "1",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json
index 0551a9ba865d..54bfe9e4045c 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json
@@ -1,442 +1,6 @@
 [
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x11",
-        "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions that miss the STLB.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x12",
-        "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store instructions that miss the STLB.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1",
-        "L1_Hit_Indication": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x21",
-        "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load instructions with locked access.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions that split across a cacheline boundary.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store instructions that split across a cacheline boundary.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1",
-        "L1_Hit_Indication": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load instructions.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store instructions.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1",
-        "L1_Hit_Indication": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions with L1 cache hits as data sources.",
-        "EventCode": "0xD1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retired load instructions with L1 cache hits as data sources",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions with L2 cache hits as data sources.",
-        "EventCode": "0xD1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions with L2 cache hits as data sources",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions with L3 cache hits as data sources.",
-        "EventCode": "0xD1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load instructions with L3 cache hits as data sources",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions missed L1 cache as data sources.",
-        "EventCode": "0xD1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions missed L1 cache as data sources",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions missed L2 cache as data sources.",
-        "EventCode": "0xD1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load instructions missed L2 cache as data sources",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions missed L3 cache as data sources.",
-        "EventCode": "0xD1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load instructions missed L3 cache as data sources",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
-        "EventCode": "0xD1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
-        "EventCode": "0xD2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.",
-        "EventCode": "0xD2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.",
-        "EventCode": "0xD2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PEBS": "1",
-        "EventCode": "0xD4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
-    },
-    {
-        "PublicDescription": "This event counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
-        "EventCode": "0x51",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L1D.REPLACEMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D data line replacements",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand\n from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L1D_PEND_MISS.PENDING",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D miss outstandings duration in cycles",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts duration of L1D miss outstanding in cycles.",
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
-        "EventCode": "0xB0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand Data Read requests sent to uncore",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts both cacheable and noncachaeble code read requests.",
-        "EventCode": "0xB0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cacheable and noncachaeble code read requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
-        "EventCode": "0xB0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
-        "EventCode": "0xB0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand and prefetch data reads",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, and so on.",
-        "EventCode": "0xB0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Any memory transaction that reached the SQ.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.\nNote: A prefetch promoted to Demand is counted from the promotion point.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle. ",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.\nNote: Writeback pending FIFO has six entries.",
-        "EventCode": "0xB2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts L2 writebacks that access L2 cache.",
-        "EventCode": "0xF0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "L2_TRANS.L2_WB",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 writebacks that access L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts core-originated cacheable demand requests that miss the last level cache (LLC). Demand requests include loads, RFOs, and hardware prefetches from L1D, and instruction fetches from IFU.",
-        "EventCode": "0x2E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "Errata": "SKL057",
-        "EventName": "LONGEST_LAT_CACHE.MISS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests missed L3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts core-originated cacheable demand requests that refer to the last level cache (LLC). Demand requests include loads, RFOs, and hardware prefetches from L1D, and instruction fetches from IFU.",
-        "EventCode": "0x2E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4f",
-        "Errata": "SKL057",
-        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of cache line split locks sent to the uncore.",
-        "EventCode": "0xF4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "SQ_MISC.SPLIT_LOCK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of cache line split locks sent to uncore.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "EventCode": "0xB7, 0xBB",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PublicDescription": "This event counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
         "UMask": "0x21",
@@ -446,122 +10,123 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "UMask": "0x22",
+        "EventName": "L2_RQSTS.RFO_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "BriefDescription": "RFO requests that miss L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0xe1",
-        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "UMask": "0x24",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests",
+        "BriefDescription": "L2 cache misses when fetching instructions",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Demand requests that miss L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0xe2",
-        "EventName": "L2_RQSTS.ALL_RFO",
+        "UMask": "0x27",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests to L2 cache",
+        "BriefDescription": "Demand requests that miss L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the total number of L2 code requests.",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0xe4",
-        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "UMask": "0x38",
+        "EventName": "L2_RQSTS.PF_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "L2 code requests",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the total number of requests from the L2 hardware prefetchers.",
+        "PublicDescription": "All requests that miss L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0xf8",
-        "EventName": "L2_RQSTS.ALL_PF",
+        "UMask": "0x3f",
+        "EventName": "L2_RQSTS.MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches",
+        "BriefDescription": "All requests that miss L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x38",
-        "EventName": "L2_RQSTS.PF_MISS",
+        "UMask": "0x41",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0xd8",
-        "EventName": "L2_RQSTS.PF_HIT",
+        "UMask": "0x42",
+        "EventName": "L2_RQSTS.RFO_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache",
+        "BriefDescription": "RFO requests that hit L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "RFO requests that hit L2 cache.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "L2_RQSTS.RFO_HIT",
+        "UMask": "0x44",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that hit L2 cache",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "RFO requests that miss L2 cache.",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x22",
-        "EventName": "L2_RQSTS.RFO_MISS",
+        "UMask": "0xd8",
+        "EventName": "L2_RQSTS.PF_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that miss L2 cache",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x44",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "UMask": "0xe1",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
         "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "BriefDescription": "Demand Data Read requests",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "UMask": "0xe2",
+        "EventName": "L2_RQSTS.ALL_RFO",
         "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache misses when fetching instructions",
+        "BriefDescription": "RFO requests to L2 cache",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Demand requests that miss L2 cache.",
+        "PublicDescription": "Counts the total number of L2 code requests.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x27",
-        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
+        "UMask": "0xe4",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Demand requests that miss L2 cache",
+        "BriefDescription": "L2 code requests",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -575,13 +140,13 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "All requests that miss L2 cache.",
+        "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x3f",
-        "EventName": "L2_RQSTS.MISS",
+        "UMask": "0xf8",
+        "EventName": "L2_RQSTS.ALL_PF",
         "SampleAfterValue": "200003",
-        "BriefDescription": "All requests that miss L2 cache",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -595,62 +160,45 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xF2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L2_LINES_OUT.SILENT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xF2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L2_LINES_OUT.NON_SILENT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
-        "EventCode": "0xF2",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
+        "EventCode": "0x2E",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_LINES_OUT.USELESS_PREF",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "UMask": "0x41",
+        "Errata": "SKL057",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Core-originated cacheable demand requests missed L3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
-        "EventCode": "0xF1",
+        "PublicDescription": "Counts core-originated cacheable requests to the  L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
+        "EventCode": "0x2E",
         "Counter": "0,1,2,3",
-        "UMask": "0x1f",
-        "EventName": "L2_LINES_IN.ALL",
+        "UMask": "0x4f",
+        "Errata": "SKL057",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "L2 cache lines filling L2",
+        "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "EventCode": "0x48",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "UMask": "0x1",
+        "EventName": "L1D_PEND_MISS.PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
-        "CounterMask": "1",
+        "BriefDescription": "L1D miss outstandings duration in cycles",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "EventCode": "0x48",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "UMask": "0x1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -666,3121 +214,483 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x60",
+        "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.",
+        "EventCode": "0x48",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "UMask": "0x2",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xF2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoops sent to sibling cores return clean response.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000018000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that have any response type.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts streaming stores that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts streaming stores that hit in the L3 and the snoops sent to sibling cores return clean response.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts streaming stores that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts streaming stores that have any response type.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops sent to sibling cores return clean response.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops sent to sibling cores return clean response.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops sent to sibling cores return clean response.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that have any response type.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0400002 ",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "EventCode": "0x51",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L1D.REPLACEMENT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "L1D data line replacements",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400002 ",
+        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400002 ",
+        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400002 ",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400002 ",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x2",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400002 ",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x2",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400002 ",
+        "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c0002 ",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c0002 ",
+        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x8",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c0002 ",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "EventCode": "0x60",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x8",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c0002 ",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "EventCode": "0xB0",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops sent to sibling cores return clean response.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Demand Data Read requests sent to uncore",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c0002 ",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "EventCode": "0xB0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x2",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cacheable and noncachaeble code read requests",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c0002 ",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "EventCode": "0xB0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401c0002 ",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "EventCode": "0xB0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x8",
+        "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Demand and prefetch data reads",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0100002 ",
+        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
+        "EventCode": "0xB0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x80",
+        "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Any memory transaction that reached the SQ.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100002 ",
+        "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.",
+        "EventCode": "0xB2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100002 ",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "EventName": "OFFCORE_RESPONSE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions that miss the STLB.",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x11",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Retired load instructions that miss the STLB. (Precise Event)",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired store instructions that miss the STLB.",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x12",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Retired store instructions that miss the STLB. (Precise Event)",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "L1_Hit_Indication": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100002 ",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x21",
+        "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired load instructions with locked access. (Precise Event)",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100002 ",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x41",
+        "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Retired load instructions that split across a cacheline boundary. (Precise Event)",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0080002 ",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x42",
+        "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Retired store instructions that split across a cacheline boundary. (Precise Event)",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "L1_Hit_Indication": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080002 ",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x81",
+        "EventName": "MEM_INST_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "All retired load instructions. (Precise Event)",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080002 ",
+        "PEBS": "1",
+        "PublicDescription": "All retired store instructions.",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x82",
+        "EventName": "MEM_INST_RETIRED.ALL_STORES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "All retired store instructions. (Precise Event)",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "L1_Hit_Indication": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080002 ",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "MEM_LOAD_RETIRED.L1_HIT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Retired load instructions with L1 cache hits as data sources",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions with L2 cache hits as data sources.",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x2",
+        "EventName": "MEM_LOAD_RETIRED.L2_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Retired load instructions with L2 cache hits as data sources",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions with L3 cache hits as data sources.",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "MEM_LOAD_RETIRED.L3_HIT",
+        "SampleAfterValue": "50021",
+        "BriefDescription": "Retired load instructions with L3 cache hits as data sources",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080002 ",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x8",
+        "EventName": "MEM_LOAD_RETIRED.L1_MISS",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Retired load instructions missed L1 cache as data sources",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0040002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions missed L2 cache as data sources.",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x10",
+        "EventName": "MEM_LOAD_RETIRED.L2_MISS",
+        "SampleAfterValue": "50021",
+        "BriefDescription": "Retired load instructions missed L2 cache as data sources",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions missed L3 cache as data sources.",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x20",
+        "EventName": "MEM_LOAD_RETIRED.L3_MISS",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired load instructions missed L3 cache as data sources",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040002 ",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x40",
+        "EventName": "MEM_LOAD_RETIRED.FB_HIT",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040002 ",
+        "PEBS": "1",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x2",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040002 ",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x8",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0020002 ",
+        "PEBS": "1",
+        "EventCode": "0xD4",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "MEM_LOAD_MISC_RETIRED.UC",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020002 ",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "EventCode": "0xF0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x40",
+        "EventName": "L2_TRANS.L2_WB",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 writebacks that access L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020002 ",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "EventCode": "0xF1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x1f",
+        "EventName": "L2_LINES_IN.ALL",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "L2 cache lines filling L2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020002 ",
+        "EventCode": "0xF2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L2_LINES_OUT.SILENT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020002 ",
+        "EventCode": "0xF2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x2",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020002 ",
+        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+        "EventCode": "0xF2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "L2_LINES_OUT.USELESS_PREF",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020002 ",
+        "EventCode": "0xF2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "L2_LINES_OUT.USELESS_HWPF",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010002 ",
+        "PublicDescription": "Counts the number of cache line split locks sent to the uncore.",
+        "EventCode": "0xF4",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "UMask": "0x10",
+        "EventName": "SQ_MISC.SPLIT_LOCK",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Number of cache line split locks sent to uncore.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fc0400001 ",
         "Counter": "0,1,2,3",
@@ -3793,6 +703,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000400001 ",
         "Counter": "0,1,2,3",
@@ -3805,6 +716,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400400001 ",
         "Counter": "0,1,2,3",
@@ -3817,6 +729,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200400001 ",
         "Counter": "0,1,2,3",
@@ -3829,6 +742,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400001 ",
         "Counter": "0,1,2,3",
@@ -3841,6 +755,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080400001 ",
         "Counter": "0,1,2,3",
@@ -3853,18 +768,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fc01c0001 ",
         "Counter": "0,1,2,3",
@@ -3877,6 +781,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10001c0001 ",
         "Counter": "0,1,2,3",
@@ -3889,6 +794,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x04001c0001 ",
         "Counter": "0,1,2,3",
@@ -3901,6 +807,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x02001c0001 ",
         "Counter": "0,1,2,3",
@@ -3913,6 +820,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x01001c0001 ",
         "Counter": "0,1,2,3",
@@ -3925,6 +833,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00801c0001 ",
         "Counter": "0,1,2,3",
@@ -3937,270 +846,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401c0001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fc0020001 ",
         "Counter": "0,1,2,3",
@@ -4213,6 +859,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1000020001 ",
         "Counter": "0,1,2,3",
@@ -4225,6 +872,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0400020001 ",
         "Counter": "0,1,2,3",
@@ -4237,6 +885,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0200020001 ",
         "Counter": "0,1,2,3",
@@ -4249,6 +898,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100020001 ",
         "Counter": "0,1,2,3",
@@ -4261,6 +911,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0080020001 ",
         "Counter": "0,1,2,3",
@@ -4273,18 +924,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
+        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0000010001 ",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json
index 3c6b59af5d54..213dd6230cf2 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json
@@ -27,13 +27,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "EventCode": "0xC7",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -55,7 +54,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+        "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x1e",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
index e697dbd63e6e..578dff5bd823 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
@@ -1,62 +1,81 @@
 [
     {
-        "EventCode": "0x80",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "ICACHE_16B.IFDATA_STALL",
+        "EventName": "IDQ.MITE_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x83",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ICACHE_64B.IFTAG_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "UMask": "0x4",
+        "EventName": "IDQ.MITE_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x83",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ICACHE_64B.IFTAG_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x83",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ICACHE_64B.IFTAG_STALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_UOPS",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
+        "UMask": "0x18",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "EventCode": "0x79",
+        "Counter": "0,1,2,3",
+        "UMask": "0x18",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -66,95 +85,99 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "UMask": "0x24",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterMask": "1",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
+        "UMask": "0x24",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "BriefDescription": "Cycles MITE is delivering any Uop",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_CYCLES",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_CYCLES",
+        "UMask": "0x30",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_SWITCHES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
-        "CounterMask": "4",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles  uops were  delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
+        "EventCode": "0x80",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "UMask": "0x4",
+        "EventName": "ICACHE_16B.IFDATA_STALL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
-        "CounterMask": "1",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles 4  uops were  delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
-        "EventCode": "0x79",
+        "EventCode": "0x83",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering 4 Uops",
-        "CounterMask": "4",
+        "UMask": "0x1",
+        "EventName": "ICACHE_64B.IFTAG_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles  uops were delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
-        "EventCode": "0x79",
+        "EventCode": "0x83",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering any Uop",
-        "CounterMask": "1",
+        "UMask": "0x2",
+        "EventName": "ICACHE_64B.IFTAG_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x83",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "ICACHE_64B.IFTAG_STALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding ?4 ? x? when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread\n\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions)\n \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -164,7 +187,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -175,7 +198,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles when less than 1 uop is  delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >=3.",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -186,6 +209,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -196,6 +220,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -217,7 +242,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0?2 cycles.",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
         "EventCode": "0xAB",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -228,6 +253,7 @@
     },
     {
         "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
         "EventCode": "0xC6",
         "MSRValue": "0x11",
         "Counter": "0,1,2,3",
@@ -235,7 +261,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.",
+        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -248,7 +274,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -261,12 +287,13 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
         "EventCode": "0xC6",
         "MSRValue": "0x14",
         "Counter": "0,1,2,3",
@@ -274,12 +301,13 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced iTLB true miss.",
+        "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "EventCode": "0xC6",
         "MSRValue": "0x15",
         "Counter": "0,1,2,3",
@@ -287,7 +315,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -300,7 +328,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -313,7 +341,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -326,34 +354,13 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
         "EventCode": "0xC6",
         "MSRValue": "0x400806",
         "Counter": "0,1,2,3",
@@ -367,6 +374,7 @@
     },
     {
         "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
         "EventCode": "0xC6",
         "MSRValue": "0x401006",
         "Counter": "0,1,2,3",
@@ -374,12 +382,13 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
         "EventCode": "0xC6",
         "MSRValue": "0x402006",
         "Counter": "0,1,2,3",
@@ -387,7 +396,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -400,7 +409,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -413,7 +422,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -426,7 +435,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -439,12 +448,13 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
         "EventCode": "0xC6",
         "MSRValue": "0x100206",
         "Counter": "0,1,2,3",
@@ -452,7 +462,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -465,7 +475,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
         "MSRIndex": "0x3F7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json
index d7fd5b06825b..3bd8b712c889 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json
@@ -1,6 +1,74 @@
 [
     {
-        "PublicDescription": "Unfriendly TSX abort triggered by  a flowmarker.",
+        "PublicDescription": "Number of times a TSX line had a cache conflict.",
+        "EventCode": "0x54",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "TX_MEM.ABORT_CONFLICT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "TX_MEM.ABORT_CAPACITY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.",
+        "EventCode": "0x54",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
+        "EventCode": "0x54",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
+        "EventCode": "0x54",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
+        "EventCode": "0x54",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of times we could not allocate Lock Buffer.",
+        "EventCode": "0x54",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x5d",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -10,7 +78,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Unfriendly TSX abort triggered by  a vzeroupper instruction.",
+        "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.",
         "EventCode": "0x5d",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -50,7 +118,77 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of times we entered an HLE region\n does not count nested transactions.",
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
+        "CounterMask": "2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x6",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Demand Data Read requests who miss L3 cache.",
+        "EventCode": "0xB0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand Data Read requests who miss L3 cache",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "Errata": "SKL089",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.",
         "EventCode": "0xC8",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -71,7 +209,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of times HLE abort was triggered.",
+        "PublicDescription": "Number of times HLE abort was triggered. (PEBS)",
         "EventCode": "0xC8",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
@@ -99,13 +237,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "EventCode": "0xC8",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
         "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.). ",
+        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -128,7 +265,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of times we entered an RTM region\n does not count nested transactions.",
+        "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.",
         "EventCode": "0xC9",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -149,7 +286,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Number of times RTM abort was triggered.",
+        "PublicDescription": "Number of times RTM abort was triggered. (PEBS)",
         "EventCode": "0xC9",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
@@ -208,17 +345,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:\n1. memory disambiguation,\n2. external snoop, or\n3. cross SMT-HW-thread snoop (stores) hitting load buffer.",
-        "EventCode": "0xC3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "SKL089",
-        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "PEBS": "2",
         "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
@@ -331,1718 +457,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of times a TSX line had a cache conflict.",
-        "EventCode": "0x54",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "TX_MEM.ABORT_CONFLICT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x54",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "TX_MEM.ABORT_CAPACITY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.",
-        "EventCode": "0x54",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
-        "EventCode": "0x54",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
-        "EventCode": "0x54",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
-        "EventCode": "0x54",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Number of times we could not allocate Lock Buffer.",
-        "EventCode": "0x54",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Demand Data Read requests who miss L3 cache.",
-        "EventCode": "0xB0",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand Data Read requests who miss L3 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA3",
-        "Counter": "0,1,2,3",
-        "UMask": "0x6",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203c008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007c008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000408000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L4_HIT_LOCAL_L4 & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001c8000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000108000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_S & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000088000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_E & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000048000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT_M & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000028000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203c000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007c000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_MISS_LOCAL_DRAM & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L4_HIT_LOCAL_L4 & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001c0800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_S & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_E & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & L3_HIT_M & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "STREAMING_STORES & SUPPLIER_NONE & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203c000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007c000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L4_HIT_LOCAL_L4 & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001c0100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_S & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_E & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT_M & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203c000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007c000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001c0080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_S & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_E & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT_M & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203c000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007c000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L4_HIT_LOCAL_L4 & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001c0004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_S & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_E & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT_M & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203c000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007c000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L4_HIT_LOCAL_L4 & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001c0002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_S & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_E & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT_M & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3ffc000001 ",
         "Counter": "0,1,2,3",
@@ -2055,18 +470,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203c000001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x103c000001 ",
         "Counter": "0,1,2,3",
@@ -2079,6 +483,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x043c000001 ",
         "Counter": "0,1,2,3",
@@ -2091,6 +496,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x023c000001 ",
         "Counter": "0,1,2,3",
@@ -2103,6 +509,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x013c000001 ",
         "Counter": "0,1,2,3",
@@ -2115,6 +522,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x00bc000001 ",
         "Counter": "0,1,2,3",
@@ -2127,18 +535,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007c000001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x3fc4000001 ",
         "Counter": "0,1,2,3",
@@ -2151,18 +548,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x1004000001 ",
         "Counter": "0,1,2,3",
@@ -2175,6 +561,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0404000001 ",
         "Counter": "0,1,2,3",
@@ -2187,6 +574,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0204000001 ",
         "Counter": "0,1,2,3",
@@ -2199,6 +587,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0104000001 ",
         "Counter": "0,1,2,3",
@@ -2211,6 +600,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0084000001 ",
         "Counter": "0,1,2,3",
@@ -2221,89 +611,5 @@
         "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SPL_HIT",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001c0001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_S & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_E & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT_M & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/other.json b/tools/perf/pmu-events/arch/x86/skylake/other.json
index cfdc323acc82..84a316d380ac 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/other.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/other.json
@@ -1,11 +1,47 @@
 [
     {
-        "PublicDescription": "This event counts the number of hardware interruptions received by the processor.",
+        "EventCode": "0x32",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "SW_PREFETCH_ACCESS.NTA",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of PREFETCHNTA instructions executed.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x32",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "SW_PREFETCH_ACCESS.T0",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of PREFETCHT0 instructions executed.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x32",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "SW_PREFETCH_ACCESS.T1_T2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x32",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of PREFETCHW instructions executed.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of hardware interruptions received by the processor.",
         "EventCode": "0xCB",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "HW_INTERRUPTS.RECEIVED",
-        "SampleAfterValue": "100003",
+        "SampleAfterValue": "203",
         "BriefDescription": "Number of hardware interrupts received by the processor.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
index 0f7adb809be3..bc6d2afbcd8a 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
@@ -1,80 +1,92 @@
 [
     {
-        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
+        "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Core cycles when the thread is not in halt state",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
-        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
         "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
-        "EventCode": "0x3C",
+        "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "UMask": "0x2",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xE6",
+        "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BACLEARS.ANY",
+        "UMask": "0x8",
+        "EventName": "LD_BLOCKS.NO_SR",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
+        "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA8",
+        "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.",
+        "EventCode": "0x07",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "LSD.UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of Uops delivered by the LSD.",
+        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "False dependencies in MOB due to partial compare on address.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
-        "EventCode": "0x87",
+        "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "ILD_STALL.LCP",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles checkpoints in Resource Allocation Table (RAT) are recovering from JEClear or machine clear.",
         "EventCode": "0x0D",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "AnyThread": "1",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -87,33 +99,35 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
-        "EventCode": "0xA2",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "EventCode": "0x0E",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "RESOURCE_STALLS.ANY",
+        "EventName": "UOPS_ISSUED.ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource-related stall cycles",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts stall cycles caused by the store buffer (SB) overflow (excluding draining from synch). This counts cycles that the pipeline backend blocked uop delivery from the front end.",
-        "EventCode": "0xA2",
+        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "EventCode": "0x0E",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "RESOURCE_STALLS.SB",
+        "UMask": "0x1",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS).",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.ANY",
+        "UMask": "0x2",
+        "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
+        "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -126,361 +140,318 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
-        "EventCode": "0x0E",
-        "Invert": "1",
+        "EventCode": "0x14",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "EventName": "ARITH.DIVIDER_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread.\nNote: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
-        "EventCode": "0x5E",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "UMask": "0x0",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5E",
-        "Invert": "1",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
+        "UMask": "0x0",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
-        "EventCode": "0xCC",
+        "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Increments whenever there is an update to the LBR array.",
+        "UMask": "0x0",
+        "EdgeDetect": "1",
+        "EventName": "CPU_CLK_UNHALTED.RING0_TRANS",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of machine clears (nukes) of any type.",
-        "EventCode": "0xC3",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of machine clears (nukes) of any type. ",
-        "CounterMask": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2503",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts self-modifying code (SMC) detected, which causes a machine clear.",
-        "EventCode": "0xC3",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MACHINE_CLEARS.SMC",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Self-modifying code (SMC) detected.",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2503",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
-        "EventCode": "0xC0",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "Errata": "SKL091, SKL044",
-        "EventName": "INST_RETIRED.ANY_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of instructions retired. General Counter - architectural event",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2503",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts instructions retired.",
-        "EventCode": "0xC0",
-        "Counter": "1",
+        "EventCode": "0x3C",
+        "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "Errata": "SKL091, SKL044",
-        "EventName": "INST_RETIRED.PREC_DIST",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
-        "CounterHTOff": "1"
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2503",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts the number of retirement slots used.",
-        "EventCode": "0xC2",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used.",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.STALL_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
-        "CounterMask": "1",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2503",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "EventCode": "0x4C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
-        "CounterMask": "10",
+        "EventName": "LOAD_HIT_PRE.SW_PF",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "EventCode": "0x5E",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Conditional branch instructions retired.",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.",
+        "EventCode": "0x5E",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts all (macro) branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "EventCode": "0x87",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
+        "UMask": "0x1",
+        "EventName": "ILD_STALL.LCP",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Return instructions retired.",
+        "UMask": "0x1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "UMask": "0x2",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Taken branch instructions retired.",
+        "UMask": "0x4",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.",
-        "EventCode": "0xC4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Far branch instructions retired.",
+        "UMask": "0x8",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
-        "EventCode": "0xC4",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired. ",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.",
-        "EventCode": "0xC5",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted conditional branch instructions retired.",
+        "UMask": "0x10",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
-        "EventCode": "0xC5",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted direct and indirect near call instructions retired.",
+        "UMask": "0x20",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts all mispredicted macro branch instructions retired.",
-        "EventCode": "0xC5",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All mispredicted macro branch instructions retired.",
+        "UMask": "0x40",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "UMask": "0x80",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.",
-        "EventCode": "0xC5",
+        "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted macro branch instructions retired. ",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1",
+        "EventName": "RESOURCE_STALLS.ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource-related stall cycles",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
-        "EventCode": "0xB1",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.THREAD",
+        "UMask": "0x8",
+        "EventName": "RESOURCE_STALLS.SB",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
+        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of uops executed from any thread.",
-        "EventCode": "0xB1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE",
+        "UMask": "0x1",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of uops executed on the core.",
+        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "UOPS_EXECUTED.X87",
+        "UMask": "0x4",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of x87 uops dispatched.",
+        "BriefDescription": "Total execution stalls.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
-        "EventCode": "0xB1",
-        "Invert": "1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "UMask": "0x5",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
-        "CounterMask": "1",
+        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
+        "CounterMask": "5",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
-        "EventCode": "0xB1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "UMask": "0x8",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
-        "CounterMask": "1",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "CounterMask": "8",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "EventCode": "0xB1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "UMask": "0xc",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "CounterMask": "2",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "CounterMask": "12",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
-        "EventCode": "0xB1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "UMask": "0x10",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
-        "CounterMask": "3",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "CounterMask": "16",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
-        "EventCode": "0xB1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "UMask": "0x14",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "CounterMask": "20",
+        "CounterHTOff": "0,1,2,3"
     },
     {
+        "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.",
         "EventCode": "0xA6",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -490,6 +461,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
         "EventCode": "0xA6",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -499,6 +471,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
         "EventCode": "0xA6",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
@@ -508,6 +481,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
         "EventCode": "0xA6",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
@@ -517,6 +491,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
         "EventCode": "0xA6",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -535,212 +510,196 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 0.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "EventName": "LSD.UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 0",
+        "BriefDescription": "Number of Uops delivered by the LSD.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 1.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 1",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 2.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 2",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 3.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.THREAD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 3",
+        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 4.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "EventCode": "0xB1",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 4",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 5.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 5",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 6.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 6",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+        "CounterMask": "2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts, on the per-thread basis, cycles during which uops are dispatched from the Reservation Station (RS) to port 7.",
-        "EventCode": "0xA1",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 7",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "CounterMask": "3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "UMask": "0x1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls.",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
         "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "PublicDescription": "Number of uops executed from any thread.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "CounterMask": "8",
+        "BriefDescription": "Number of uops executed on the core.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
-        "CounterMask": "12",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by asm inspection of the nearby instructions.",
-        "EventCode": "0x4C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LOAD_HIT_PRE.SW_PF",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:\n - preceding store conflicts with the load (incomplete overlap)\n\n - store forwarding is impossible due to u-arch limitations\n\n - preceding lock RMW operations are not forwarded\n\n - store has the no-forward bit set (uncacheable/page-split/masked stores)\n\n - all-blocking stores are used (mostly, fences and port I/O)\n\nand others.\nThe most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events.\nSee the table of not supported store forwards in the Optimization Guide.",
-        "EventCode": "0x03",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
-        "EventCode": "0x03",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "LD_BLOCKS.NO_SR",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "CounterMask": "2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.",
-        "EventCode": "0x07",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "False dependencies in MOB due to partial compare on address.",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "CounterMask": "3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
-        "CounterMask": "1",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xB1",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
-        "CounterMask": "5",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "PublicDescription": "Counts the number of x87 uops executed.",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "EventName": "UOPS_EXECUTED.X87",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
-        "CounterMask": "16",
+        "BriefDescription": "Counts the number of x87 uops dispatched.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
+        "EventCode": "0xC0",
         "Counter": "0,1,2,3",
-        "UMask": "0x14",
-        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "UMask": "0x0",
+        "Errata": "SKL091, SKL044",
+        "EventName": "INST_RETIRED.ANY_P",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
-        "CounterMask": "20",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "BriefDescription": "Number of instructions retired. General Counter - architectural event",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+        "PEBS": "2",
+        "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.",
+        "EventCode": "0xC0",
+        "Counter": "1",
+        "UMask": "0x1",
+        "Errata": "SKL091, SKL044",
+        "EventName": "INST_RETIRED.PREC_DIST",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
+        "CounterHTOff": "1"
     },
     {
         "PEBS": "2",
@@ -757,183 +716,235 @@
         "CounterHTOff": "0,2,3"
     },
     {
-        "EventCode": "0x14",
+        "EventCode": "0xC1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ARITH.DIVIDER_ACTIVE",
+        "UMask": "0x3f",
+        "EventName": "OTHER_ASSISTS.ANY",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the retirement slots used.",
+        "EventCode": "0xC2",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
-        "CounterMask": "1",
+        "BriefDescription": "Retirement slots used.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA8",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "EventCode": "0xC2",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_ACTIVE",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "BriefDescription": "Cycles without actually retired uops.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA8",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+        "EventCode": "0xC2",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "4",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "CounterMask": "10",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC1",
+        "EventCode": "0xC3",
         "Counter": "0,1,2,3",
-        "UMask": "0x3f",
-        "EventName": "OTHER_ASSISTS.ANY",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "MACHINE_CLEARS.COUNT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register.\r\nFor more information, refer to ?Mixing Intel AVX and Intel SSE Code? section of the Optimization Guide.",
-        "EventCode": "0x0E",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "EventCode": "0xC3",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
+        "UMask": "0x4",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Self-modifying code (SMC) detected.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
-    },
-    {
-        "EventCode": "0x3C",
+        "PublicDescription": "Counts all (macro) branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Conditional branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0D",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "UMask": "0x2",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "2",
+        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "CounterMask": "2",
+        "UMask": "0x8",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Return instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "CounterMask": "3",
+        "UMask": "0x10",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Not taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "CounterMask": "4",
+        "UMask": "0x20",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "Invert": "1",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "CounterMask": "1",
+        "UMask": "0x40",
+        "Errata": "SKL091",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Counts the number of far branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).",
-        "EventCode": "0x3C",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
-        "EdgeDetect": "1",
-        "EventName": "CPU_CLK_UNHALTED.RING0_TRANS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.",
-        "CounterMask": "1",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "PublicDescription": "This event counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "UMask": "0x2",
+        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted direct and indirect near call instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "2",
+        "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
+        "UMask": "0x4",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted macro branch instructions retired.",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PEBS": "1",
+        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "EventCode": "0xCC",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Increments whenever there is an update to the LBR array.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "BACLEARS.ANY",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
new file mode 100644
index 000000000000..36c903faed0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json
index 02f32cbf6789..2bcba7daca14 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json
@@ -1,83 +1,6 @@
 [
     {
-        "PublicDescription": "This event counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
-        "EventCode": "0xAE",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ITLB.ITLB_FLUSH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x4F",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "EPT.WALK_PENDING",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Misses at all ITLB levels that cause page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (1G  page size). The page walk can end with or without a fault.",
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "ITLB_MISSES.WALK_PENDING",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake. ",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ITLB_MISSES.STLB_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts load misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
+        "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -87,45 +10,68 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
+        "BriefDescription": "Page walk completed due to a demand data load to a 4K page",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
+        "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts load misses in all DTLB levels that cause a completed page walk (1G  page size). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
+        "BriefDescription": "Page walk completed due to a demand data load to a 1G page",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.",
+        "EventCode": "0x08",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
         "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -135,7 +81,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause page walks of any page size (4K/2M/4M/1G).",
+        "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -145,45 +91,68 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (4K page size). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
+        "BriefDescription": "Page walk completed due to a demand data store to a 4K page",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
+        "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts store misses in all DTLB levels that cause a completed page walk (1G  page size). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages.  The page walks can end with or without a page fault.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
+        "BriefDescription": "Page walk completed due to a demand data store to a 1G page",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0xe",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "EventCode": "0x49",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
         "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -193,73 +162,77 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of DTLB flush attempts of the thread-specific entries.",
-        "EventCode": "0xBD",
+        "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.",
+        "EventCode": "0x4F",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "TLB_FLUSH.DTLB_THREAD",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "DTLB flush attempts of the thread-specific entries",
+        "UMask": "0x10",
+        "EventName": "EPT.WALK_PENDING",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, and so on).",
-        "EventCode": "0xBD",
+        "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "TLB_FLUSH.STLB_ANY",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "STLB flush attempts",
+        "UMask": "0x1",
+        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Misses at all ITLB levels that cause page walks",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
         "EventCode": "0x85",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "UMask": "0x2",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x08",
+        "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "UMask": "0x4",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "UMask": "0x8",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+        "UMask": "0xe",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
-        "CounterMask": "1",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x08",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
+        "EventName": "ITLB_MISSES.WALK_PENDING",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
-        "CounterMask": "1",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.",
         "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -268,5 +241,44 @@
         "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
+        "EventCode": "0xAE",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "ITLB.ITLB_FLUSH",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
+        "EventCode": "0xBD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "TLB_FLUSH.DTLB_THREAD",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "DTLB flush attempts of the thread-specific entries",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
+        "EventCode": "0xBD",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "TLB_FLUSH.STLB_ANY",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "STLB flush attempts",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
index b5bc742b6fbc..5c9940866acd 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
@@ -265,7 +265,7 @@
     {
         "EventCode": "0x60",
         "UMask": "0x2",
-        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle. ",
+        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
         "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
@@ -398,22 +398,24 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load instructions that miss the STLB.",
+        "BriefDescription": "Retired load instructions that miss the STLB. (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
+        "PublicDescription": "Retired load instructions that miss the STLB.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store instructions that miss the STLB.",
+        "BriefDescription": "Retired store instructions that miss the STLB. (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
+        "PublicDescription": "Retired store instructions that miss the STLB.",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -421,7 +423,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load instructions with locked access.",
+        "BriefDescription": "Retired load instructions with locked access. (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -432,24 +434,22 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load instructions that split across a cacheline boundary.",
+        "BriefDescription": "Retired load instructions that split across a cacheline boundary. (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store instructions that split across a cacheline boundary.",
+        "BriefDescription": "Retired store instructions that split across a cacheline boundary. (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -457,7 +457,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load instructions.",
+        "BriefDescription": "All retired load instructions. (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -468,11 +468,12 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "All retired store instructions.",
+        "BriefDescription": "All retired store instructions. (Precise Event)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
+        "PublicDescription": "All retired store instructions.",
         "SampleAfterValue": "2000003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -485,7 +486,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -509,7 +510,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. ",
+        "PublicDescription": "Retired load instructions with L3 cache hits as data sources.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
@@ -545,7 +546,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. ",
+        "PublicDescription": "Retired load instructions missed L3 cache as data sources.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -557,7 +558,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. ",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -616,7 +617,6 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -639,7 +639,6 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
-        "PublicDescription": "Retired load instructions whose data sources was remote HITM.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -648,9 +647,9 @@
         "UMask": "0x8",
         "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache",
         "Data_LA": "1",
+        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -697,7 +696,7 @@
     {
         "EventCode": "0xF2",
         "UMask": "0x2",
-        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped ",
+        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped",
         "Counter": "0,1,2,3",
         "EventName": "L2_LINES_OUT.NON_SILENT",
         "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped.",
@@ -742,7 +741,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -755,7 +754,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -768,7 +767,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -781,7 +780,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -794,7 +793,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -807,7 +806,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -820,7 +819,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -833,7 +832,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -846,7 +845,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -859,7 +858,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -872,7 +871,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -885,7 +884,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -898,7 +897,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -911,7 +910,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -924,7 +923,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -937,7 +936,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -950,7 +949,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -963,7 +962,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -976,7 +975,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -989,7 +988,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1002,7 +1001,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1015,7 +1014,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1028,7 +1027,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1041,7 +1040,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1054,7 +1053,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1067,7 +1066,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1080,7 +1079,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1093,7 +1092,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1106,7 +1105,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1119,7 +1118,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1132,7 +1131,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1145,7 +1144,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1158,7 +1157,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1171,7 +1170,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1184,7 +1183,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1197,7 +1196,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1210,7 +1209,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1223,7 +1222,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1236,7 +1235,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1249,7 +1248,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1262,7 +1261,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1275,7 +1274,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1288,7 +1287,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1301,7 +1300,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1314,7 +1313,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1327,7 +1326,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1340,7 +1339,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1353,7 +1352,85 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that have any response type.",
+        "MSRValue": "0x0000018000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c8000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c8000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "OTHER & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c8000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c8000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that hit in the L3.",
+        "MSRValue": "0x3f803c8000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1366,7 +1443,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1379,7 +1456,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1392,7 +1469,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1405,7 +1482,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1418,7 +1495,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1431,7 +1508,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1444,7 +1521,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1457,7 +1534,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1470,7 +1547,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1483,7 +1560,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1496,7 +1573,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1509,7 +1586,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1522,7 +1599,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1535,7 +1612,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1548,7 +1625,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1561,7 +1638,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1574,7 +1651,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1587,7 +1664,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1600,7 +1677,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1613,7 +1690,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1626,7 +1703,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1639,7 +1716,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1652,7 +1729,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1665,7 +1742,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
index 1c09a328df36..286ed1a37ec9 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
@@ -29,10 +29,9 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x8",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
index 40abc0852cd6..403a4f89e9b2 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
@@ -182,7 +182,7 @@
         "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -247,20 +247,20 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "Counter": "0,1,2,3",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.",
+        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x11",
         "Counter": "0,1,2,3",
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. ",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -268,7 +268,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x12",
         "Counter": "0,1,2,3",
@@ -281,7 +281,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x13",
         "Counter": "0,1,2,3",
@@ -294,7 +294,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced iTLB true miss.",
+        "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x14",
         "Counter": "0,1,2,3",
@@ -308,13 +308,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x15",
         "Counter": "0,1,2,3",
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. ",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -322,7 +322,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x400206",
         "Counter": "0,1,2,3",
@@ -335,7 +335,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x200206",
         "Counter": "0,1,2,3",
@@ -348,7 +348,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x400406",
         "Counter": "0,1,2,3",
@@ -367,7 +367,7 @@
         "Counter": "0,1,2,3",
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -375,13 +375,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x401006",
         "Counter": "0,1,2,3",
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -389,13 +389,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x402006",
         "Counter": "0,1,2,3",
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -403,7 +403,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x404006",
         "Counter": "0,1,2,3",
@@ -416,7 +416,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x408006",
         "Counter": "0,1,2,3",
@@ -429,7 +429,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x410006",
         "Counter": "0,1,2,3",
@@ -442,7 +442,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x420006",
         "Counter": "0,1,2,3",
@@ -455,13 +455,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x100206",
         "Counter": "0,1,2,3",
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -469,7 +469,7 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
         "MSRValue": "0x300206",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
index ca22a22c1abd..e7f1aa31226d 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
@@ -214,7 +214,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED",
-        "PublicDescription": "Number of times HLE abort was triggered.",
+        "PublicDescription": "Number of times HLE abort was triggered. (PEBS)",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -239,10 +239,9 @@
     {
         "EventCode": "0xC8",
         "UMask": "0x20",
-        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.). ",
+        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
-        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -292,7 +291,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Number of times RTM abort was triggered.",
+        "PublicDescription": "Number of times RTM abort was triggered. (PEBS)",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -466,7 +465,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss in the L3. ",
+        "PublicDescription": "Counts demand data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -479,7 +478,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -492,7 +491,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -505,7 +504,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -518,7 +517,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -531,7 +530,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -544,7 +543,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. ",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -557,7 +556,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -570,7 +569,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -583,7 +582,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -596,7 +595,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -609,7 +608,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -622,7 +621,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss in the L3. ",
+        "PublicDescription": "Counts all demand code reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -635,7 +634,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -648,7 +647,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -661,7 +660,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -674,7 +673,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -687,7 +686,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -700,7 +699,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. ",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -713,7 +712,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -726,7 +725,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -739,7 +738,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -752,7 +751,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -765,7 +764,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -778,7 +777,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. ",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -791,7 +790,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -804,7 +803,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -817,7 +816,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -830,7 +829,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -843,7 +842,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -856,7 +855,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -869,7 +868,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -882,7 +881,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -895,7 +894,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -908,7 +907,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -921,7 +920,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -934,7 +933,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -947,7 +946,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -960,7 +959,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -973,7 +972,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -986,7 +985,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -999,7 +998,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1012,7 +1011,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. ",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1025,7 +1024,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1038,7 +1037,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1051,7 +1050,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1064,7 +1063,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1077,7 +1076,85 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that miss in the L3.",
+        "MSRValue": "0x3fbc008000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc08000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc08000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc08000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b808000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604008000 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1090,7 +1167,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss in the L3. ",
+        "PublicDescription": "Counts all prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1103,7 +1180,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1116,7 +1193,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1129,7 +1206,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1142,7 +1219,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1155,7 +1232,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1168,7 +1245,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss in the L3. ",
+        "PublicDescription": "Counts prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1181,7 +1258,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1194,7 +1271,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1207,7 +1284,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1220,7 +1297,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1233,7 +1310,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1246,7 +1323,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. ",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1259,7 +1336,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1272,7 +1349,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1285,7 +1362,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1298,7 +1375,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1311,7 +1388,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. ",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1324,7 +1401,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. ",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1337,7 +1414,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1350,7 +1427,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1363,7 +1440,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1376,7 +1453,7 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. ",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1389,8 +1466,8 @@
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json
index 70243b0b0586..778a541463eb 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json
@@ -40,6 +40,42 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x32",
+        "UMask": "0x1",
+        "BriefDescription": "Number of PREFETCHNTA instructions executed.",
+        "Counter": "0,1,2,3",
+        "EventName": "SW_PREFETCH_ACCESS.NTA",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x32",
+        "UMask": "0x2",
+        "BriefDescription": "Number of PREFETCHT0 instructions executed.",
+        "Counter": "0,1,2,3",
+        "EventName": "SW_PREFETCH_ACCESS.T0",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x32",
+        "UMask": "0x4",
+        "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "Counter": "0,1,2,3",
+        "EventName": "SW_PREFETCH_ACCESS.T1_T2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x32",
+        "UMask": "0x8",
+        "BriefDescription": "Number of PREFETCHW instructions executed.",
+        "Counter": "0,1,2,3",
+        "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xCB",
         "UMask": "0x1",
         "BriefDescription": "Number of hardware interrupts received by the processor.",
@@ -50,6 +86,62 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xEF",
+        "UMask": "0x1",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xEF",
+        "UMask": "0x2",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xEF",
+        "UMask": "0x4",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xEF",
+        "UMask": "0x8",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xEF",
+        "UMask": "0x10",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xEF",
+        "UMask": "0x20",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xEF",
+        "UMask": "0x40",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xFE",
         "UMask": "0x2",
         "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
@@ -69,4 +161,4 @@
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
-]
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
index 0895d1e52a4a..f99f7ae27820 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
@@ -3,41 +3,41 @@
         "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
-        "Counter": "Fixed counter 1",
+        "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
         "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "Counter": "Fixed counter 2",
+        "Counter": "Fixed counter 1",
         "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
         "AnyThread": "1",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
     },
     {
         "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "Counter": "Fixed counter 3",
+        "Counter": "Fixed counter 2",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
         "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
         "SampleAfterValue": "2000003",
-        "CounterHTOff": "Fixed counter 3"
+        "CounterHTOff": "Fixed counter 2"
     },
     {
         "EventCode": "0x03",
@@ -126,7 +126,7 @@
         "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
-        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -762,11 +762,10 @@
         "EdgeDetect": "1",
         "EventCode": "0xC3",
         "UMask": "0x1",
-        "BriefDescription": "Number of machine clears (nukes) of any type. ",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
         "Counter": "0,1,2,3",
         "EventName": "MACHINE_CLEARS.COUNT",
         "CounterMask": "1",
-        "PublicDescription": "Number of machine clears (nukes) of any type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -799,7 +798,7 @@
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
         "Errata": "SKL091",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -811,14 +810,14 @@
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
         "Errata": "SKL091",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x4",
-        "BriefDescription": "All (macro) branch instructions retired. ",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "PEBS": "2",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
@@ -835,7 +834,7 @@
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
         "Errata": "SKL091",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -858,19 +857,19 @@
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
         "Errata": "SKL091",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x40",
-        "BriefDescription": "Far branch instructions retired.",
+        "BriefDescription": "Counts the number of far branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "Errata": "SKL091",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -891,7 +890,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -902,14 +901,14 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
+        "PublicDescription": "This event counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC5",
         "UMask": "0x4",
-        "BriefDescription": "Mispredicted macro branch instructions retired. ",
+        "BriefDescription": "Mispredicted macro branch instructions retired.",
         "PEBS": "2",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
@@ -920,10 +919,11 @@
     {
         "EventCode": "0xC5",
         "UMask": "0x20",
-        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
new file mode 100644
index 000000000000..36c903faed0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -0,0 +1,164 @@
+[
+    {
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Uops Per Instruction",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline",
+        "MetricName": "UPI"
+    },
+    {
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
+        "MetricGroup": "Frontend",
+        "MetricName": "IFetch_Line_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
+        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
+        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricName": "DSB_Coverage"
+    },
+    {
+        "BriefDescription": "Cycles Per Instruction (threaded)",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "MetricGroup": "Pipeline;Summary",
+        "MetricName": "CPI"
+    },
+    {
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Summary",
+        "MetricName": "CLKS"
+    },
+    {
+        "BriefDescription": "Total issue-pipeline slots",
+        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "TopDownL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "INST_RETIRED.ANY",
+        "MetricGroup": "Summary",
+        "MetricName": "Instructions"
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC"
+    },
+    {
+        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricGroup": "Pipeline;Ports_Utilization",
+        "MetricName": "ILP"
+    },
+    {
+        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
+        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
+        "MetricGroup": "Unknown_Branches",
+        "MetricName": "BAClear_Cost"
+    },
+    {
+        "BriefDescription": "Core actual clocks when any thread is active on the physical core",
+        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "SMT",
+        "MetricName": "CORE_CLKS"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
+        "MetricGroup": "Memory_Bound;Memory_Lat",
+        "MetricName": "Load_Miss_Real_Latency"
+    },
+    {
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricGroup": "Memory_Bound;Memory_BW",
+        "MetricName": "MLP"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
+        "MetricGroup": "TLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
+        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "MetricGroup": "Summary",
+        "MetricName": "CPU_Utilization"
+    },
+    {
+        "BriefDescription": "Giga Floating Point Operations Per Second",
+        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
+        "MetricGroup": "FLOPS;Summary",
+        "MetricName": "GFLOPs"
+    },
+    {
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
+        "MetricName": "Turbo_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "MetricGroup": "SMT;Summary",
+        "MetricName": "SMT_2T_Utilization"
+    },
+    {
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Summary",
+        "MetricName": "Kernel_Utilization"
+    },
+    {
+        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Core_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Core_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Core_Residency"
+    },
+    {
+        "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C2_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C3_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C6_Pkg_Residency"
+    },
+    {
+        "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "MetricGroup": "Power",
+        "MetricName": "C7_Pkg_Residency"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
index 70750dab7ead..7f466c97e485 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
@@ -12,30 +12,30 @@
     {
         "EventCode": "0x08",
         "UMask": "0x2",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
+        "BriefDescription": "Page walk completed due to a demand data load to a 4K page",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts demand data loads that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x08",
         "UMask": "0x4",
-        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
+        "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts demand data loads that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x08",
         "UMask": "0x8",
-        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
+        "BriefDescription": "Page walk completed due to a demand data load to a 1G page",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts load misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -52,17 +52,17 @@
     {
         "EventCode": "0x08",
         "UMask": "0x10",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture. ",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x08",
         "UMask": "0x10",
-        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
         "CounterMask": "1",
@@ -93,30 +93,30 @@
     {
         "EventCode": "0x49",
         "UMask": "0x2",
-        "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
+        "BriefDescription": "Page walk completed due to a demand data store to a 4K page",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts demand data stores that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x49",
         "UMask": "0x4",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
+        "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts demand data stores that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x49",
         "UMask": "0x8",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
+        "BriefDescription": "Page walk completed due to a demand data store to a 1G page",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages.  The page walks can end with or without a page fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -133,17 +133,17 @@
     {
         "EventCode": "0x49",
         "UMask": "0x10",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture. ",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x49",
         "UMask": "0x10",
-        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
         "CounterMask": "1",
@@ -197,7 +197,7 @@
         "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
         "Counter": "0,1,2,3",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -224,10 +224,10 @@
     {
         "EventCode": "0x85",
         "UMask": "0x10",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake. ",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture. ",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index d51dc9ca8861..b578aa26e375 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -116,6 +116,43 @@ static void fixdesc(char *s)
                 *e = 0;
 }
 
+/* Add escapes for '\' so they are proper C strings. */
+static char *fixregex(char *s)
+{
+        int len = 0;
+        int esc_count = 0;
+        char *fixed = NULL;
+        char *p, *q;
+
+        /* Count the number of '\' in string */
+        for (p = s; *p; p++) {
+                ++len;
+                if (*p == '\\')
+                        ++esc_count;
+        }
+
+        if (esc_count == 0)
+                return s;
+
+        /* allocate space for a new string */
+        fixed = (char *) malloc(len + 1);
+        if (!fixed)
+                return NULL;
+
+        /* copy over the characters */
+        q = fixed;
+        for (p = s; *p; p++) {
+                if (*p == '\\') {
+                        *q = '\\';
+                        ++q;
+                }
+                *q = *p;
+                ++q;
+        }
+        *q = '\0';
+        return fixed;
+}
+
 static struct msrmap {
         const char *num;
         const char *pname;
@@ -292,7 +329,7 @@ static int print_events_table_entry(void *data, char *name, char *event,
                                     char *desc, char *long_desc,
                                     char *pmu, char *unit, char *perpkg,
                                     char *metric_expr,
-                                    char *metric_name)
+                                    char *metric_name, char *metric_group)
 {
         struct perf_entry_data *pd = data;
         FILE *outfp = pd->outfp;
@@ -304,8 +341,10 @@ static int print_events_table_entry(void *data, char *name, char *event,
          */
         fprintf(outfp, "{\n");
 
-        fprintf(outfp, "\t.name = \"%s\",\n", name);
-        fprintf(outfp, "\t.event = \"%s\",\n", event);
+        if (name)
+                fprintf(outfp, "\t.name = \"%s\",\n", name);
+        if (event)
+                fprintf(outfp, "\t.event = \"%s\",\n", event);
         fprintf(outfp, "\t.desc = \"%s\",\n", desc);
         fprintf(outfp, "\t.topic = \"%s\",\n", topic);
         if (long_desc && long_desc[0])
@@ -320,6 +359,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
                 fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr);
         if (metric_name)
                 fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
+        if (metric_group)
+                fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
         fprintf(outfp, "},\n");
 
         return 0;
@@ -357,6 +398,9 @@ static char *real_event(const char *name, char *event)
 {
         int i;
 
+        if (!name)
+                return NULL;
+
         for (i = 0; fixed[i].name; i++)
                 if (!strcasecmp(name, fixed[i].name))
                         return (char *)fixed[i].event;
@@ -369,7 +413,7 @@ int json_events(const char *fn,
                       char *long_desc,
                       char *pmu, char *unit, char *perpkg,
                       char *metric_expr,
-                      char *metric_name),
+                      char *metric_name, char *metric_group),
           void *data)
 {
         int err = -EIO;
@@ -397,6 +441,7 @@ int json_events(const char *fn,
                 char *unit = NULL;
                 char *metric_expr = NULL;
                 char *metric_name = NULL;
+                char *metric_group = NULL;
                 unsigned long long eventcode = 0;
                 struct msrmap *msr = NULL;
                 jsmntok_t *msrval = NULL;
@@ -476,6 +521,8 @@ int json_events(const char *fn,
                                 addfield(map, &perpkg, "", "", val);
                         } else if (json_streq(map, field, "MetricName")) {
                                 addfield(map, &metric_name, "", "", val);
+                        } else if (json_streq(map, field, "MetricGroup")) {
+                                addfield(map, &metric_group, "", "", val);
                         } else if (json_streq(map, field, "MetricExpr")) {
                                 addfield(map, &metric_expr, "", "", val);
                                 for (s = metric_expr; *s; s++)
@@ -501,10 +548,11 @@ int json_events(const char *fn,
                         addfield(map, &event, ",", filter, NULL);
                 if (msr != NULL)
                         addfield(map, &event, ",", msr->pname, msrval);
-                fixname(name);
+                if (name)
+                        fixname(name);
 
                 err = func(data, name, real_event(name, event), desc, long_desc,
-                                pmu, unit, perpkg, metric_expr, metric_name);
+                           pmu, unit, perpkg, metric_expr, metric_name, metric_group);
                 free(event);
                 free(desc);
                 free(name);
@@ -516,6 +564,7 @@ int json_events(const char *fn,
                 free(unit);
                 free(metric_expr);
                 free(metric_name);
+                free(metric_group);
                 if (err)
                         break;
                 tok += j;
@@ -636,7 +685,7 @@ static int process_mapfile(FILE *outfp, char *fpath)
                 }
                 line[strlen(line)-1] = '\0';
 
-                cpuid = strtok_r(p, ",", &save);
+                cpuid = fixregex(strtok_r(p, ",", &save));
                 version = strtok_r(NULL, ",", &save);
                 fname = strtok_r(NULL, ",", &save);
                 type = strtok_r(NULL, ",", &save);
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index d87efd2685b8..4684c673c445 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -7,7 +7,7 @@ int json_events(const char *fn,
                                 char *long_desc,
                                 char *pmu,
                                 char *unit, char *perpkg, char *metric_expr,
-                                char *metric_name),
+                                char *metric_name, char *metric_group),
                 void *data);
 char *get_cpu_str(void);
 
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index e08789ddfe6c..92a4d15ee0b9 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -16,6 +16,7 @@ struct pmu_event {
         const char *perpkg;
         const char *metric_expr;
         const char *metric_name;
+        const char *metric_group;
 };
 
 /*
diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-record b/tools/perf/scripts/python/bin/mem-phys-addr-record
new file mode 100644
index 000000000000..5a875122a904
--- /dev/null
+++ b/tools/perf/scripts/python/bin/mem-phys-addr-record
@@ -0,0 +1,19 @@
+#!/bin/bash
+
+#
+# Profiling physical memory by all retired load instructions/uops event
+# MEM_INST_RETIRED.ALL_LOADS or MEM_UOPS_RETIRED.ALL_LOADS
+#
+
+load=`perf list | grep mem_inst_retired.all_loads`
+if [ -z "$load" ]; then
+        load=`perf list | grep mem_uops_retired.all_loads`
+fi
+if [ -z "$load" ]; then
+        echo "There is no event to count all retired load instructions/uops."
+        exit 1
+fi
+
+arg=$(echo $load | tr -d ' ')
+arg="$arg:P"
+perf record --phys-data -e $arg $@
diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-report b/tools/perf/scripts/python/bin/mem-phys-addr-report
new file mode 100644
index 000000000000..3f2b847e2eab
--- /dev/null
+++ b/tools/perf/scripts/python/bin/mem-phys-addr-report
@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: resolve physical address samples
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/mem-phys-addr.py
diff --git a/tools/perf/scripts/python/mem-phys-addr.py b/tools/perf/scripts/python/mem-phys-addr.py
new file mode 100644
index 000000000000..ebee2c5ae496
--- /dev/null
+++ b/tools/perf/scripts/python/mem-phys-addr.py
@@ -0,0 +1,95 @@
+# mem-phys-addr.py: Resolve physical address samples
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2018, Intel Corporation.
+
+from __future__ import division
+import os
+import sys
+import struct
+import re
+import bisect
+import collections
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+#physical address ranges for System RAM
+system_ram = []
+#physical address ranges for Persistent Memory
+pmem = []
+#file object for proc iomem
+f = None
+#Count for each type of memory
+load_mem_type_cnt = collections.Counter()
+#perf event name
+event_name = None
+
+def parse_iomem():
+        global f
+        f = open('/proc/iomem', 'r')
+        for i, j in enumerate(f):
+                m = re.split('-|:',j,2)
+                if m[2].strip() == 'System RAM':
+                        system_ram.append(long(m[0], 16))
+                        system_ram.append(long(m[1], 16))
+                if m[2].strip() == 'Persistent Memory':
+                        pmem.append(long(m[0], 16))
+                        pmem.append(long(m[1], 16))
+
+def print_memory_type():
+        print "Event: %s" % (event_name)
+        print "%-40s  %10s  %10s\n" % ("Memory type", "count", "percentage"),
+        print "%-40s  %10s  %10s\n" % ("----------------------------------------", \
+                                        "-----------", "-----------"),
+        total = sum(load_mem_type_cnt.values())
+        for mem_type, count in sorted(load_mem_type_cnt.most_common(), \
+                                        key = lambda(k, v): (v, k), reverse = True):
+                print "%-40s  %10d  %10.1f%%\n" % (mem_type, count, 100 * count / total),
+
+def trace_begin():
+        parse_iomem()
+
+def trace_end():
+        print_memory_type()
+        f.close()
+
+def is_system_ram(phys_addr):
+        #/proc/iomem is sorted
+        position = bisect.bisect(system_ram, phys_addr)
+        if position % 2 == 0:
+                return False
+        return True
+
+def is_persistent_mem(phys_addr):
+        position = bisect.bisect(pmem, phys_addr)
+        if position % 2 == 0:
+                return False
+        return True
+
+def find_memory_type(phys_addr):
+        if phys_addr == 0:
+                return "N/A"
+        if is_system_ram(phys_addr):
+                return "System RAM"
+
+        if is_persistent_mem(phys_addr):
+                return "Persistent Memory"
+
+        #slow path, search all
+        f.seek(0, 0)
+        for j in f:
+                m = re.split('-|:',j,2)
+                if long(m[0], 16) <= phys_addr <= long(m[1], 16):
+                        return m[2]
+        return "N/A"
+
+def process_event(param_dict):
+        name       = param_dict["ev_name"]
+        sample     = param_dict["sample"]
+        phys_addr  = sample["phys_addr"]
+
+        global event_name
+        if event_name == None:
+                event_name = name
+        load_mem_type_cnt[find_memory_type(phys_addr)] += 1
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index c180bbcdbef6..97f64ad7fa08 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -124,6 +124,12 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
         WRITE_ASS(exclude_guest,  "d");
         WRITE_ASS(exclude_callchain_kernel, "d");
         WRITE_ASS(exclude_callchain_user, "d");
+        WRITE_ASS(mmap2,          "d");
+        WRITE_ASS(comm_exec,      "d");
+        WRITE_ASS(context_switch, "d");
+        WRITE_ASS(write_backward, "d");
+        WRITE_ASS(namespaces,     "d");
+        WRITE_ASS(use_clockid,    "d");
         WRITE_ASS(wakeup_events, PRIu32);
         WRITE_ASS(bp_type, PRIu32);
         WRITE_ASS(config1, "llu");
@@ -167,7 +173,7 @@ static int run_dir(const char *d, const char *perf)
         snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
                  d, d, perf, vcnt, v);
 
-        return system(cmd);
+        return system(cmd) ? TEST_FAIL : TEST_OK;
 }
 
 int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index 907b1b2f56ad..ff9b60b99f52 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -238,6 +238,7 @@ class Test(object):
         # events in result. Fail if there's not any.
         for exp_name, exp_event in expect.items():
             exp_list = []
+            res_event = {}
             log.debug("    matching [%s]" % exp_name)
             for res_name, res_event in result.items():
                 log.debug("      to [%s]" % res_name)
@@ -254,7 +255,10 @@ class Test(object):
                 if exp_event.optional():
                     log.debug("    %s does not match, but is optional" % exp_name)
                 else:
-                    exp_event.diff(res_event)
+                    if not res_event:
+                        log.debug("    res_event is empty");
+                    else:
+                        exp_event.diff(res_event)
                     raise Fail(self, 'match failure');
 
             match[exp_name] = exp_list
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 31e0b1da830b..37940665f736 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -23,7 +23,7 @@ comm=1
 freq=1
 inherit_stat=0
 enable_on_exec=1
-task=0
+task=1
 watermark=0
 precise_ip=0|1|2|3
 mmap_data=0
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index 6e7961f6f7a5..618ba1c17474 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -17,5 +17,6 @@ sample_type=327
 read_format=4
 mmap=0
 comm=0
+task=0
 enable_on_exec=0
 disabled=0
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index ef59afd6d635..f906b793196f 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -23,7 +23,7 @@ sample_type=343
 
 # PERF_FORMAT_ID | PERF_FORMAT_GROUP
 read_format=12
-
+task=0
 mmap=0
 comm=0
 enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
index 87a222d014d8..48e8bd12fe46 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -18,5 +18,6 @@ sample_type=327
 read_format=4
 mmap=0
 comm=0
+task=0
 enable_on_exec=0
 disabled=0
diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0
index 67717fe6a65d..a2c76d10b2bb 100644
--- a/tools/perf/tests/attr/test-stat-C0
+++ b/tools/perf/tests/attr/test-stat-C0
@@ -7,3 +7,4 @@ ret     = 1
 # events are disabled by default when attached to cpu
 disabled=1
 enable_on_exec=0
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-basic b/tools/perf/tests/attr/test-stat-basic
index 74e17881f2ba..69867d049fda 100644
--- a/tools/perf/tests/attr/test-stat-basic
+++ b/tools/perf/tests/attr/test-stat-basic
@@ -4,3 +4,4 @@ args    = -e cycles kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-stat]
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
index e911dbd4eb47..d9e99b3f77e6 100644
--- a/tools/perf/tests/attr/test-stat-default
+++ b/tools/perf/tests/attr/test-stat-default
@@ -32,6 +32,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -52,15 +53,18 @@ optional=1
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
index b39270a08e74..8b04a055d154 100644
--- a/tools/perf/tests/attr/test-stat-detailed-1
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -33,6 +33,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -53,18 +54,21 @@ optional=1
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -74,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -83,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -92,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -101,3 +108,4 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
index 45f8e6ea34f8..4fca9f1bfbf8 100644
--- a/tools/perf/tests/attr/test-stat-detailed-2
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -33,6 +33,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -53,18 +54,21 @@ optional=1
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -74,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -83,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -92,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -101,6 +108,7 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -120,6 +128,7 @@ optional=1
 fd=16
 type=3
 config=65537
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -129,6 +138,7 @@ config=65537
 fd=17
 type=3
 config=3
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -138,6 +148,7 @@ config=3
 fd=18
 type=3
 config=65539
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -147,6 +158,7 @@ config=65539
 fd=19
 type=3
 config=4
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -156,3 +168,4 @@ config=4
 fd=20
 type=3
 config=65540
+optional=1
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
index 30ae0fb7a3fd..4bb58e1c82a6 100644
--- a/tools/perf/tests/attr/test-stat-detailed-3
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -33,6 +33,7 @@ config=2
 fd=5
 type=0
 config=0
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
 [event6:base-stat]
@@ -53,18 +54,21 @@ optional=1
 fd=8
 type=0
 config=1
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
 [event9:base-stat]
 fd=9
 type=0
 config=4
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
 [event10:base-stat]
 fd=10
 type=0
 config=5
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -74,6 +78,7 @@ config=5
 fd=11
 type=3
 config=0
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -83,6 +88,7 @@ config=0
 fd=12
 type=3
 config=65536
+optional=1
 
 # PERF_TYPE_HW_CACHE /
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -92,6 +98,7 @@ config=65536
 fd=13
 type=3
 config=2
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_LL                 <<  0  |
@@ -101,6 +108,7 @@ config=2
 fd=14
 type=3
 config=65538
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -120,6 +128,7 @@ optional=1
 fd=16
 type=3
 config=65537
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -129,6 +138,7 @@ config=65537
 fd=17
 type=3
 config=3
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
@@ -138,6 +148,7 @@ config=3
 fd=18
 type=3
 config=65539
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -147,6 +158,7 @@ config=65539
 fd=19
 type=3
 config=4
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
@@ -156,6 +168,7 @@ config=4
 fd=20
 type=3
 config=65540
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
diff --git a/tools/perf/tests/attr/test-stat-group b/tools/perf/tests/attr/test-stat-group
index fdc1596a8862..e15d6946e9b3 100644
--- a/tools/perf/tests/attr/test-stat-group
+++ b/tools/perf/tests/attr/test-stat-group
@@ -6,6 +6,7 @@ ret     = 1
 [event-1:base-stat]
 fd=1
 group_fd=-1
+read_format=3|15
 
 [event-2:base-stat]
 fd=2
@@ -13,3 +14,4 @@ group_fd=1
 config=1
 disabled=0
 enable_on_exec=0
+read_format=3|15
diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1
index 2a1f86e4a904..1746751123dc 100644
--- a/tools/perf/tests/attr/test-stat-group1
+++ b/tools/perf/tests/attr/test-stat-group1
@@ -6,6 +6,7 @@ ret     = 1
 [event-1:base-stat]
 fd=1
 group_fd=-1
+read_format=3|15
 
 [event-2:base-stat]
 fd=2
@@ -13,3 +14,4 @@ group_fd=1
 config=1
 disabled=0
 enable_on_exec=0
+read_format=3|15
diff --git a/tools/perf/tests/attr/test-stat-no-inherit b/tools/perf/tests/attr/test-stat-no-inherit
index d54b2a1e3e28..924fbb9300d1 100644
--- a/tools/perf/tests/attr/test-stat-no-inherit
+++ b/tools/perf/tests/attr/test-stat-no-inherit
@@ -5,3 +5,4 @@ ret     = 1
 
 [event:base-stat]
 inherit=0
+optional=1
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 71b9a0b613d2..e0b1b414d466 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -31,10 +31,12 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
         int i;
 
         for (i = 0; i < evlist->nr_mmaps; i++) {
+                struct perf_mmap *map = &evlist->overwrite_mmap[i];
                 union perf_event *event;
+                u64 start, end;
 
-                perf_mmap__read_catchup(&evlist->backward_mmap[i]);
-                while ((event = perf_mmap__read_backward(&evlist->backward_mmap[i])) != NULL) {
+                perf_mmap__read_init(map, true, &start, &end);
+                while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) {
                         const u32 type = event->header.type;
 
                         switch (type) {
@@ -49,6 +51,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
                                 return TEST_FAIL;
                         }
                 }
+                perf_mmap__read_done(map);
         }
         return TEST_OK;
 }
@@ -59,7 +62,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
         int err;
         char sbuf[STRERR_BUFSIZE];
 
-        err = perf_evlist__mmap(evlist, mmap_pages, true);
+        err = perf_evlist__mmap(evlist, mmap_pages);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
                          str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 335b695f4970..a467615c5a0e 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -296,7 +296,7 @@ bool test__bp_signal_is_supported(void)
  * instruction breakpoint using the perf event interface.
  * Once it's there we can release this.
  */
-#ifdef __powerpc__
+#if defined(__powerpc__) || defined(__s390x__)
         return false;
 #else
         return true;
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index 268e5f8e4aa2..e4123c1b0e88 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -31,8 +31,8 @@ struct bpf_map_def SEC("maps") flip_table = {
         .max_entries = 1,
 };
 
-SEC("func=SyS_epoll_wait")
-int bpf_func__SyS_epoll_wait(void *ctx)
+SEC("func=SyS_epoll_pwait")
+int bpf_func__SyS_epoll_pwait(void *ctx)
 {
         int ind =0;
         int *flag = bpf_map_lookup_elem(&flip_table, &ind);
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 34c22cdf4d5d..e8399beca62b 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -3,6 +3,7 @@
 #include <sys/epoll.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
@@ -19,13 +20,13 @@
 
 #ifdef HAVE_LIBBPF_SUPPORT
 
-static int epoll_wait_loop(void)
+static int epoll_pwait_loop(void)
 {
         int i;
 
         /* Should fail NR_ITERS times */
         for (i = 0; i < NR_ITERS; i++)
-                epoll_wait(-(i + 1), NULL, 0, 0);
+                epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
         return 0;
 }
 
@@ -63,46 +64,41 @@ static struct {
         bool    pin;
 } bpf_testcase_table[] = {
         {
-                LLVM_TESTCASE_BASE,
-                "Basic BPF filtering",
-                "[basic_bpf_test]",
-                "fix 'perf test LLVM' first",
-                "load bpf object failed",
-                &epoll_wait_loop,
-                (NR_ITERS + 1) / 2,
-                false,
+                .prog_id          = LLVM_TESTCASE_BASE,
+                .desc             = "Basic BPF filtering",
+                .name             = "[basic_bpf_test]",
+                .msg_compile_fail = "fix 'perf test LLVM' first",
+                .msg_load_fail    = "load bpf object failed",
+                .target_func      = &epoll_pwait_loop,
+                .expect_result    = (NR_ITERS + 1) / 2,
         },
         {
-                LLVM_TESTCASE_BASE,
-                "BPF pinning",
-                "[bpf_pinning]",
-                "fix kbuild first",
-                "check your vmlinux setting?",
-                &epoll_wait_loop,
-                (NR_ITERS + 1) / 2,
-                true,
+                .prog_id          = LLVM_TESTCASE_BASE,
+                .desc             = "BPF pinning",
+                .name             = "[bpf_pinning]",
+                .msg_compile_fail = "fix kbuild first",
+                .msg_load_fail    = "check your vmlinux setting?",
+                .target_func      = &epoll_pwait_loop,
+                .expect_result    = (NR_ITERS + 1) / 2,
+                .pin              = true,
         },
 #ifdef HAVE_BPF_PROLOGUE
         {
-                LLVM_TESTCASE_BPF_PROLOGUE,
-                "BPF prologue generation",
-                "[bpf_prologue_test]",
-                "fix kbuild first",
-                "check your vmlinux setting?",
-                &llseek_loop,
-                (NR_ITERS + 1) / 4,
-                false,
+                .prog_id          = LLVM_TESTCASE_BPF_PROLOGUE,
+                .desc             = "BPF prologue generation",
+                .name             = "[bpf_prologue_test]",
+                .msg_compile_fail = "fix kbuild first",
+                .msg_load_fail    = "check your vmlinux setting?",
+                .target_func      = &llseek_loop,
+                .expect_result    = (NR_ITERS + 1) / 4,
         },
 #endif
         {
-                LLVM_TESTCASE_BPF_RELOCATION,
-                "BPF relocation checker",
-                "[bpf_relocation_test]",
-                "fix 'perf test LLVM' first",
-                "libbpf error when dealing with relocation",
-                NULL,
-                0,
-                false,
+                .prog_id          = LLVM_TESTCASE_BPF_RELOCATION,
+                .desc             = "BPF relocation checker",
+                .name             = "[bpf_relocation_test]",
+                .msg_compile_fail = "fix 'perf test LLVM' first",
+                .msg_load_fail    = "libbpf error when dealing with relocation",
         },
 };
 
@@ -167,7 +163,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
                 goto out_delete_evlist;
         }
 
-        err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+        err = perf_evlist__mmap(evlist, opts.mmap_pages);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
                          str_error_r(errno, sbuf, sizeof(sbuf)));
@@ -190,7 +186,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
         }
 
         if (count != expect) {
-                pr_debug("BPF filter result incorrect\n");
+                pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count);
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 53d06f37406a..fafa014240cd 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -4,6 +4,7 @@
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <fcntl.h>
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
@@ -410,9 +411,9 @@ static const char *shell_test__description(char *description, size_t size,
         return description ? trim(description + 1) : NULL;
 }
 
-#define for_each_shell_test(dir, ent)           \
+#define for_each_shell_test(dir, base, ent)     \
         while ((ent = readdir(dir)) != NULL)    \
-                if (ent->d_type == DT_REG && ent->d_name[0] != '.')
+                if (!is_directory(base, ent))
 
 static const char *shell_tests__dir(char *path, size_t size)
 {
@@ -451,7 +452,7 @@ static int shell_tests__max_desc_width(void)
         if (!dir)
                 return -1;
 
-        for_each_shell_test(dir, ent) {
+        for_each_shell_test(dir, path, ent) {
                 char bf[256];
                 const char *desc = shell_test__description(bf, sizeof(bf), path, ent->d_name);
 
@@ -503,7 +504,7 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width)
         if (!dir)
                 return -1;
 
-        for_each_shell_test(dir, ent) {
+        for_each_shell_test(dir, st.dir, ent) {
                 int curr = i++;
                 char desc[256];
                 struct test test = {
@@ -613,7 +614,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i)
         if (!dir)
                 return -1;
 
-        for_each_shell_test(dir, ent) {
+        for_each_shell_test(dir, path, ent) {
                 int curr = i++;
                 char bf[256];
                 struct test t = {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index fcc8984bc329..3bf7b145b826 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -639,7 +639,7 @@ static int do_test_code_reading(bool try_kcore)
                 break;
         }
 
-        ret = perf_evlist__mmap(evlist, UINT_MAX, false);
+        ret = perf_evlist__mmap(evlist, UINT_MAX);
         if (ret < 0) {
                 pr_debug("perf_evlist__mmap failed\n");
                 goto out_put;
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index ac40e05bcab4..260418969120 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -173,6 +173,7 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu
         }
 
         callchain_param.record_mode = CALLCHAIN_DWARF;
+        dwarf_callchain_users = true;
 
         if (init_live_machine(machine)) {
                 pr_err("Could not init machine\n");
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 842d33637a18..c46530918938 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -95,7 +95,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un
                 goto out_err;
         }
 
-        CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+        CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
 
         /*
          * First, test that a 'comm' event can be found when the event is
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5a8bf318f8a7..c0e971da965c 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -94,7 +94,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
                 expected_nr_events[i] = 1 + rand() % 127;
         }
 
-        if (perf_evlist__mmap(evlist, 128, true) < 0) {
+        if (perf_evlist__mmap(evlist, 128) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
                          str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 3c3f3e029e33..868d82b501f4 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -132,7 +132,7 @@ static int synth_all(struct machine *machine)
 {
         return perf_event__synthesize_threads(NULL,
                                               perf_event__process,
-                                              machine, 0, 500);
+                                              machine, 0, 500, 1);
 }
 
 static int synth_process(struct machine *machine)
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index d9619d265314..43519267b93b 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/err.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include "perf.h"
 #include "evlist.h"
 #include "evsel.h"
@@ -64,7 +67,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
                 goto out_delete_evlist;
         }
 
-        err = perf_evlist__mmap(evlist, UINT_MAX, false);
+        err = perf_evlist__mmap(evlist, UINT_MAX);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
                          str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index f0679613bd18..18b06444f230 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -13,7 +13,6 @@
 #include <unistd.h>
 #include <linux/kernel.h>
 #include <linux/hw_breakpoint.h>
-#include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
 
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index c34904d37705..0afafab85238 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -141,7 +141,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
          * fds in the same CPU to be injected in the same mmap ring buffer
          * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
          */
-        err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+        err = perf_evlist__mmap(evlist, opts.mmap_pages);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
                          str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 3ec6302b6498..0e2d00d69e6e 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -248,7 +248,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
         event->header.size = sz;
 
         err = perf_event__synthesize_sample(event, sample_type, read_format,
-                                            &sample, false);
+                                            &sample);
         if (err) {
                 pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
                          "perf_event__synthesize_sample", sample_type, err);
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 7a84d73324e3..c446c894b297 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,8 +10,8 @@
 
 . $(dirname $0)/lib/probe.sh
 
-ld=$(realpath /lib64/ld*.so.* | uniq)
-libc=$(echo $ld | sed 's/ld/libc/g')
+libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
+nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
         idx=0
@@ -22,10 +22,23 @@ trace_libc_inet_pton_backtrace() {
         expected[4]="rtt min.*"
         expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
         expected[6]=".*inet_pton[[:space:]]\($libc\)$"
-        expected[7]="getaddrinfo[[:space:]]\($libc\)$"
-        expected[8]=".*\(.*/bin/ping.*\)$"
+        case "$(uname -m)" in
+        s390x)
+                eventattr='call-graph=dwarf'
+                expected[7]="gaih_inet[[:space:]]\(inlined\)$"
+                expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$"
+                expected[9]="main[[:space:]]\(.*/bin/ping.*\)$"
+                expected[10]="__libc_start_main[[:space:]]\($libc\)$"
+                expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$"
+                ;;
+        *)
+                eventattr='max-stack=3'
+                expected[7]="getaddrinfo[[:space:]]\($libc\)$"
+                expected[8]=".*\(.*/bin/ping.*\)$"
+                ;;
+        esac
 
-        perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
+        perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
                 echo $line
                 echo "$line" | egrep -q "${expected[$idx]}"
                 if [ $? -ne 0 ] ; then
@@ -33,10 +46,13 @@ trace_libc_inet_pton_backtrace() {
                         exit 1
                 fi
                 let idx+=1
-                [ $idx -eq 9 ] && break
+                [ -z "${expected[$idx]}" ] && break
         done
 }
 
+# Check for IPv6 interface existence
+ip a sh lo | fgrep -q inet6 || exit 2
+
 skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 2e68c5f120da..55ad9793d544 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,8 +17,9 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-        perf trace -e open touch $file 2>&1 | \
-        egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+        evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+        perf trace -e $evts touch $file 2>&1 | \
+        egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 725a196991a8..f6c72f915d48 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
                 goto out_delete_evlist;
         }
 
-        err = perf_evlist__mmap(evlist, 128, true);
+        err = perf_evlist__mmap(evlist, 128);
         if (err < 0) {
                 pr_debug("failed to mmap event: %d (%s)\n", errno,
                          str_error_r(errno, sbuf, sizeof(sbuf)));
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 7d3f4bf9534f..33e00295a972 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -449,7 +449,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
                 goto out;
         }
 
-        err = perf_evlist__mmap(evlist, UINT_MAX, false);
+        err = perf_evlist__mmap(evlist, UINT_MAX);
         if (err) {
                 pr_debug("perf_evlist__mmap failed!\n");
                 goto out_err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bc4a7344e274..01b62b81751b 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
         evsel = perf_evlist__first(evlist);
         evsel->attr.task = 1;
+#ifdef __s390x__
+        evsel->attr.sample_freq = 1000000;
+#else
         evsel->attr.sample_freq = 1;
+#endif
         evsel->attr.inherit = 0;
         evsel->attr.watermark = 0;
         evsel->attr.wakeup_events = 1;
@@ -97,7 +101,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
                 goto out_delete_evlist;
         }
 
-        if (perf_evlist__mmap(evlist, 128, true) < 0) {
+        if (perf_evlist__mmap(evlist, 128) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
                          str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index dbcb6a19b375..4de1939b58ba 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -105,7 +105,7 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
         TEST_ASSERT_VAL("failed to allocate map string",
                         asprintf(&str, "%d,%d", getpid(), getppid()) >= 0);
 
-        threads = thread_map__new_str(str, NULL, 0);
+        threads = thread_map__new_str(str, NULL, 0, false);
 
         TEST_ASSERT_VAL("failed to allocate thread_map",
                         threads);
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index a59db7c45a65..17cb1bb3448c 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -30,12 +30,14 @@ static int get_temp(char *path)
 static int session_write_header(char *path)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = path,
-                .mode = PERF_DATA_MODE_WRITE,
+        struct perf_data data = {
+                .file      = {
+                        .path = path,
+                },
+                .mode      = PERF_DATA_MODE_WRITE,
         };
 
-        session = perf_session__new(&file, false, NULL);
+        session = perf_session__new(&data, false, NULL);
         TEST_ASSERT_VAL("can't get session", session);
 
         session->evlist = perf_evlist__new_default();
@@ -47,7 +49,7 @@ static int session_write_header(char *path)
         session->header.data_size += DATA_SIZE;
 
         TEST_ASSERT_VAL("failed to write header",
-                        !perf_session__write_header(session, session->evlist, file.fd, true));
+                        !perf_session__write_header(session, session->evlist, data.file.fd, true));
 
         perf_session__delete(session);
 
@@ -57,13 +59,15 @@ static int session_write_header(char *path)
 static int check_cpu_topology(char *path, struct cpu_map *map)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = path,
-                .mode = PERF_DATA_MODE_READ,
+        struct perf_data data = {
+                .file      = {
+                        .path = path,
+                },
+                .mode      = PERF_DATA_MODE_READ,
         };
         int i;
 
-        session = perf_session__new(&file, false, NULL);
+        session = perf_session__new(&data, false, NULL);
         TEST_ASSERT_VAL("can't get session", session);
 
         for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 175d633c6b49..66330d4b739b 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -1,7 +1,10 @@
 libperf-y += clone.o
 libperf-y += fcntl.o
+libperf-y += flock.o
 ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
 libperf-y += ioctl.o
 endif
+libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
+libperf-y += prctl.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/arch_errno_names.c b/tools/perf/trace/beauty/arch_errno_names.c
new file mode 100644
index 000000000000..ede031c3a9e0
--- /dev/null
+++ b/tools/perf/trace/beauty/arch_errno_names.c
@@ -0,0 +1 @@
+#include "trace/beauty/generated/arch_errno_name_array.c"
diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
new file mode 100755
index 000000000000..22c9fc900c84
--- /dev/null
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -0,0 +1,100 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate C file mapping errno codes to errno names.
+#
+# Copyright IBM Corp. 2018
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+
+gcc="$1"
+toolsdir="$2"
+include_path="-I$toolsdir/include/uapi"
+
+arch_string()
+{
+        echo "$1" |sed -e 'y/- /__/' |tr '[[:upper:]]' '[[:lower:]]'
+}
+
+asm_errno_file()
+{
+        local arch="$1"
+        local header
+
+        header="$toolsdir/arch/$arch/include/uapi/asm/errno.h"
+        if test -r "$header"; then
+                echo "$header"
+        else
+                echo "$toolsdir/include/uapi/asm-generic/errno.h"
+        fi
+}
+
+create_errno_lookup_func()
+{
+        local arch=$(arch_string "$1")
+        local nr name
+
+        cat <<EoFuncBegin
+static const char *errno_to_name__$arch(int err)
+{
+        switch (err) {
+EoFuncBegin
+
+        while read name nr; do
+                printf '\tcase %d: return "%s";\n' $nr $name
+        done
+
+        cat <<EoFuncEnd
+        default:
+                return "(unknown)";
+        }
+}
+
+EoFuncEnd
+}
+
+process_arch()
+{
+        local arch="$1"
+        local asm_errno=$(asm_errno_file "$arch")
+
+        $gcc $include_path -E -dM -x c $asm_errno \
+                |grep -hE '^#define[[:blank:]]+(E[^[:blank:]]+)[[:blank:]]+([[:digit:]]+).*' \
+                |awk '{ print $2","$3; }' \
+                |sort -t, -k2 -nu \
+                |IFS=, create_errno_lookup_func "$arch"
+}
+
+create_arch_errno_table_func()
+{
+        local archlist="$1"
+        local default="$2"
+        local arch
+
+        printf 'const char *arch_syscalls__strerrno(const char *arch, int err)\n'
+        printf '{\n'
+        for arch in $archlist; do
+                printf '\tif (!strcmp(arch, "%s"))\n' $(arch_string "$arch")
+                printf '\t\treturn errno_to_name__%s(err);\n' $(arch_string "$arch")
+        done
+        printf '\treturn errno_to_name__%s(err);\n' $(arch_string "$default")
+        printf '}\n'
+}
+
+cat <<EoHEADER
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <string.h>
+
+EoHEADER
+
+# Create list of architectures and ignore those that do not appear
+# in tools/perf/arch
+archlist=""
+for arch in $(find $toolsdir/arch -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | grep -v x86 | sort); do
+        test -d arch/$arch && archlist="$archlist $arch"
+done
+
+for arch in x86 $archlist generic; do
+        process_arch "$arch"
+done
+create_arch_errno_table_func "x86 $archlist" "generic"
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index d80655cd1881..984a504d335c 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -4,6 +4,7 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <sys/types.h>
 
 struct strarray {
         int         offset;
@@ -27,6 +28,8 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 struct trace;
 struct thread;
 
+size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
+
 /**
  * @val: value of syscall argument being formatted
  * @args: All the args, use syscall_args__val(arg, nth) to access one
@@ -76,15 +79,33 @@ size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_FCNTL_ARG syscall_arg__scnprintf_fcntl_arg
 
+size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FLOCK syscall_arg__scnprintf_flock
+
 size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_IOCTL_CMD syscall_arg__scnprintf_ioctl_cmd
 
+size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_KCMP_TYPE syscall_arg__scnprintf_kcmp_type
+
+size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_KCMP_IDX syscall_arg__scnprintf_kcmp_idx
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
 
 size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
 
+size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option
+
+size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2
+
+size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
@@ -96,4 +117,6 @@ size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size);
 void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
                                     size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg));
 
+const char *arch_syscalls__strerrno(const char *arch, int err);
+
 #endif /* _PERF_TRACE_BEAUTY_H */
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index f9707f57566c..c4ff6ad30b06 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <fcntl.h>
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <uapi/linux/fcntl.h>
 
 #ifndef LOCK_MAND
 #define LOCK_MAND        32
@@ -17,8 +20,7 @@
 #define LOCK_RW         192
 #endif
 
-static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
-                                           struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg)
 {
         int printed = 0, op = arg->val;
 
@@ -45,5 +47,3 @@ static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
 
         return printed;
 }
-
-#define SCA_FLOCK syscall_arg__scnprintf_flock
diff --git a/tools/perf/trace/beauty/futex_val3.c b/tools/perf/trace/beauty/futex_val3.c
new file mode 100644
index 000000000000..26f6b3253511
--- /dev/null
+++ b/tools/perf/trace/beauty/futex_val3.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/futex.h>
+
+#ifndef FUTEX_BITSET_MATCH_ANY
+#define FUTEX_BITSET_MATCH_ANY 0xffffffff
+#endif
+
+static size_t syscall_arg__scnprintf_futex_val3(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned int bitset = arg->val;
+
+        if (bitset == FUTEX_BITSET_MATCH_ANY)
+                return scnprintf(bf, size, "MATCH_ANY");
+
+        return scnprintf(bf, size, "%#xd", bitset);
+}
+
+#define SCA_FUTEX_VAL3  syscall_arg__scnprintf_futex_val3
diff --git a/tools/perf/trace/beauty/kcmp.c b/tools/perf/trace/beauty/kcmp.c
new file mode 100644
index 000000000000..f62040eb9d5c
--- /dev/null
+++ b/tools/perf/trace/beauty/kcmp.c
@@ -0,0 +1,44 @@
+/*
+ * trace/beauty/kcmp.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <machine.h>
+#include <uapi/linux/kcmp.h>
+
+#include "trace/beauty/generated/kcmp_type_array.c"
+
+size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long fd = arg->val;
+        int type = syscall_arg__val(arg, 2);
+        pid_t pid;
+
+        if (type != KCMP_FILE)
+                return syscall_arg__scnprintf_long(bf, size, arg);
+
+        pid = syscall_arg__val(arg, arg->idx == 3 ? 0 : 1); /* idx1 -> pid1, idx2 -> pid2 */
+        return pid__scnprintf_fd(arg->trace, pid, fd, bf, size);
+}
+
+static size_t kcmp__scnprintf_type(int type, char *bf, size_t size)
+{
+        static DEFINE_STRARRAY(kcmp_types);
+        return strarray__scnprintf(&strarray__kcmp_types, bf, size, "%d", type);
+}
+
+size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long type = arg->val;
+
+        if (type != KCMP_FILE)
+                arg->mask |= (1 << 3) | (1 << 4); /* Ignore idx1 and idx2 */
+
+        return kcmp__scnprintf_type(type, bf, size);
+}
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
new file mode 100755
index 000000000000..40d063b8c082
--- /dev/null
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *kcmp_types[] = {\n"
+regex='^[[:space:]]+(KCMP_(\w+)),'
+egrep $regex ${header_dir}/kcmp.h | grep -v KCMP_TYPES, | \
+        sed -r "s/$regex/\1 \2/g" | \
+        xargs printf "\t[%s]\t= \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
new file mode 100755
index 000000000000..60ef8640ee70
--- /dev/null
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *madvise_advices[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
+egrep $regex ${header_dir}/mman-common.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 51f1cea406f5..417e3ecfe9d7 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -62,6 +62,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
         P_MMAP_FLAG(POPULATE);
         P_MMAP_FLAG(STACK);
         P_MMAP_FLAG(UNINITIALIZED);
+#ifdef MAP_SYNC
+        P_MMAP_FLAG(SYNC);
+#endif
 #undef P_MMAP_FLAG
 
         if (flags)
@@ -95,35 +98,21 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 
 #define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
 
+static size_t madvise__scnprintf_behavior(int behavior, char *bf, size_t size)
+{
+#include "trace/beauty/generated/madvise_behavior_array.c"
+       static DEFINE_STRARRAY(madvise_advices);
+
+       if (behavior < strarray__madvise_advices.nr_entries && strarray__madvise_advices.entries[behavior] != NULL)
+               return scnprintf(bf, size, "MADV_%s", strarray__madvise_advices.entries[behavior]);
+
+       return scnprintf(bf, size, "%#", behavior);
+}
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
                                                       struct syscall_arg *arg)
 {
-        int behavior = arg->val;
-
-        switch (behavior) {
-#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
-        P_MADV_BHV(NORMAL);
-        P_MADV_BHV(RANDOM);
-        P_MADV_BHV(SEQUENTIAL);
-        P_MADV_BHV(WILLNEED);
-        P_MADV_BHV(DONTNEED);
-        P_MADV_BHV(FREE);
-        P_MADV_BHV(REMOVE);
-        P_MADV_BHV(DONTFORK);
-        P_MADV_BHV(DOFORK);
-        P_MADV_BHV(HWPOISON);
-        P_MADV_BHV(SOFT_OFFLINE);
-        P_MADV_BHV(MERGEABLE);
-        P_MADV_BHV(UNMERGEABLE);
-        P_MADV_BHV(HUGEPAGE);
-        P_MADV_BHV(NOHUGEPAGE);
-        P_MADV_BHV(DONTDUMP);
-        P_MADV_BHV(DODUMP);
-#undef P_MADV_BHV
-        default: break;
-        }
-
-        return scnprintf(bf, size, "%#x", behavior);
+        return madvise__scnprintf_behavior(arg->val, bf, size);
 }
 
 #define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
new file mode 100644
index 000000000000..246130dad6c4
--- /dev/null
+++ b/tools/perf/trace/beauty/prctl.c
@@ -0,0 +1,82 @@
+/*
+ * trace/beauty/prctl.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <uapi/linux/prctl.h>
+
+#include "trace/beauty/generated/prctl_option_array.c"
+
+static size_t prctl__scnprintf_option(int option, char *bf, size_t size)
+{
+        static DEFINE_STRARRAY(prctl_options);
+        return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", option);
+}
+
+static size_t prctl__scnprintf_set_mm(int option, char *bf, size_t size)
+{
+        static DEFINE_STRARRAY(prctl_set_mm_options);
+        return strarray__scnprintf(&strarray__prctl_set_mm_options, bf, size, "%d", option);
+}
+
+size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int option = syscall_arg__val(arg, 0);
+
+        if (option == PR_SET_MM)
+                return prctl__scnprintf_set_mm(arg->val, bf, size);
+        /*
+         * We still don't grab the contents of pointers on entry or exit,
+         * so just print them as hex numbers
+         */
+        if (option == PR_SET_NAME)
+                return syscall_arg__scnprintf_hex(bf, size, arg);
+
+        return syscall_arg__scnprintf_long(bf, size, arg);
+}
+
+size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int option = syscall_arg__val(arg, 0);
+
+        if (option == PR_SET_MM)
+                return syscall_arg__scnprintf_hex(bf, size, arg);
+
+        return syscall_arg__scnprintf_long(bf, size, arg);
+}
+
+size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long option = arg->val;
+        enum {
+                SPO_ARG2 = (1 << 1),
+                SPO_ARG3 = (1 << 2),
+                SPO_ARG4 = (1 << 3),
+                SPO_ARG5 = (1 << 4),
+                SPO_ARG6 = (1 << 5),
+        };
+        const u8 all_but2 = SPO_ARG3 | SPO_ARG4 | SPO_ARG5 | SPO_ARG6;
+        const u8 all = SPO_ARG2 | all_but2;
+        const u8 masks[] = {
+                [PR_GET_DUMPABLE]        = all,
+                [PR_SET_DUMPABLE]        = all_but2,
+                [PR_SET_NAME]            = all_but2,
+                [PR_GET_CHILD_SUBREAPER] = all_but2,
+                [PR_SET_CHILD_SUBREAPER] = all_but2,
+                [PR_GET_SECUREBITS]      = all,
+                [PR_SET_SECUREBITS]      = all_but2,
+                [PR_SET_MM]              = SPO_ARG4 | SPO_ARG5 | SPO_ARG6,
+                [PR_GET_PDEATHSIG]       = all,
+                [PR_SET_PDEATHSIG]       = all_but2,
+        };
+
+        if (option < ARRAY_SIZE(masks))
+                arg->mask |= masks[option];
+
+        return prctl__scnprintf_option(option, bf, size);
+}
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
new file mode 100755
index 000000000000..0be4138fbe71
--- /dev/null
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -0,0 +1,17 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *prctl_options[] = {\n"
+regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
+egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
+
+printf "static const char *prctl_set_mm_options[] = {\n"
+regex='^#[[:space:]]+define[[:space:]]+PR_SET_MM_(\w+)[[:space:]]*([[:digit:]]+).*'
+egrep $regex ${header_dir}/prctl.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 8f7f59d1a2b5..286427975112 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -25,16 +25,10 @@ struct disasm_line_samples {
 #define IPC_WIDTH 6
 #define CYCLES_WIDTH 6
 
-struct browser_disasm_line {
-        struct rb_node                  rb_node;
-        u32                             idx;
-        int                             idx_asm;
-        int                             jump_sources;
-        /*
-         * actual length of this array is saved on the nr_events field
-         * of the struct annotate_browser
-         */
-        struct disasm_line_samples      samples[1];
+struct browser_line {
+        u32     idx;
+        int     idx_asm;
+        int     jump_sources;
 };
 
 static struct annotate_browser_opt {
@@ -53,39 +47,43 @@ static struct annotate_browser_opt {
 struct arch;
 
 struct annotate_browser {
-        struct ui_browser b;
-        struct rb_root    entries;
-        struct rb_node    *curr_hot;
-        struct disasm_line  *selection;
-        struct disasm_line  **offsets;
-        struct arch         *arch;
-        int                 nr_events;
-        u64                 start;
-        int                 nr_asm_entries;
-        int                 nr_entries;
-        int                 max_jump_sources;
-        int                 nr_jumps;
-        bool                searching_backwards;
-        bool                have_cycles;
-        u8                  addr_width;
-        u8                  jumps_width;
-        u8                  target_width;
-        u8                  min_addr_width;
-        u8                  max_addr_width;
-        char                search_bf[128];
+        struct ui_browser           b;
+        struct rb_root              entries;
+        struct rb_node             *curr_hot;
+        struct annotation_line     *selection;
+        struct annotation_line    **offsets;
+        struct arch                *arch;
+        int                         nr_events;
+        u64                         start;
+        int                         nr_asm_entries;
+        int                         nr_entries;
+        int                         max_jump_sources;
+        int                         nr_jumps;
+        bool                        searching_backwards;
+        bool                        have_cycles;
+        u8                          addr_width;
+        u8                          jumps_width;
+        u8                          target_width;
+        u8                          min_addr_width;
+        u8                          max_addr_width;
+        char                        search_bf[128];
 };
 
-static inline struct browser_disasm_line *disasm_line__browser(struct disasm_line *dl)
+static inline struct browser_line *browser_line(struct annotation_line *al)
 {
-        return (struct browser_disasm_line *)(dl + 1);
+        void *ptr = al;
+
+        ptr = container_of(al, struct disasm_line, al);
+        return ptr - sizeof(struct browser_line);
 }
 
 static bool disasm_line__filter(struct ui_browser *browser __maybe_unused,
                                 void *entry)
 {
         if (annotate_browser__opts.hide_src_code) {
-                struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
-                return dl->offset == -1;
+                struct annotation_line *al = list_entry(entry, struct annotation_line, node);
+
+                return al->offset == -1;
         }
 
         return false;
@@ -120,11 +118,37 @@ static int annotate_browser__cycles_width(struct annotate_browser *ab)
         return ab->have_cycles ? IPC_WIDTH + CYCLES_WIDTH : 0;
 }
 
+static void disasm_line__write(struct disasm_line *dl, struct ui_browser *browser,
+                               char *bf, size_t size)
+{
+        if (dl->ins.ops && dl->ins.ops->scnprintf) {
+                if (ins__is_jump(&dl->ins)) {
+                        bool fwd = dl->ops.target.offset > dl->al.offset;
+
+                        ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
+                                                            SLSMG_UARROW_CHAR);
+                        SLsmg_write_char(' ');
+                } else if (ins__is_call(&dl->ins)) {
+                        ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
+                        SLsmg_write_char(' ');
+                } else if (ins__is_ret(&dl->ins)) {
+                        ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
+                        SLsmg_write_char(' ');
+                } else {
+                        ui_browser__write_nstring(browser, " ", 2);
+                }
+        } else {
+                ui_browser__write_nstring(browser, " ", 2);
+        }
+
+        disasm_line__scnprintf(dl, bf, size, !annotate_browser__opts.use_offset);
+}
+
 static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
 {
         struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
-        struct disasm_line *dl = list_entry(entry, struct disasm_line, node);
-        struct browser_disasm_line *bdl = disasm_line__browser(dl);
+        struct annotation_line *al = list_entry(entry, struct annotation_line, node);
+        struct browser_line *bl = browser_line(al);
         bool current_entry = ui_browser__is_current_entry(browser, row);
         bool change_color = (!annotate_browser__opts.hide_src_code &&
                              (!current_entry || (browser->use_navkeypressed &&
@@ -137,32 +161,32 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
         bool show_title = false;
 
         for (i = 0; i < ab->nr_events; i++) {
-                if (bdl->samples[i].percent > percent_max)
-                        percent_max = bdl->samples[i].percent;
+                if (al->samples[i].percent > percent_max)
+                        percent_max = al->samples[i].percent;
         }
 
-        if ((row == 0) && (dl->offset == -1 || percent_max == 0.0)) {
+        if ((row == 0) && (al->offset == -1 || percent_max == 0.0)) {
                 if (ab->have_cycles) {
-                        if (dl->ipc == 0.0 && dl->cycles == 0)
+                        if (al->ipc == 0.0 && al->cycles == 0)
                                 show_title = true;
                 } else
                         show_title = true;
         }
 
-        if (dl->offset != -1 && percent_max != 0.0) {
+        if (al->offset != -1 && percent_max != 0.0) {
                 for (i = 0; i < ab->nr_events; i++) {
                         ui_browser__set_percent_color(browser,
-                                                bdl->samples[i].percent,
+                                                al->samples[i].percent,
                                                 current_entry);
                         if (annotate_browser__opts.show_total_period) {
                                 ui_browser__printf(browser, "%11" PRIu64 " ",
-                                                   bdl->samples[i].he.period);
+                                                   al->samples[i].he.period);
                         } else if (annotate_browser__opts.show_nr_samples) {
                                 ui_browser__printf(browser, "%6" PRIu64 " ",
-                                                   bdl->samples[i].he.nr_samples);
+                                                   al->samples[i].he.nr_samples);
                         } else {
                                 ui_browser__printf(browser, "%6.2f ",
-                                                   bdl->samples[i].percent);
+                                                   al->samples[i].percent);
                         }
                 }
         } else {
@@ -177,16 +201,16 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 }
         }
         if (ab->have_cycles) {
-                if (dl->ipc)
-                        ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, dl->ipc);
+                if (al->ipc)
+                        ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, al->ipc);
                 else if (!show_title)
                         ui_browser__write_nstring(browser, " ", IPC_WIDTH);
                 else
                         ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC");
 
-                if (dl->cycles)
+                if (al->cycles)
                         ui_browser__printf(browser, "%*" PRIu64 " ",
-                                           CYCLES_WIDTH - 1, dl->cycles);
+                                           CYCLES_WIDTH - 1, al->cycles);
                 else if (!show_title)
                         ui_browser__write_nstring(browser, " ", CYCLES_WIDTH);
                 else
@@ -199,19 +223,19 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
         if (!browser->navkeypressed)
                 width += 1;
 
-        if (!*dl->line)
+        if (!*al->line)
                 ui_browser__write_nstring(browser, " ", width - pcnt_width - cycles_width);
-        else if (dl->offset == -1) {
-                if (dl->line_nr && annotate_browser__opts.show_linenr)
+        else if (al->offset == -1) {
+                if (al->line_nr && annotate_browser__opts.show_linenr)
                         printed = scnprintf(bf, sizeof(bf), "%-*d ",
-                                        ab->addr_width + 1, dl->line_nr);
+                                        ab->addr_width + 1, al->line_nr);
                 else
                         printed = scnprintf(bf, sizeof(bf), "%*s  ",
                                     ab->addr_width, " ");
                 ui_browser__write_nstring(browser, bf, printed);
-                ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width - cycles_width + 1);
+                ui_browser__write_nstring(browser, al->line, width - printed - pcnt_width - cycles_width + 1);
         } else {
-                u64 addr = dl->offset;
+                u64 addr = al->offset;
                 int color = -1;
 
                 if (!annotate_browser__opts.use_offset)
@@ -220,13 +244,13 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 if (!annotate_browser__opts.use_offset) {
                         printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
                 } else {
-                        if (bdl->jump_sources) {
+                        if (bl->jump_sources) {
                                 if (annotate_browser__opts.show_nr_jumps) {
                                         int prev;
                                         printed = scnprintf(bf, sizeof(bf), "%*d ",
                                                             ab->jumps_width,
-                                                            bdl->jump_sources);
-                                        prev = annotate_browser__set_jumps_percent_color(ab, bdl->jump_sources,
+                                                            bl->jump_sources);
+                                        prev = annotate_browser__set_jumps_percent_color(ab, bl->jump_sources,
                                                                                          current_entry);
                                         ui_browser__write_nstring(browser, bf, printed);
                                         ui_browser__set_color(browser, prev);
@@ -245,32 +269,14 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 ui_browser__write_nstring(browser, bf, printed);
                 if (change_color)
                         ui_browser__set_color(browser, color);
-                if (dl->ins.ops && dl->ins.ops->scnprintf) {
-                        if (ins__is_jump(&dl->ins)) {
-                                bool fwd = dl->ops.target.offset > dl->offset;
-
-                                ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
-                                                                    SLSMG_UARROW_CHAR);
-                                SLsmg_write_char(' ');
-                        } else if (ins__is_call(&dl->ins)) {
-                                ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
-                                SLsmg_write_char(' ');
-                        } else if (ins__is_ret(&dl->ins)) {
-                                ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
-                                SLsmg_write_char(' ');
-                        } else {
-                                ui_browser__write_nstring(browser, " ", 2);
-                        }
-                } else {
-                        ui_browser__write_nstring(browser, " ", 2);
-                }
 
-                disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
+                disasm_line__write(disasm_line(al), browser, bf, sizeof(bf));
+
                 ui_browser__write_nstring(browser, bf, width - pcnt_width - cycles_width - 3 - printed);
         }
 
         if (current_entry)
-                ab->selection = dl;
+                ab->selection = al;
 }
 
 static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym)
@@ -286,7 +292,7 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy
 
 static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 {
-        struct disasm_line *pos = list_prev_entry(cursor, node);
+        struct disasm_line *pos = list_prev_entry(cursor, al.node);
         const char *name;
 
         if (!pos)
@@ -306,8 +312,9 @@ static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 {
         struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
-        struct disasm_line *cursor = ab->selection, *target;
-        struct browser_disasm_line *btarget, *bcursor;
+        struct disasm_line *cursor = disasm_line(ab->selection);
+        struct annotation_line *target;
+        struct browser_line *btarget, *bcursor;
         unsigned int from, to;
         struct map_symbol *ms = ab->b.priv;
         struct symbol *sym = ms->sym;
@@ -321,11 +328,9 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
                 return;
 
         target = ab->offsets[cursor->ops.target.offset];
-        if (!target)
-                return;
 
-        bcursor = disasm_line__browser(cursor);
-        btarget = disasm_line__browser(target);
+        bcursor = browser_line(&cursor->al);
+        btarget = browser_line(target);
 
         if (annotate_browser__opts.hide_src_code) {
                 from = bcursor->idx_asm;
@@ -361,12 +366,11 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
         return ret;
 }
 
-static int disasm__cmp(struct browser_disasm_line *a,
-                       struct browser_disasm_line *b, int nr_pcnt)
+static int disasm__cmp(struct annotation_line *a, struct annotation_line *b)
 {
         int i;
 
-        for (i = 0; i < nr_pcnt; i++) {
+        for (i = 0; i < a->samples_nr; i++) {
                 if (a->samples[i].percent == b->samples[i].percent)
                         continue;
                 return a->samples[i].percent < b->samples[i].percent;
@@ -374,28 +378,27 @@ static int disasm__cmp(struct browser_disasm_line *a,
         return 0;
 }
 
-static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl,
-                                   int nr_events)
+static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al)
 {
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
-        struct browser_disasm_line *l;
+        struct annotation_line *l;
 
         while (*p != NULL) {
                 parent = *p;
-                l = rb_entry(parent, struct browser_disasm_line, rb_node);
+                l = rb_entry(parent, struct annotation_line, rb_node);
 
-                if (disasm__cmp(bdl, l, nr_events))
+                if (disasm__cmp(al, l))
                         p = &(*p)->rb_left;
                 else
                         p = &(*p)->rb_right;
         }
-        rb_link_node(&bdl->rb_node, parent, p);
-        rb_insert_color(&bdl->rb_node, root);
+        rb_link_node(&al->rb_node, parent, p);
+        rb_insert_color(&al->rb_node, root);
 }
 
 static void annotate_browser__set_top(struct annotate_browser *browser,
-                                      struct disasm_line *pos, u32 idx)
+                                      struct annotation_line *pos, u32 idx)
 {
         unsigned back;
 
@@ -404,7 +407,7 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
         browser->b.top_idx = browser->b.index = idx;
 
         while (browser->b.top_idx != 0 && back != 0) {
-                pos = list_entry(pos->node.prev, struct disasm_line, node);
+                pos = list_entry(pos->node.prev, struct annotation_line, node);
 
                 if (disasm_line__filter(&browser->b, &pos->node))
                         continue;
@@ -420,12 +423,13 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 static void annotate_browser__set_rb_top(struct annotate_browser *browser,
                                          struct rb_node *nd)
 {
-        struct browser_disasm_line *bpos;
-        struct disasm_line *pos;
+        struct browser_line *bpos;
+        struct annotation_line *pos;
         u32 idx;
 
-        bpos = rb_entry(nd, struct browser_disasm_line, rb_node);
-        pos = ((struct disasm_line *)bpos) - 1;
+        pos = rb_entry(nd, struct annotation_line, rb_node);
+        bpos = browser_line(pos);
+
         idx = bpos->idx;
         if (annotate_browser__opts.hide_src_code)
                 idx = bpos->idx_asm;
@@ -439,46 +443,35 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
         struct map_symbol *ms = browser->b.priv;
         struct symbol *sym = ms->sym;
         struct annotation *notes = symbol__annotation(sym);
-        struct disasm_line *pos, *next;
-        s64 len = symbol__size(sym);
+        struct disasm_line *pos;
 
         browser->entries = RB_ROOT;
 
         pthread_mutex_lock(&notes->lock);
 
-        list_for_each_entry(pos, &notes->src->source, node) {
-                struct browser_disasm_line *bpos = disasm_line__browser(pos);
-                const char *path = NULL;
+        symbol__calc_percent(sym, evsel);
+
+        list_for_each_entry(pos, &notes->src->source, al.node) {
                 double max_percent = 0.0;
                 int i;
 
-                if (pos->offset == -1) {
-                        RB_CLEAR_NODE(&bpos->rb_node);
+                if (pos->al.offset == -1) {
+                        RB_CLEAR_NODE(&pos->al.rb_node);
                         continue;
                 }
 
-                next = disasm__get_next_ip_line(&notes->src->source, pos);
-
-                for (i = 0; i < browser->nr_events; i++) {
-                        struct sym_hist_entry sample;
-
-                        bpos->samples[i].percent = disasm__calc_percent(notes,
-                                                evsel->idx + i,
-                                                pos->offset,
-                                                next ? next->offset : len,
-                                                &path, &sample);
-                        bpos->samples[i].he = sample;
+                for (i = 0; i < pos->al.samples_nr; i++) {
+                        struct annotation_data *sample = &pos->al.samples[i];
 
-                        if (max_percent < bpos->samples[i].percent)
-                                max_percent = bpos->samples[i].percent;
+                        if (max_percent < sample->percent)
+                                max_percent = sample->percent;
                 }
 
-                if (max_percent < 0.01 && pos->ipc == 0) {
-                        RB_CLEAR_NODE(&bpos->rb_node);
+                if (max_percent < 0.01 && pos->al.ipc == 0) {
+                        RB_CLEAR_NODE(&pos->al.rb_node);
                         continue;
                 }
-                disasm_rb_tree__insert(&browser->entries, bpos,
-                                       browser->nr_events);
+                disasm_rb_tree__insert(&browser->entries, &pos->al);
         }
         pthread_mutex_unlock(&notes->lock);
 
@@ -487,38 +480,38 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 
 static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 {
-        struct disasm_line *dl;
-        struct browser_disasm_line *bdl;
+        struct annotation_line *al;
+        struct browser_line *bl;
         off_t offset = browser->b.index - browser->b.top_idx;
 
         browser->b.seek(&browser->b, offset, SEEK_CUR);
-        dl = list_entry(browser->b.top, struct disasm_line, node);
-        bdl = disasm_line__browser(dl);
+        al = list_entry(browser->b.top, struct annotation_line, node);
+        bl = browser_line(al);
 
         if (annotate_browser__opts.hide_src_code) {
-                if (bdl->idx_asm < offset)
-                        offset = bdl->idx;
+                if (bl->idx_asm < offset)
+                        offset = bl->idx;
 
                 browser->b.nr_entries = browser->nr_entries;
                 annotate_browser__opts.hide_src_code = false;
                 browser->b.seek(&browser->b, -offset, SEEK_CUR);
-                browser->b.top_idx = bdl->idx - offset;
-                browser->b.index = bdl->idx;
+                browser->b.top_idx = bl->idx - offset;
+                browser->b.index = bl->idx;
         } else {
-                if (bdl->idx_asm < 0) {
+                if (bl->idx_asm < 0) {
                         ui_helpline__puts("Only available for assembly lines.");
                         browser->b.seek(&browser->b, -offset, SEEK_CUR);
                         return false;
                 }
 
-                if (bdl->idx_asm < offset)
-                        offset = bdl->idx_asm;
+                if (bl->idx_asm < offset)
+                        offset = bl->idx_asm;
 
                 browser->b.nr_entries = browser->nr_asm_entries;
                 annotate_browser__opts.hide_src_code = true;
                 browser->b.seek(&browser->b, -offset, SEEK_CUR);
-                browser->b.top_idx = bdl->idx_asm - offset;
-                browser->b.index = bdl->idx_asm;
+                browser->b.top_idx = bl->idx_asm - offset;
+                browser->b.index = bl->idx_asm;
         }
 
         return true;
@@ -543,7 +536,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
                                     struct hist_browser_timer *hbt)
 {
         struct map_symbol *ms = browser->b.priv;
-        struct disasm_line *dl = browser->selection;
+        struct disasm_line *dl = disasm_line(browser->selection);
         struct annotation *notes;
         struct addr_map_symbol target = {
                 .map = ms->map,
@@ -589,10 +582,10 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows
         struct disasm_line *pos;
 
         *idx = 0;
-        list_for_each_entry(pos, &notes->src->source, node) {
-                if (pos->offset == offset)
+        list_for_each_entry(pos, &notes->src->source, al.node) {
+                if (pos->al.offset == offset)
                         return pos;
-                if (!disasm_line__filter(&browser->b, &pos->node))
+                if (!disasm_line__filter(&browser->b, &pos->al.node))
                         ++*idx;
         }
 
@@ -601,7 +594,7 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows
 
 static bool annotate_browser__jump(struct annotate_browser *browser)
 {
-        struct disasm_line *dl = browser->selection;
+        struct disasm_line *dl = disasm_line(browser->selection);
         u64 offset;
         s64 idx;
 
@@ -615,29 +608,29 @@ static bool annotate_browser__jump(struct annotate_browser *browser)
                 return true;
         }
 
-        annotate_browser__set_top(browser, dl, idx);
+        annotate_browser__set_top(browser, &dl->al, idx);
 
         return true;
 }
 
 static
-struct disasm_line *annotate_browser__find_string(struct annotate_browser *browser,
+struct annotation_line *annotate_browser__find_string(struct annotate_browser *browser,
                                           char *s, s64 *idx)
 {
         struct map_symbol *ms = browser->b.priv;
         struct symbol *sym = ms->sym;
         struct annotation *notes = symbol__annotation(sym);
-        struct disasm_line *pos = browser->selection;
+        struct annotation_line *al = browser->selection;
 
         *idx = browser->b.index;
-        list_for_each_entry_continue(pos, &notes->src->source, node) {
-                if (disasm_line__filter(&browser->b, &pos->node))
+        list_for_each_entry_continue(al, &notes->src->source, node) {
+                if (disasm_line__filter(&browser->b, &al->node))
                         continue;
 
                 ++*idx;
 
-                if (pos->line && strstr(pos->line, s) != NULL)
-                        return pos;
+                if (al->line && strstr(al->line, s) != NULL)
+                        return al;
         }
 
         return NULL;
@@ -645,38 +638,38 @@ struct disasm_line *annotate_browser__find_string(struct annotate_browser *brows
 
 static bool __annotate_browser__search(struct annotate_browser *browser)
 {
-        struct disasm_line *dl;
+        struct annotation_line *al;
         s64 idx;
 
-        dl = annotate_browser__find_string(browser, browser->search_bf, &idx);
-        if (dl == NULL) {
+        al = annotate_browser__find_string(browser, browser->search_bf, &idx);
+        if (al == NULL) {
                 ui_helpline__puts("String not found!");
                 return false;
         }
 
-        annotate_browser__set_top(browser, dl, idx);
+        annotate_browser__set_top(browser, al, idx);
         browser->searching_backwards = false;
         return true;
 }
 
 static
-struct disasm_line *annotate_browser__find_string_reverse(struct annotate_browser *browser,
+struct annotation_line *annotate_browser__find_string_reverse(struct annotate_browser *browser,
                                                   char *s, s64 *idx)
 {
         struct map_symbol *ms = browser->b.priv;
         struct symbol *sym = ms->sym;
         struct annotation *notes = symbol__annotation(sym);
-        struct disasm_line *pos = browser->selection;
+        struct annotation_line *al = browser->selection;
 
         *idx = browser->b.index;
-        list_for_each_entry_continue_reverse(pos, &notes->src->source, node) {
-                if (disasm_line__filter(&browser->b, &pos->node))
+        list_for_each_entry_continue_reverse(al, &notes->src->source, node) {
+                if (disasm_line__filter(&browser->b, &al->node))
                         continue;
 
                 --*idx;
 
-                if (pos->line && strstr(pos->line, s) != NULL)
-                        return pos;
+                if (al->line && strstr(al->line, s) != NULL)
+                        return al;
         }
 
         return NULL;
@@ -684,16 +677,16 @@ struct disasm_line *annotate_browser__find_string_reverse(struct annotate_browse
 
 static bool __annotate_browser__search_reverse(struct annotate_browser *browser)
 {
-        struct disasm_line *dl;
+        struct annotation_line *al;
         s64 idx;
 
-        dl = annotate_browser__find_string_reverse(browser, browser->search_bf, &idx);
-        if (dl == NULL) {
+        al = annotate_browser__find_string_reverse(browser, browser->search_bf, &idx);
+        if (al == NULL) {
                 ui_helpline__puts("String not found!");
                 return false;
         }
 
-        annotate_browser__set_top(browser, dl, idx);
+        annotate_browser__set_top(browser, al, idx);
         browser->searching_backwards = true;
         return true;
 }
@@ -899,13 +892,16 @@ show_help:
                         continue;
                 case K_ENTER:
                 case K_RIGHT:
+                {
+                        struct disasm_line *dl = disasm_line(browser->selection);
+
                         if (browser->selection == NULL)
                                 ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
                         else if (browser->selection->offset == -1)
                                 ui_helpline__puts("Actions are only available for assembly lines.");
-                        else if (!browser->selection->ins.ops)
+                        else if (!dl->ins.ops)
                                 goto show_sup_ins;
-                        else if (ins__is_ret(&browser->selection->ins))
+                        else if (ins__is_ret(&dl->ins))
                                 goto out;
                         else if (!(annotate_browser__jump(browser) ||
                                      annotate_browser__callq(browser, evsel, hbt))) {
@@ -913,6 +909,7 @@ show_sup_ins:
                                 ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
                         }
                         continue;
+                }
                 case 't':
                         if (annotate_browser__opts.show_total_period) {
                                 annotate_browser__opts.show_total_period = false;
@@ -990,10 +987,10 @@ static void count_and_fill(struct annotate_browser *browser, u64 start, u64 end,
                         return;
 
                 for (offset = start; offset <= end; offset++) {
-                        struct disasm_line *dl = browser->offsets[offset];
+                        struct annotation_line *al = browser->offsets[offset];
 
-                        if (dl)
-                                dl->ipc = ipc;
+                        if (al)
+                                al->ipc = ipc;
                 }
         }
 }
@@ -1018,13 +1015,13 @@ static void annotate__compute_ipc(struct annotate_browser *browser, size_t size,
 
                 ch = &notes->src->cycles_hist[offset];
                 if (ch && ch->cycles) {
-                        struct disasm_line *dl;
+                        struct annotation_line *al;
 
                         if (ch->have_start)
                                 count_and_fill(browser, ch->start, offset, ch);
-                        dl = browser->offsets[offset];
-                        if (dl && ch->num_aggr)
-                                dl->cycles = ch->cycles_aggr / ch->num_aggr;
+                        al = browser->offsets[offset];
+                        if (al && ch->num_aggr)
+                                al->cycles = ch->cycles_aggr / ch->num_aggr;
                         browser->have_cycles = true;
                 }
         }
@@ -1043,23 +1040,27 @@ static void annotate_browser__mark_jump_targets(struct annotate_browser *browser
                 return;
 
         for (offset = 0; offset < size; ++offset) {
-                struct disasm_line *dl = browser->offsets[offset], *dlt;
-                struct browser_disasm_line *bdlt;
+                struct annotation_line *al = browser->offsets[offset];
+                struct disasm_line *dl;
+                struct browser_line *blt;
+
+                dl = disasm_line(al);
 
                 if (!disasm_line__is_valid_jump(dl, sym))
                         continue;
 
-                dlt = browser->offsets[dl->ops.target.offset];
+                al = browser->offsets[dl->ops.target.offset];
+
                 /*
                  * FIXME: Oops, no jump target? Buggy disassembler? Or do we
                  * have to adjust to the previous offset?
                  */
-                if (dlt == NULL)
+                if (al == NULL)
                         continue;
 
-                bdlt = disasm_line__browser(dlt);
-                if (++bdlt->jump_sources > browser->max_jump_sources)
-                        browser->max_jump_sources = bdlt->jump_sources;
+                blt = browser_line(al);
+                if (++blt->jump_sources > browser->max_jump_sources)
+                        browser->max_jump_sources = blt->jump_sources;
 
                 ++browser->nr_jumps;
         }
@@ -1078,7 +1079,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
                          struct perf_evsel *evsel,
                          struct hist_browser_timer *hbt)
 {
-        struct disasm_line *pos, *n;
+        struct annotation_line *al;
         struct annotation *notes;
         size_t size;
         struct map_symbol ms = {
@@ -1097,7 +1098,6 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
         };
         int ret = -1, err;
         int nr_pcnt = 1;
-        size_t sizeof_bdl = sizeof(struct browser_disasm_line);
 
         if (sym == NULL)
                 return -1;
@@ -1107,21 +1107,16 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
         if (map->dso->annotate_warned)
                 return -1;
 
-        browser.offsets = zalloc(size * sizeof(struct disasm_line *));
+        browser.offsets = zalloc(size * sizeof(struct annotation_line *));
         if (browser.offsets == NULL) {
                 ui__error("Not enough memory!");
                 return -1;
         }
 
-        if (perf_evsel__is_group_event(evsel)) {
+        if (perf_evsel__is_group_event(evsel))
                 nr_pcnt = evsel->nr_members;
-                sizeof_bdl += sizeof(struct disasm_line_samples) *
-                  (nr_pcnt - 1);
-        }
 
-        err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                  sizeof_bdl, &browser.arch,
-                                  perf_evsel__env_cpuid(evsel));
+        err = symbol__annotate(sym, map, evsel, sizeof(struct browser_line), &browser.arch);
         if (err) {
                 char msg[BUFSIZ];
                 symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
@@ -1129,20 +1124,22 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
                 goto out_free_offsets;
         }
 
+        symbol__calc_percent(sym, evsel);
+
         ui_helpline__push("Press ESC to exit");
 
         notes = symbol__annotation(sym);
         browser.start = map__rip_2objdump(map, sym->start);
 
-        list_for_each_entry(pos, &notes->src->source, node) {
-                struct browser_disasm_line *bpos;
-                size_t line_len = strlen(pos->line);
+        list_for_each_entry(al, &notes->src->source, node) {
+                struct browser_line *bpos;
+                size_t line_len = strlen(al->line);
 
                 if (browser.b.width < line_len)
                         browser.b.width = line_len;
-                bpos = disasm_line__browser(pos);
+                bpos = browser_line(al);
                 bpos->idx = browser.nr_entries++;
-                if (pos->offset != -1) {
+                if (al->offset != -1) {
                         bpos->idx_asm = browser.nr_asm_entries++;
                         /*
                          * FIXME: short term bandaid to cope with assembly
@@ -1151,8 +1148,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
                          *
                          * E.g. copy_user_generic_unrolled
                          */
-                        if (pos->offset < (s64)size)
-                                browser.offsets[pos->offset] = pos;
+                        if (al->offset < (s64)size)
+                                browser.offsets[al->offset] = al;
                 } else
                         bpos->idx_asm = -1;
         }
@@ -1174,10 +1171,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
         annotate_browser__update_addr_width(&browser);
 
         ret = annotate_browser__run(&browser, evsel, hbt);
-        list_for_each_entry_safe(pos, n, &notes->src->source, node) {
-                list_del(&pos->node);
-                disasm_line__free(pos);
-        }
+
+        annotated_source__purge(notes->src);
 
 out_free_offsets:
         free(browser.offsets);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 628ad5f7eddb..6495ee55d9c3 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -155,57 +155,9 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
         cl->unfolded = unfold ? cl->has_children : false;
 }
 
-static struct inline_node *inline_node__create(struct map *map, u64 ip)
-{
-        struct dso *dso;
-        struct inline_node *node;
-
-        if (map == NULL)
-                return NULL;
-
-        dso = map->dso;
-        if (dso == NULL)
-                return NULL;
-
-        node = dso__parse_addr_inlines(dso,
-                                       map__rip_2objdump(map, ip));
-
-        return node;
-}
-
-static int inline__count_rows(struct inline_node *node)
-{
-        struct inline_list *ilist;
-        int i = 0;
-
-        if (node == NULL)
-                return 0;
-
-        list_for_each_entry(ilist, &node->val, list) {
-                if ((ilist->filename != NULL) || (ilist->funcname != NULL))
-                        i++;
-        }
-
-        return i;
-}
-
-static int callchain_list__inline_rows(struct callchain_list *chain)
-{
-        struct inline_node *node;
-        int rows;
-
-        node = inline_node__create(chain->ms.map, chain->ip);
-        if (node == NULL)
-                return 0;
-
-        rows = inline__count_rows(node);
-        inline_node__delete(node);
-        return rows;
-}
-
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 {
-        int n = 0, inline_rows;
+        int n = 0;
         struct rb_node *nd;
 
         for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
@@ -216,12 +168,6 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
                 list_for_each_entry(chain, &child->val, list) {
                         ++n;
 
-                        if (symbol_conf.inline_name) {
-                                inline_rows =
-                                        callchain_list__inline_rows(chain);
-                                n += inline_rows;
-                        }
-
                         /* We need this because we may not have children */
                         folded_sign = callchain_list__folded(chain);
                         if (folded_sign == '+')
@@ -273,7 +219,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 {
         struct callchain_list *chain;
         bool unfolded = false;
-        int n = 0, inline_rows;
+        int n = 0;
 
         if (callchain_param.mode == CHAIN_FLAT)
                 return callchain_node__count_flat_rows(node);
@@ -282,10 +228,6 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
         list_for_each_entry(chain, &node->val, list) {
                 ++n;
-                if (symbol_conf.inline_name) {
-                        inline_rows = callchain_list__inline_rows(chain);
-                        n += inline_rows;
-                }
 
                 unfolded = chain->unfolded;
         }
@@ -433,19 +375,6 @@ static void hist_entry__init_have_children(struct hist_entry *he)
         he->init_have_children = true;
 }
 
-static void hist_entry_init_inline_node(struct hist_entry *he)
-{
-        if (he->inline_node)
-                return;
-
-        he->inline_node = inline_node__create(he->ms.map, he->ip);
-
-        if (he->inline_node == NULL)
-                return;
-
-        he->has_children = true;
-}
-
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
         struct hist_entry *he = browser->he_selection;
@@ -477,12 +406,8 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 
                 if (he->unfolded) {
                         if (he->leaf)
-                                if (he->inline_node)
-                                        he->nr_rows = inline__count_rows(
-                                                        he->inline_node);
-                                else
-                                        he->nr_rows = callchain__count_rows(
-                                                        &he->sorted_chain);
+                                he->nr_rows = callchain__count_rows(
+                                                &he->sorted_chain);
                         else
                                 he->nr_rows = hierarchy_count_rows(browser, he, false);
 
@@ -683,7 +608,8 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si
         return browser->title ? browser->title(browser, bf, size) : 0;
 }
 
-int hist_browser__run(struct hist_browser *browser, const char *help)
+int hist_browser__run(struct hist_browser *browser, const char *help,
+                      bool warn_lost_event)
 {
         int key;
         char title[160];
@@ -713,8 +639,9 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
                         nr_entries = hist_browser__nr_entries(browser);
                         ui_browser__update_nr_entries(&browser->b, nr_entries);
 
-                        if (browser->hists->stats.nr_lost_warned !=
-                            browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
+                        if (warn_lost_event &&
+                            (browser->hists->stats.nr_lost_warned !=
+                            browser->hists->stats.nr_events[PERF_RECORD_LOST])) {
                                 browser->hists->stats.nr_lost_warned =
                                         browser->hists->stats.nr_events[PERF_RECORD_LOST];
                                 ui_browser__warn_lost_events(&browser->b);
@@ -842,71 +769,6 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
-static int hist_browser__show_inline(struct hist_browser *browser,
-                                     struct inline_node *node,
-                                     unsigned short row,
-                                     int offset)
-{
-        struct inline_list *ilist;
-        char buf[1024];
-        int color, width, first_row;
-
-        first_row = row;
-        width = browser->b.width - (LEVEL_OFFSET_STEP + 2);
-        list_for_each_entry(ilist, &node->val, list) {
-                if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
-                        color = HE_COLORSET_NORMAL;
-                        if (ui_browser__is_current_entry(&browser->b, row))
-                                color = HE_COLORSET_SELECTED;
-
-                        if (callchain_param.key == CCKEY_ADDRESS ||
-                            callchain_param.key == CCKEY_SRCLINE) {
-                                if (ilist->filename != NULL)
-                                        scnprintf(buf, sizeof(buf),
-                                                  "%s:%d (inline)",
-                                                  ilist->filename,
-                                                  ilist->line_nr);
-                                else
-                                        scnprintf(buf, sizeof(buf), "??");
-                        } else if (ilist->funcname != NULL)
-                                scnprintf(buf, sizeof(buf), "%s (inline)",
-                                          ilist->funcname);
-                        else if (ilist->filename != NULL)
-                                scnprintf(buf, sizeof(buf),
-                                          "%s:%d (inline)",
-                                          ilist->filename,
-                                          ilist->line_nr);
-                        else
-                                scnprintf(buf, sizeof(buf), "??");
-
-                        ui_browser__set_color(&browser->b, color);
-                        hist_browser__gotorc(browser, row, 0);
-                        ui_browser__write_nstring(&browser->b, " ",
-                                LEVEL_OFFSET_STEP + offset);
-                        ui_browser__write_nstring(&browser->b, buf, width);
-                        row++;
-                }
-        }
-
-        return row - first_row;
-}
-
-static size_t show_inline_list(struct hist_browser *browser, struct map *map,
-                               u64 ip, int row, int offset)
-{
-        struct inline_node *node;
-        int ret;
-
-        node = inline_node__create(map, ip);
-        if (node == NULL)
-                return 0;
-
-        ret = hist_browser__show_inline(browser, node, row, offset);
-
-        inline_node__delete(node);
-        return ret;
-}
-
 static int hist_browser__show_callchain_list(struct hist_browser *browser,
                                              struct callchain_node *node,
                                              struct callchain_list *chain,
@@ -918,7 +780,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
         char bf[1024], *alloc_str;
         char buf[64], *alloc_str2;
         const char *str;
-        int inline_rows = 0, ret = 1;
+        int ret = 1;
 
         if (arg->row_offset != 0) {
                 arg->row_offset--;
@@ -955,12 +817,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
         free(alloc_str);
         free(alloc_str2);
 
-        if (symbol_conf.inline_name) {
-                inline_rows = show_inline_list(browser, chain->ms.map,
-                                               chain->ip, row + 1, offset);
-        }
-
-        return ret + inline_rows;
+        return ret;
 }
 
 static bool check_percent_display(struct rb_node *node, u64 parent_total)
@@ -1384,12 +1241,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                 folded_sign = hist_entry__folded(entry);
         }
 
-        if (symbol_conf.inline_name &&
-            (!entry->has_children)) {
-                hist_entry_init_inline_node(entry);
-                folded_sign = hist_entry__folded(entry);
-        }
-
         if (row_offset == 0) {
                 struct hpp_arg arg = {
                         .b              = &browser->b,
@@ -1421,8 +1272,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         }
 
                         if (first) {
-                                if (symbol_conf.use_callchain ||
-                                        symbol_conf.inline_name) {
+                                if (symbol_conf.use_callchain) {
                                         ui_browser__printf(&browser->b, "%c ", folded_sign);
                                         width -= 2;
                                 }
@@ -1464,15 +1314,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         .is_current_entry = current_entry,
                 };
 
-                if (entry->inline_node)
-                        printed += hist_browser__show_inline(browser,
-                                        entry->inline_node, row, 0);
-                else
-                        printed += hist_browser__show_callchain(browser,
-                                        entry, 1, row,
-                                        hist_browser__show_callchain_entry,
-                                        &arg,
-                                        hist_browser__check_output_full);
+                printed += hist_browser__show_callchain(browser,
+                                entry, 1, row,
+                                hist_browser__show_callchain_entry,
+                                &arg,
+                                hist_browser__check_output_full);
         }
 
         return printed;
@@ -2919,7 +2765,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                     bool left_exits,
                                     struct hist_browser_timer *hbt,
                                     float min_pcnt,
-                                    struct perf_env *env)
+                                    struct perf_env *env,
+                                    bool warn_lost_event)
 {
         struct hists *hists = evsel__hists(evsel);
         struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
@@ -3000,7 +2847,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
                 nr_options = 0;
 
-                key = hist_browser__run(browser, helpline);
+                key = hist_browser__run(browser, helpline,
+                                        warn_lost_event);
 
                 if (browser->he_selection != NULL) {
                         thread = hist_browser__selected_thread(browser);
@@ -3340,7 +3188,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 
 static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
                                 int nr_events, const char *help,
-                                struct hist_browser_timer *hbt)
+                                struct hist_browser_timer *hbt,
+                                bool warn_lost_event)
 {
         struct perf_evlist *evlist = menu->b.priv;
         struct perf_evsel *pos;
@@ -3359,7 +3208,9 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
                 case K_TIMER:
                         hbt->timer(hbt->arg);
 
-                        if (!menu->lost_events_warned && menu->lost_events) {
+                        if (!menu->lost_events_warned &&
+                            menu->lost_events &&
+                            warn_lost_event) {
                                 ui_browser__warn_lost_events(&menu->b);
                                 menu->lost_events_warned = true;
                         }
@@ -3380,7 +3231,8 @@ browse_hists:
                         key = perf_evsel__hists_browse(pos, nr_events, help,
                                                        true, hbt,
                                                        menu->min_pcnt,
-                                                       menu->env);
+                                                       menu->env,
+                                                       warn_lost_event);
                         ui_browser__show_title(&menu->b, title);
                         switch (key) {
                         case K_TAB:
@@ -3438,7 +3290,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                                            int nr_entries, const char *help,
                                            struct hist_browser_timer *hbt,
                                            float min_pcnt,
-                                           struct perf_env *env)
+                                           struct perf_env *env,
+                                           bool warn_lost_event)
 {
         struct perf_evsel *pos;
         struct perf_evsel_menu menu = {
@@ -3465,13 +3318,15 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                         menu.b.width = line_len;
         }
 
-        return perf_evsel_menu__run(&menu, nr_entries, help, hbt);
+        return perf_evsel_menu__run(&menu, nr_entries, help,
+                                    hbt, warn_lost_event);
 }
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                   struct hist_browser_timer *hbt,
                                   float min_pcnt,
-                                  struct perf_env *env)
+                                  struct perf_env *env,
+                                  bool warn_lost_event)
 {
         int nr_entries = evlist->nr_entries;
 
@@ -3481,7 +3336,7 @@ single_entry:
 
                 return perf_evsel__hists_browse(first, nr_entries, help,
                                                 false, hbt, min_pcnt,
-                                                env);
+                                                env, warn_lost_event);
         }
 
         if (symbol_conf.event_group) {
@@ -3498,5 +3353,6 @@ single_entry:
         }
 
         return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
-                                               hbt, min_pcnt, env);
+                                               hbt, min_pcnt, env,
+                                               warn_lost_event);
 }
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index ba431777f559..9428bee076f2 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -28,7 +28,8 @@ struct hist_browser {
 
 struct hist_browser *hist_browser__new(struct hists *hists);
 void hist_browser__delete(struct hist_browser *browser);
-int hist_browser__run(struct hist_browser *browser, const char *help);
+int hist_browser__run(struct hist_browser *browser, const char *help,
+                      bool warn_lost_event);
 void hist_browser__init(struct hist_browser *browser,
                         struct hists *hists);
 #endif /* _PERF_UI_BROWSER_HISTS_H_ */
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index fc7a2e105bfd..aeeaf15029f0 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -31,14 +31,14 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
 
         strcpy(buf, "");
 
-        if (dl->offset == (s64) -1)
+        if (dl->al.offset == (s64) -1)
                 return 0;
 
         symhist = annotation__histogram(symbol__annotation(sym), evidx);
-        if (!symbol_conf.event_group && !symhist->addr[dl->offset].nr_samples)
+        if (!symbol_conf.event_group && !symhist->addr[dl->al.offset].nr_samples)
                 return 0;
 
-        percent = 100.0 * symhist->addr[dl->offset].nr_samples / symhist->nr_samples;
+        percent = 100.0 * symhist->addr[dl->al.offset].nr_samples / symhist->nr_samples;
 
         markup = perf_gtk__get_percent_color(percent);
         if (markup)
@@ -57,16 +57,16 @@ static int perf_gtk__get_offset(char *buf, size_t size, struct symbol *sym,
 
         strcpy(buf, "");
 
-        if (dl->offset == (s64) -1)
+        if (dl->al.offset == (s64) -1)
                 return 0;
 
-        return scnprintf(buf, size, "%"PRIx64, start + dl->offset);
+        return scnprintf(buf, size, "%"PRIx64, start + dl->al.offset);
 }
 
 static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl)
 {
         int ret = 0;
-        char *line = g_markup_escape_text(dl->line, -1);
+        char *line = g_markup_escape_text(dl->al.line, -1);
         const char *markup = "<span fgcolor='gray'>";
 
         strcpy(buf, "");
@@ -74,7 +74,7 @@ static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl)
         if (!line)
                 return 0;
 
-        if (dl->offset != (s64) -1)
+        if (dl->al.offset != (s64) -1)
                 markup = NULL;
 
         if (markup)
@@ -119,7 +119,7 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
         gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
         g_object_unref(GTK_TREE_MODEL(store));
 
-        list_for_each_entry(pos, &notes->src->source, node) {
+        list_for_each_entry(pos, &notes->src->source, al.node) {
                 GtkTreeIter iter;
                 int ret = 0;
 
@@ -148,8 +148,8 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
 
         gtk_container_add(GTK_CONTAINER(window), view);
 
-        list_for_each_entry_safe(pos, n, &notes->src->source, node) {
-                list_del(&pos->node);
+        list_for_each_entry_safe(pos, n, &notes->src->source, al.node) {
+                list_del(&pos->al.node);
                 disasm_line__free(pos);
         }
 
@@ -169,8 +169,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
         if (map->dso->annotate_warned)
                 return -1;
 
-        err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                  0, NULL, NULL);
+        err = symbol__annotate(sym, map, evsel, 0, NULL);
         if (err) {
                 char msg[BUFSIZ];
                 symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
@@ -178,6 +177,8 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
                 return -1;
         }
 
+        symbol__calc_percent(sym, evsel);
+
         if (perf_gtk__is_active_context(pgctx)) {
                 window = pgctx->main_window;
                 notebook = pgctx->notebook;
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index b5a5df14d702..bbfbc91a0fa4 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -28,13 +28,17 @@ void ui_progress__update(struct ui_progress *p, u64 adv)
         }
 }
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
+void __ui_progress__init(struct ui_progress *p, u64 total,
+                         const char *title, bool size)
 {
         p->curr = 0;
         p->next = p->step = total / 16 ?: 1;
         p->total = total;
         p->title = title;
+        p->size  = size;
 
+        if (ui_progress__ops->init)
+                ui_progress__ops->init(p);
 }
 
 void ui_progress__finish(void)
diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h
index 594bbe6935dd..4f52c37b2f09 100644
--- a/tools/perf/ui/progress.h
+++ b/tools/perf/ui/progress.h
@@ -9,12 +9,22 @@ void ui_progress__finish(void);
 struct ui_progress {
         const char *title;
         u64 curr, next, step, total;
+        bool size;
 };
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
+void __ui_progress__init(struct ui_progress *p, u64 total,
+                         const char *title, bool size);
+
+#define ui_progress__init(p, total, title) \
+        __ui_progress__init(p, total, title, false)
+
+#define ui_progress__init_size(p, total, title) \
+        __ui_progress__init(p, total, title, true)
+
 void ui_progress__update(struct ui_progress *p, u64 adv);
 
 struct ui_progress_ops {
+        void (*init)(struct ui_progress *p);
         void (*update)(struct ui_progress *p);
         void (*finish)(void);
 };
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index de2810ae16be..25dd1e0ecc58 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -22,64 +22,6 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
         return ret;
 }
 
-static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
-                              int depth, int depth_mask, FILE *fp)
-{
-        struct dso *dso;
-        struct inline_node *node;
-        struct inline_list *ilist;
-        int ret = 0, i;
-
-        if (map == NULL)
-                return 0;
-
-        dso = map->dso;
-        if (dso == NULL)
-                return 0;
-
-        node = dso__parse_addr_inlines(dso,
-                                       map__rip_2objdump(map, ip));
-        if (node == NULL)
-                return 0;
-
-        list_for_each_entry(ilist, &node->val, list) {
-                if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
-                        ret += callchain__fprintf_left_margin(fp, left_margin);
-
-                        for (i = 0; i < depth; i++) {
-                                if (depth_mask & (1 << i))
-                                        ret += fprintf(fp, "|");
-                                else
-                                        ret += fprintf(fp, " ");
-                                ret += fprintf(fp, "          ");
-                        }
-
-                        if (callchain_param.key == CCKEY_ADDRESS ||
-                            callchain_param.key == CCKEY_SRCLINE) {
-                                if (ilist->filename != NULL)
-                                        ret += fprintf(fp, "%s:%d (inline)",
-                                                       ilist->filename,
-                                                       ilist->line_nr);
-                                else
-                                        ret += fprintf(fp, "??");
-                        } else if (ilist->funcname != NULL)
-                                ret += fprintf(fp, "%s (inline)",
-                                               ilist->funcname);
-                        else if (ilist->filename != NULL)
-                                ret += fprintf(fp, "%s:%d (inline)",
-                                               ilist->filename,
-                                               ilist->line_nr);
-                        else
-                                ret += fprintf(fp, "??");
-
-                        ret += fprintf(fp, "\n");
-                }
-        }
-
-        inline_node__delete(node);
-        return ret;
-}
-
 static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
                                           int left_margin)
 {
@@ -138,9 +80,6 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
         fputc('\n', fp);
         free(alloc_str);
 
-        if (symbol_conf.inline_name)
-                ret += inline__fprintf(chain->ms.map, chain->ip,
-                                       left_margin, depth, depth_mask, fp);
         return ret;
 }
 
@@ -315,13 +254,6 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
                         if (++entries_printed == callchain_param.print_limit)
                                 break;
-
-                        if (symbol_conf.inline_name)
-                                ret += inline__fprintf(chain->ms.map,
-                                                       chain->ip,
-                                                       left_margin,
-                                                       0, 0,
-                                                       fp);
                 }
                 root = &cnode->rb_root;
         }
@@ -601,7 +533,6 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 {
         int ret;
         int callchain_ret = 0;
-        int inline_ret = 0;
         struct perf_hpp hpp = {
                 .buf            = bf,
                 .size           = size,
@@ -623,13 +554,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
                 callchain_ret = hist_entry_callchain__fprintf(he, total_period,
                                                               0, fp);
 
-        if (callchain_ret == 0 && symbol_conf.inline_name) {
-                inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp);
-                ret += inline_ret;
-                if (inline_ret > 0)
-                        ret += fprintf(fp, "\n");
-        } else
-                ret += callchain_ret;
+        ret += callchain_ret;
 
         return ret;
 }
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index 236bcb620ae4..bc134b82829d 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -1,13 +1,34 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
 #include "tui.h"
+#include "units.h"
 #include "../browser.h"
 
+static void __tui_progress__init(struct ui_progress *p)
+{
+        p->next = p->step = p->total / (SLtt_Screen_Cols - 2) ?: 1;
+}
+
+static int get_title(struct ui_progress *p, char *buf, size_t size)
+{
+        char buf_cur[20];
+        char buf_tot[20];
+        int ret;
+
+        ret  = unit_number__scnprintf(buf_cur, sizeof(buf_cur), p->curr);
+        ret += unit_number__scnprintf(buf_tot, sizeof(buf_tot), p->total);
+
+        return ret + scnprintf(buf, size, "%s [%s/%s]",
+                               p->title, buf_cur, buf_tot);
+}
+
 static void tui_progress__update(struct ui_progress *p)
 {
+        char buf[100], *title = (char *) p->title;
         int bar, y;
         /*
          * FIXME: We should have a per UI backend way of showing progress,
@@ -19,13 +40,18 @@ static void tui_progress__update(struct ui_progress *p)
         if (p->total == 0)
                 return;
 
+        if (p->size) {
+                get_title(p, buf, sizeof(buf));
+                title = buf;
+        }
+
         ui__refresh_dimensions(false);
         pthread_mutex_lock(&ui__lock);
         y = SLtt_Screen_Rows / 2 - 2;
         SLsmg_set_color(0);
         SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
         SLsmg_gotorc(y++, 1);
-        SLsmg_write_string((char *)p->title);
+        SLsmg_write_string(title);
         SLsmg_fill_region(y, 1, 1, SLtt_Screen_Cols - 2, ' ');
         SLsmg_set_color(HE_COLORSET_SELECTED);
         bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total;
@@ -50,8 +76,8 @@ static void tui_progress__finish(void)
         pthread_mutex_unlock(&ui__lock);
 }
 
-static struct ui_progress_ops tui_progress__ops =
-{
+static struct ui_progress_ops tui_progress__ops = {
+        .init   = __tui_progress__init,
         .update = tui_progress__update,
         .finish = tui_progress__finish,
 };
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 94518c1bf8b6..ea0a452550b0 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -13,6 +13,7 @@ libperf-y += find_bit.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
+libperf-y += mmap.o
 libperf-y += memswap.o
 libperf-y += parse-events.o
 libperf-y += perf_regs.o
@@ -34,6 +35,7 @@ libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += symbol_fprintf.o
 libperf-y += color.o
+libperf-y += metricgroup.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
@@ -42,7 +44,7 @@ libperf-y += machine.o
 libperf-y += map.o
 libperf-y += pstack.o
 libperf-y += session.o
-libperf-$(CONFIG_AUDIT) += syscalltbl.o
+libperf-$(CONFIG_TRACE) += syscalltbl.o
 libperf-y += ordered-events.o
 libperf-y += namespaces.o
 libperf-y += comm.o
@@ -78,11 +80,20 @@ libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o
 libperf-y += call-path.o
+libperf-y += rwsem.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
+libperf-$(CONFIG_AUXTRACE) += arm-spe.o
+libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o
+
+ifdef CONFIG_LIBOPENCSD
+libperf-$(CONFIG_AUXTRACE) += cs-etm.o
+libperf-$(CONFIG_AUXTRACE) += cs-etm-decoder/
+endif
+
 libperf-y += parse-branch-options.o
 libperf-y += dump-insn.o
 libperf-y += parse-regs-options.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index aa66791b1bfc..28b233c3dcbe 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -26,7 +26,6 @@
 #include <pthread.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
-#include <sys/utsname.h>
 
 #include "sane_ctype.h"
 
@@ -49,10 +48,9 @@ struct arch {
         void            *priv;
         unsigned int    model;
         unsigned int    family;
-        int             (*init)(struct arch *arch);
+        int             (*init)(struct arch *arch, char *cpuid);
         bool            (*ins_is_fused)(struct arch *arch, const char *ins1,
                                         const char *ins2);
-        int             (*cpuid_parse)(struct arch *arch, char *cpuid);
         struct          {
                 char comment_char;
                 char skip_functions_char;
@@ -132,10 +130,10 @@ static struct arch architectures[] = {
         },
         {
                 .name = "x86",
+                .init = x86__annotate_init,
                 .instructions = x86__instructions,
                 .nr_instructions = ARRAY_SIZE(x86__instructions),
                 .ins_is_fused = x86__ins_is_fused,
-                .cpuid_parse = x86__cpuid_parse,
                 .objdump =  {
                         .comment_char = '#',
                 },
@@ -166,7 +164,7 @@ static void ins__delete(struct ins_operands *ops)
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
                               struct ins_operands *ops)
 {
-        return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw);
+        return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
@@ -231,12 +229,12 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
                            struct ins_operands *ops)
 {
         if (ops->target.name)
-                return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name);
+                return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
 
         if (ops->target.addr == 0)
                 return ins__raw_scnprintf(ins, bf, size, ops);
 
-        return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
+        return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -300,7 +298,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
                         c++;
         }
 
-        return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+        return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
                          ins->name, c ? c - ops->raw : 0, ops->raw,
                          ops->target.offset);
 }
@@ -323,6 +321,8 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
                 return 0;
 
         *addrp = strtoull(comment, &endptr, 16);
+        if (endptr == comment)
+                return 0;
         name = strchr(endptr, '<');
         if (name == NULL)
                 return -1;
@@ -373,7 +373,7 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
         if (ops->locked.ins.ops == NULL)
                 return ins__raw_scnprintf(ins, bf, size, ops);
 
-        printed = scnprintf(bf, size, "%-6.6s ", ins->name);
+        printed = scnprintf(bf, size, "%-6s ", ins->name);
         return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
                                         size - printed, ops->locked.ops);
 }
@@ -436,8 +436,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
                 return 0;
 
         comment = ltrim(comment);
-        comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name);
-        comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+        comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
+        comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
         return 0;
 
@@ -449,7 +449,7 @@ out_free_source:
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
                            struct ins_operands *ops)
 {
-        return scnprintf(bf, size, "%-6.6s %s,%s", ins->name,
+        return scnprintf(bf, size, "%-6s %s,%s", ins->name,
                          ops->source.name ?: ops->source.raw,
                          ops->target.name ?: ops->target.raw);
 }
@@ -481,7 +481,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
                 return 0;
 
         comment = ltrim(comment);
-        comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
+        comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
         return 0;
 }
@@ -489,7 +489,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
                            struct ins_operands *ops)
 {
-        return scnprintf(bf, size, "%-6.6s %s", ins->name,
+        return scnprintf(bf, size, "%-6s %s", ins->name,
                          ops->target.name ?: ops->target.raw);
 }
 
@@ -501,7 +501,7 @@ static struct ins_ops dec_ops = {
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
                           struct ins_operands *ops __maybe_unused)
 {
-        return scnprintf(bf, size, "%-6.6s", "nop");
+        return scnprintf(bf, size, "%-6s", "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -879,32 +879,99 @@ out_free_name:
         return -1;
 }
 
-static struct disasm_line *disasm_line__new(s64 offset, char *line,
-                                            size_t privsize, int line_nr,
-                                            struct arch *arch,
-                                            struct map *map)
+struct annotate_args {
+        size_t                   privsize;
+        struct arch             *arch;
+        struct map              *map;
+        struct perf_evsel       *evsel;
+        s64                      offset;
+        char                    *line;
+        int                      line_nr;
+};
+
+static void annotation_line__delete(struct annotation_line *al)
 {
-        struct disasm_line *dl = zalloc(sizeof(*dl) + privsize);
+        void *ptr = (void *) al - al->privsize;
+
+        free_srcline(al->path);
+        zfree(&al->line);
+        free(ptr);
+}
+
+/*
+ * Allocating the annotation line data with following
+ * structure:
+ *
+ *    --------------------------------------
+ *    private space | struct annotation_line
+ *    --------------------------------------
+ *
+ * Size of the private space is stored in 'struct annotation_line'.
+ *
+ */
+static struct annotation_line *
+annotation_line__new(struct annotate_args *args, size_t privsize)
+{
+        struct annotation_line *al;
+        struct perf_evsel *evsel = args->evsel;
+        size_t size = privsize + sizeof(*al);
+        int nr = 1;
+
+        if (perf_evsel__is_group_event(evsel))
+                nr = evsel->nr_members;
+
+        size += sizeof(al->samples[0]) * nr;
+
+        al = zalloc(size);
+        if (al) {
+                al = (void *) al + privsize;
+                al->privsize   = privsize;
+                al->offset     = args->offset;
+                al->line       = strdup(args->line);
+                al->line_nr    = args->line_nr;
+                al->samples_nr = nr;
+        }
+
+        return al;
+}
+
+/*
+ * Allocating the disasm annotation line data with
+ * following structure:
+ *
+ *    ------------------------------------------------------------
+ *    privsize space | struct disasm_line | struct annotation_line
+ *    ------------------------------------------------------------
+ *
+ * We have 'struct annotation_line' member as last member
+ * of 'struct disasm_line' to have an easy access.
+ *
+ */
+static struct disasm_line *disasm_line__new(struct annotate_args *args)
+{
+        struct disasm_line *dl = NULL;
+        struct annotation_line *al;
+        size_t privsize = args->privsize + offsetof(struct disasm_line, al);
+
+        al = annotation_line__new(args, privsize);
+        if (al != NULL) {
+                dl = disasm_line(al);
 
-        if (dl != NULL) {
-                dl->offset = offset;
-                dl->line = strdup(line);
-                dl->line_nr = line_nr;
-                if (dl->line == NULL)
+                if (dl->al.line == NULL)
                         goto out_delete;
 
-                if (offset != -1) {
-                        if (disasm_line__parse(dl->line, &dl->ins.name, &dl->ops.raw) < 0)
+                if (args->offset != -1) {
+                        if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
                                 goto out_free_line;
 
-                        disasm_line__init_ins(dl, arch, map);
+                        disasm_line__init_ins(dl, args->arch, args->map);
                 }
         }
 
         return dl;
 
 out_free_line:
-        zfree(&dl->line);
+        zfree(&dl->al.line);
 out_delete:
         free(dl);
         return NULL;
@@ -912,30 +979,30 @@ out_delete:
 
 void disasm_line__free(struct disasm_line *dl)
 {
-        zfree(&dl->line);
         if (dl->ins.ops && dl->ins.ops->free)
                 dl->ins.ops->free(&dl->ops);
         else
                 ins__delete(&dl->ops);
         free((void *)dl->ins.name);
         dl->ins.name = NULL;
-        free(dl);
+        annotation_line__delete(&dl->al);
 }
 
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
 {
         if (raw || !dl->ins.ops)
-                return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw);
+                return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
 
         return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
 }
 
-static void disasm__add(struct list_head *head, struct disasm_line *line)
+static void annotation_line__add(struct annotation_line *al, struct list_head *head)
 {
-        list_add_tail(&line->node, head);
+        list_add_tail(&al->node, head);
 }
 
-struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos)
+struct annotation_line *
+annotation_line__next(struct annotation_line *pos, struct list_head *head)
 {
         list_for_each_entry_continue(pos, head, node)
                 if (pos->offset >= 0)
@@ -944,50 +1011,6 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
         return NULL;
 }
 
-double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-                            s64 end, const char **path, struct sym_hist_entry *sample)
-{
-        struct source_line *src_line = notes->src->lines;
-        double percent = 0.0;
-
-        sample->nr_samples = sample->period = 0;
-
-        if (src_line) {
-                size_t sizeof_src_line = sizeof(*src_line) +
-                                sizeof(src_line->samples) * (src_line->nr_pcnt - 1);
-
-                while (offset < end) {
-                        src_line = (void *)notes->src->lines +
-                                        (sizeof_src_line * offset);
-
-                        if (*path == NULL)
-                                *path = src_line->path;
-
-                        percent += src_line->samples[evidx].percent;
-                        sample->nr_samples += src_line->samples[evidx].nr;
-                        offset++;
-                }
-        } else {
-                struct sym_hist *h = annotation__histogram(notes, evidx);
-                unsigned int hits = 0;
-                u64 period = 0;
-
-                while (offset < end) {
-                        hits   += h->addr[offset].nr_samples;
-                        period += h->addr[offset].period;
-                        ++offset;
-                }
-
-                if (h->nr_samples) {
-                        sample->period     = period;
-                        sample->nr_samples = hits;
-                        percent = 100.0 * hits / h->nr_samples;
-                }
-        }
-
-        return percent;
-}
-
 static const char *annotate__address_color(struct block_range *br)
 {
         double cov = block_range__coverage(br);
@@ -1070,50 +1093,39 @@ static void annotate__branch_printf(struct block_range *br, u64 addr)
         }
 }
 
+static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_width)
+{
+        s64 offset = dl->al.offset;
+        const u64 addr = start + offset;
+        struct block_range *br;
+
+        br = block_range__find(addr);
+        color_fprintf(stdout, annotate__address_color(br), "  %*" PRIx64 ":", addr_fmt_width, addr);
+        color_fprintf(stdout, annotate__asm_color(br), "%s", dl->al.line);
+        annotate__branch_printf(br, addr);
+        return 0;
+}
 
-static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
-                      struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
-                      int max_lines, struct disasm_line *queue)
+static int
+annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start,
+                       struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
+                       int max_lines, struct annotation_line *queue, int addr_fmt_width)
 {
+        struct disasm_line *dl = container_of(al, struct disasm_line, al);
         static const char *prev_line;
         static const char *prev_color;
 
-        if (dl->offset != -1) {
-                const char *path = NULL;
-                double percent, max_percent = 0.0;
-                double *ppercents = &percent;
-                struct sym_hist_entry sample;
-                struct sym_hist_entry *psamples = &sample;
+        if (al->offset != -1) {
+                double max_percent = 0.0;
                 int i, nr_percent = 1;
                 const char *color;
                 struct annotation *notes = symbol__annotation(sym);
-                s64 offset = dl->offset;
-                const u64 addr = start + offset;
-                struct disasm_line *next;
-                struct block_range *br;
-
-                next = disasm__get_next_ip_line(&notes->src->source, dl);
-
-                if (perf_evsel__is_group_event(evsel)) {
-                        nr_percent = evsel->nr_members;
-                        ppercents = calloc(nr_percent, sizeof(double));
-                        psamples = calloc(nr_percent, sizeof(struct sym_hist_entry));
-                        if (ppercents == NULL || psamples == NULL) {
-                                return -1;
-                        }
-                }
 
-                for (i = 0; i < nr_percent; i++) {
-                        percent = disasm__calc_percent(notes,
-                                        notes->src->lines ? i : evsel->idx + i,
-                                        offset,
-                                        next ? next->offset : (s64) len,
-                                        &path, &sample);
-
-                        ppercents[i] = percent;
-                        psamples[i] = sample;
-                        if (percent > max_percent)
-                                max_percent = percent;
+                for (i = 0; i < al->samples_nr; i++) {
+                        struct annotation_data *sample = &al->samples[i];
+
+                        if (sample->percent > max_percent)
+                                max_percent = sample->percent;
                 }
 
                 if (max_percent < min_pcnt)
@@ -1124,10 +1136,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
                 if (queue != NULL) {
                         list_for_each_entry_from(queue, &notes->src->source, node) {
-                                if (queue == dl)
+                                if (queue == al)
                                         break;
-                                disasm_line__print(queue, sym, start, evsel, len,
-                                                    0, 0, 1, NULL);
+                                annotation_line__print(queue, sym, start, evsel, len,
+                                                       0, 0, 1, NULL, addr_fmt_width);
                         }
                 }
 
@@ -1138,44 +1150,34 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                  * the same color than the percentage. Don't print it
                  * twice for close colored addr with the same filename:line
                  */
-                if (path) {
-                        if (!prev_line || strcmp(prev_line, path)
+                if (al->path) {
+                        if (!prev_line || strcmp(prev_line, al->path)
                                        || color != prev_color) {
-                                color_fprintf(stdout, color, " %s", path);
-                                prev_line = path;
+                                color_fprintf(stdout, color, " %s", al->path);
+                                prev_line = al->path;
                                 prev_color = color;
                         }
                 }
 
                 for (i = 0; i < nr_percent; i++) {
-                        percent = ppercents[i];
-                        sample = psamples[i];
-                        color = get_percent_color(percent);
+                        struct annotation_data *sample = &al->samples[i];
+
+                        color = get_percent_color(sample->percent);
 
                         if (symbol_conf.show_total_period)
                                 color_fprintf(stdout, color, " %11" PRIu64,
-                                              sample.period);
+                                              sample->he.period);
                         else if (symbol_conf.show_nr_samples)
                                 color_fprintf(stdout, color, " %7" PRIu64,
-                                              sample.nr_samples);
+                                              sample->he.nr_samples);
                         else
-                                color_fprintf(stdout, color, " %7.2f", percent);
+                                color_fprintf(stdout, color, " %7.2f", sample->percent);
                 }
 
-                printf(" :      ");
+                printf(" : ");
 
-                br = block_range__find(addr);
-                color_fprintf(stdout, annotate__address_color(br), "  %" PRIx64 ":", addr);
-                color_fprintf(stdout, annotate__asm_color(br), "%s", dl->line);
-                annotate__branch_printf(br, addr);
+                disasm_line__print(dl, start, addr_fmt_width);
                 printf("\n");
-
-                if (ppercents != &percent)
-                        free(ppercents);
-
-                if (psamples != &sample)
-                        free(psamples);
-
         } else if (max_lines && printed >= max_lines)
                 return 1;
         else {
@@ -1187,10 +1189,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                 if (perf_evsel__is_group_event(evsel))
                         width *= evsel->nr_members;
 
-                if (!*dl->line)
+                if (!*al->line)
                         printf(" %*s:\n", width, " ");
                 else
-                        printf(" %*s:   %s\n", width, " ", dl->line);
+                        printf(" %*s:     %*s %s\n", width, " ", addr_fmt_width, " ", al->line);
         }
 
         return 0;
@@ -1216,11 +1218,11 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
  * means that it's not a disassembly line so should be treated differently.
  * The ops.raw part will be parsed further according to type of the instruction.
  */
-static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
-                                      struct arch *arch,
-                                      FILE *file, size_t privsize,
+static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
+                                      struct annotate_args *args,
                                       int *line_nr)
 {
+        struct map *map = args->map;
         struct annotation *notes = symbol__annotation(sym);
         struct disasm_line *dl;
         char *line = NULL, *parsed_line, *tmp, *tmp2;
@@ -1264,7 +1266,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
                         parsed_line = tmp2 + 1;
         }
 
-        dl = disasm_line__new(offset, parsed_line, privsize, *line_nr, arch, map);
+        args->offset  = offset;
+        args->line    = parsed_line;
+        args->line_nr = *line_nr;
+
+        dl = disasm_line__new(args);
         free(line);
         (*line_nr)++;
 
@@ -1289,7 +1295,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
                         dl->ops.target.name = strdup(target.sym->name);
         }
 
-        disasm__add(&notes->src->source, dl);
+        annotation_line__add(&dl->al, &notes->src->source);
 
         return 0;
 }
@@ -1306,19 +1312,19 @@ static void delete_last_nop(struct symbol *sym)
         struct disasm_line *dl;
 
         while (!list_empty(list)) {
-                dl = list_entry(list->prev, struct disasm_line, node);
+                dl = list_entry(list->prev, struct disasm_line, al.node);
 
                 if (dl->ins.ops) {
                         if (dl->ins.ops != &nop_ops)
                                 return;
                 } else {
-                        if (!strstr(dl->line, " nop ") &&
-                            !strstr(dl->line, " nopl ") &&
-                            !strstr(dl->line, " nopw "))
+                        if (!strstr(dl->al.line, " nop ") &&
+                            !strstr(dl->al.line, " nopl ") &&
+                            !strstr(dl->al.line, " nopw "))
                                 return;
                 }
 
-                list_del(&dl->node);
+                list_del(&dl->al.node);
                 disasm_line__free(dl);
         }
 }
@@ -1413,25 +1419,11 @@ fallback:
         return 0;
 }
 
-static const char *annotate__norm_arch(const char *arch_name)
-{
-        struct utsname uts;
-
-        if (!arch_name) { /* Assume we are annotating locally. */
-                if (uname(&uts) < 0)
-                        return NULL;
-                arch_name = uts.machine;
-        }
-        return normalize_arch((char *)arch_name);
-}
-
-int symbol__disassemble(struct symbol *sym, struct map *map,
-                        const char *arch_name, size_t privsize,
-                        struct arch **parch, char *cpuid)
+static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
+        struct map *map = args->map;
         struct dso *dso = map->dso;
         char command[PATH_MAX * 2];
-        struct arch *arch = NULL;
         FILE *file;
         char symfs_filename[PATH_MAX];
         struct kcore_extract kce;
@@ -1445,28 +1437,6 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
         if (err)
                 return err;
 
-        arch_name = annotate__norm_arch(arch_name);
-        if (!arch_name)
-                return -1;
-
-        arch = arch__find(arch_name);
-        if (arch == NULL)
-                return -ENOTSUP;
-
-        if (parch)
-                *parch = arch;
-
-        if (arch->init) {
-                err = arch->init(arch);
-                if (err) {
-                        pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
-                        return err;
-                }
-        }
-
-        if (arch->cpuid_parse && cpuid)
-                arch->cpuid_parse(arch, cpuid);
-
         pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
                  symfs_filename, sym->name, map->unmap_ip(map, sym->start),
                  map->unmap_ip(map, sym->end));
@@ -1550,8 +1520,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
                  * can associate it with the instructions till the next one.
                  * See disasm_line__new() and struct disasm_line::line_nr.
                  */
-                if (symbol__parse_objdump_line(sym, map, arch, file, privsize,
-                            &lineno) < 0)
+                if (symbol__parse_objdump_line(sym, file, args, &lineno) < 0)
                         break;
                 nline++;
         }
@@ -1584,21 +1553,110 @@ out_close_stdout:
         goto out_remove_tmp;
 }
 
-static void insert_source_line(struct rb_root *root, struct source_line *src_line)
+static void calc_percent(struct sym_hist *hist,
+                         struct annotation_data *sample,
+                         s64 offset, s64 end)
 {
-        struct source_line *iter;
+        unsigned int hits = 0;
+        u64 period = 0;
+
+        while (offset < end) {
+                hits   += hist->addr[offset].nr_samples;
+                period += hist->addr[offset].period;
+                ++offset;
+        }
+
+        if (hist->nr_samples) {
+                sample->he.period     = period;
+                sample->he.nr_samples = hits;
+                sample->percent = 100.0 * hits / hist->nr_samples;
+        }
+}
+
+static void annotation__calc_percent(struct annotation *notes,
+                                     struct perf_evsel *evsel, s64 len)
+{
+        struct annotation_line *al, *next;
+
+        list_for_each_entry(al, &notes->src->source, node) {
+                s64 end;
+                int i;
+
+                if (al->offset == -1)
+                        continue;
+
+                next = annotation_line__next(al, &notes->src->source);
+                end  = next ? next->offset : len;
+
+                for (i = 0; i < al->samples_nr; i++) {
+                        struct annotation_data *sample;
+                        struct sym_hist *hist;
+
+                        hist   = annotation__histogram(notes, evsel->idx + i);
+                        sample = &al->samples[i];
+
+                        calc_percent(hist, sample, al->offset, end);
+                }
+        }
+}
+
+void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel)
+{
+        struct annotation *notes = symbol__annotation(sym);
+
+        annotation__calc_percent(notes, evsel, symbol__size(sym));
+}
+
+int symbol__annotate(struct symbol *sym, struct map *map,
+                     struct perf_evsel *evsel, size_t privsize,
+                     struct arch **parch)
+{
+        struct annotate_args args = {
+                .privsize       = privsize,
+                .map            = map,
+                .evsel          = evsel,
+        };
+        struct perf_env *env = perf_evsel__env(evsel);
+        const char *arch_name = perf_env__arch(env);
+        struct arch *arch;
+        int err;
+
+        if (!arch_name)
+                return -1;
+
+        args.arch = arch = arch__find(arch_name);
+        if (arch == NULL)
+                return -ENOTSUP;
+
+        if (parch)
+                *parch = arch;
+
+        if (arch->init) {
+                err = arch->init(arch, env ? env->cpuid : NULL);
+                if (err) {
+                        pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
+                        return err;
+                }
+        }
+
+        return symbol__disassemble(sym, &args);
+}
+
+static void insert_source_line(struct rb_root *root, struct annotation_line *al)
+{
+        struct annotation_line *iter;
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
         int i, ret;
 
         while (*p != NULL) {
                 parent = *p;
-                iter = rb_entry(parent, struct source_line, node);
+                iter = rb_entry(parent, struct annotation_line, rb_node);
 
-                ret = strcmp(iter->path, src_line->path);
+                ret = strcmp(iter->path, al->path);
                 if (ret == 0) {
-                        for (i = 0; i < src_line->nr_pcnt; i++)
-                                iter->samples[i].percent_sum += src_line->samples[i].percent;
+                        for (i = 0; i < al->samples_nr; i++)
+                                iter->samples[i].percent_sum += al->samples[i].percent;
                         return;
                 }
 
@@ -1608,18 +1666,18 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
                         p = &(*p)->rb_right;
         }
 
-        for (i = 0; i < src_line->nr_pcnt; i++)
-                src_line->samples[i].percent_sum = src_line->samples[i].percent;
+        for (i = 0; i < al->samples_nr; i++)
+                al->samples[i].percent_sum = al->samples[i].percent;
 
-        rb_link_node(&src_line->node, parent, p);
-        rb_insert_color(&src_line->node, root);
+        rb_link_node(&al->rb_node, parent, p);
+        rb_insert_color(&al->rb_node, root);
 }
 
-static int cmp_source_line(struct source_line *a, struct source_line *b)
+static int cmp_source_line(struct annotation_line *a, struct annotation_line *b)
 {
         int i;
 
-        for (i = 0; i < a->nr_pcnt; i++) {
+        for (i = 0; i < a->samples_nr; i++) {
                 if (a->samples[i].percent_sum == b->samples[i].percent_sum)
                         continue;
                 return a->samples[i].percent_sum > b->samples[i].percent_sum;
@@ -1628,135 +1686,47 @@ static int cmp_source_line(struct source_line *a, struct source_line *b)
         return 0;
 }
 
-static void __resort_source_line(struct rb_root *root, struct source_line *src_line)
+static void __resort_source_line(struct rb_root *root, struct annotation_line *al)
 {
-        struct source_line *iter;
+        struct annotation_line *iter;
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
 
         while (*p != NULL) {
                 parent = *p;
-                iter = rb_entry(parent, struct source_line, node);
+                iter = rb_entry(parent, struct annotation_line, rb_node);
 
-                if (cmp_source_line(src_line, iter))
+                if (cmp_source_line(al, iter))
                         p = &(*p)->rb_left;
                 else
                         p = &(*p)->rb_right;
         }
 
-        rb_link_node(&src_line->node, parent, p);
-        rb_insert_color(&src_line->node, root);
+        rb_link_node(&al->rb_node, parent, p);
+        rb_insert_color(&al->rb_node, root);
 }
 
 static void resort_source_line(struct rb_root *dest_root, struct rb_root *src_root)
 {
-        struct source_line *src_line;
+        struct annotation_line *al;
         struct rb_node *node;
 
         node = rb_first(src_root);
         while (node) {
                 struct rb_node *next;
 
-                src_line = rb_entry(node, struct source_line, node);
+                al = rb_entry(node, struct annotation_line, rb_node);
                 next = rb_next(node);
                 rb_erase(node, src_root);
 
-                __resort_source_line(dest_root, src_line);
+                __resort_source_line(dest_root, al);
                 node = next;
         }
 }
 
-static void symbol__free_source_line(struct symbol *sym, int len)
-{
-        struct annotation *notes = symbol__annotation(sym);
-        struct source_line *src_line = notes->src->lines;
-        size_t sizeof_src_line;
-        int i;
-
-        sizeof_src_line = sizeof(*src_line) +
-                          (sizeof(src_line->samples) * (src_line->nr_pcnt - 1));
-
-        for (i = 0; i < len; i++) {
-                free_srcline(src_line->path);
-                src_line = (void *)src_line + sizeof_src_line;
-        }
-
-        zfree(&notes->src->lines);
-}
-
-/* Get the filename:line for the colored entries */
-static int symbol__get_source_line(struct symbol *sym, struct map *map,
-                                   struct perf_evsel *evsel,
-                                   struct rb_root *root, int len)
-{
-        u64 start;
-        int i, k;
-        int evidx = evsel->idx;
-        struct source_line *src_line;
-        struct annotation *notes = symbol__annotation(sym);
-        struct sym_hist *h = annotation__histogram(notes, evidx);
-        struct rb_root tmp_root = RB_ROOT;
-        int nr_pcnt = 1;
-        u64 nr_samples = h->nr_samples;
-        size_t sizeof_src_line = sizeof(struct source_line);
-
-        if (perf_evsel__is_group_event(evsel)) {
-                for (i = 1; i < evsel->nr_members; i++) {
-                        h = annotation__histogram(notes, evidx + i);
-                        nr_samples += h->nr_samples;
-                }
-                nr_pcnt = evsel->nr_members;
-                sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
-        }
-
-        if (!nr_samples)
-                return 0;
-
-        src_line = notes->src->lines = calloc(len, sizeof_src_line);
-        if (!notes->src->lines)
-                return -1;
-
-        start = map__rip_2objdump(map, sym->start);
-
-        for (i = 0; i < len; i++) {
-                u64 offset;
-                double percent_max = 0.0;
-
-                src_line->nr_pcnt = nr_pcnt;
-
-                for (k = 0; k < nr_pcnt; k++) {
-                        double percent = 0.0;
-
-                        h = annotation__histogram(notes, evidx + k);
-                        nr_samples = h->addr[i].nr_samples;
-                        if (h->nr_samples)
-                                percent = 100.0 * nr_samples / h->nr_samples;
-
-                        if (percent > percent_max)
-                                percent_max = percent;
-                        src_line->samples[k].percent = percent;
-                        src_line->samples[k].nr = nr_samples;
-                }
-
-                if (percent_max <= 0.5)
-                        goto next;
-
-                offset = start + i;
-                src_line->path = get_srcline(map->dso, offset, NULL,
-                                             false, true);
-                insert_source_line(&tmp_root, src_line);
-
-        next:
-                src_line = (void *)src_line + sizeof_src_line;
-        }
-
-        resort_source_line(root, &tmp_root);
-        return 0;
-}
-
 static void print_summary(struct rb_root *root, const char *filename)
 {
-        struct source_line *src_line;
+        struct annotation_line *al;
         struct rb_node *node;
 
         printf("\nSorted summary for file %s\n", filename);
@@ -1774,9 +1744,9 @@ static void print_summary(struct rb_root *root, const char *filename)
                 char *path;
                 int i;
 
-                src_line = rb_entry(node, struct source_line, node);
-                for (i = 0; i < src_line->nr_pcnt; i++) {
-                        percent = src_line->samples[i].percent_sum;
+                al = rb_entry(node, struct annotation_line, rb_node);
+                for (i = 0; i < al->samples_nr; i++) {
+                        percent = al->samples[i].percent_sum;
                         color = get_percent_color(percent);
                         color_fprintf(stdout, color, " %7.2f", percent);
 
@@ -1784,7 +1754,7 @@ static void print_summary(struct rb_root *root, const char *filename)
                                 percent_max = percent;
                 }
 
-                path = src_line->path;
+                path = al->path;
                 color = get_percent_color(percent_max);
                 color_fprintf(stdout, color, " %s\n", path);
 
@@ -1805,6 +1775,19 @@ static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
         printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples);
 }
 
+static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start)
+{
+        char bf[32];
+        struct annotation_line *line;
+
+        list_for_each_entry_reverse(line, lines, node) {
+                if (line->offset != -1)
+                        return scnprintf(bf, sizeof(bf), "%" PRIx64, start + line->offset);
+        }
+
+        return 0;
+}
+
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
                             struct perf_evsel *evsel, bool full_paths,
                             int min_pcnt, int max_lines, int context)
@@ -1815,9 +1798,9 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
         const char *evsel_name = perf_evsel__name(evsel);
         struct annotation *notes = symbol__annotation(sym);
         struct sym_hist *h = annotation__histogram(notes, evsel->idx);
-        struct disasm_line *pos, *queue = NULL;
+        struct annotation_line *pos, *queue = NULL;
         u64 start = map__rip_2objdump(map, sym->start);
-        int printed = 2, queue_len = 0;
+        int printed = 2, queue_len = 0, addr_fmt_width;
         int more = 0;
         u64 len;
         int width = symbol_conf.show_total_period ? 12 : 8;
@@ -1848,15 +1831,21 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
         if (verbose > 0)
                 symbol__annotate_hits(sym, evsel);
 
+        addr_fmt_width = annotated_source__addr_fmt_width(&notes->src->source, start);
+
         list_for_each_entry(pos, &notes->src->source, node) {
+                int err;
+
                 if (context && queue == NULL) {
                         queue = pos;
                         queue_len = 0;
                 }
 
-                switch (disasm_line__print(pos, sym, start, evsel, len,
-                                            min_pcnt, printed, max_lines,
-                                            queue)) {
+                err = annotation_line__print(pos, sym, start, evsel, len,
+                                             min_pcnt, printed, max_lines,
+                                             queue, addr_fmt_width);
+
+                switch (err) {
                 case 0:
                         ++printed;
                         if (context) {
@@ -1911,13 +1900,13 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
         }
 }
 
-void disasm__purge(struct list_head *head)
+void annotated_source__purge(struct annotated_source *as)
 {
-        struct disasm_line *pos, *n;
+        struct annotation_line *al, *n;
 
-        list_for_each_entry_safe(pos, n, head, node) {
-                list_del(&pos->node);
-                disasm_line__free(pos);
+        list_for_each_entry_safe(al, n, &as->source, node) {
+                list_del(&al->node);
+                disasm_line__free(disasm_line(al));
         }
 }
 
@@ -1925,10 +1914,10 @@ static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp)
 {
         size_t printed;
 
-        if (dl->offset == -1)
-                return fprintf(fp, "%s\n", dl->line);
+        if (dl->al.offset == -1)
+                return fprintf(fp, "%s\n", dl->al.line);
 
-        printed = fprintf(fp, "%#" PRIx64 " %s", dl->offset, dl->ins.name);
+        printed = fprintf(fp, "%#" PRIx64 " %s", dl->al.offset, dl->ins.name);
 
         if (dl->ops.raw[0] != '\0') {
                 printed += fprintf(fp, "%.*s %s\n", 6 - (int)printed, " ",
@@ -1943,38 +1932,73 @@ size_t disasm__fprintf(struct list_head *head, FILE *fp)
         struct disasm_line *pos;
         size_t printed = 0;
 
-        list_for_each_entry(pos, head, node)
+        list_for_each_entry(pos, head, al.node)
                 printed += disasm_line__fprintf(pos, fp);
 
         return printed;
 }
 
+static void annotation__calc_lines(struct annotation *notes, struct map *map,
+                                  struct rb_root *root, u64 start)
+{
+        struct annotation_line *al;
+        struct rb_root tmp_root = RB_ROOT;
+
+        list_for_each_entry(al, &notes->src->source, node) {
+                double percent_max = 0.0;
+                int i;
+
+                for (i = 0; i < al->samples_nr; i++) {
+                        struct annotation_data *sample;
+
+                        sample = &al->samples[i];
+
+                        if (sample->percent > percent_max)
+                                percent_max = sample->percent;
+                }
+
+                if (percent_max <= 0.5)
+                        continue;
+
+                al->path = get_srcline(map->dso, start + al->offset, NULL,
+                                       false, true, start + al->offset);
+                insert_source_line(&tmp_root, al);
+        }
+
+        resort_source_line(root, &tmp_root);
+}
+
+static void symbol__calc_lines(struct symbol *sym, struct map *map,
+                              struct rb_root *root)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        u64 start = map__rip_2objdump(map, sym->start);
+
+        annotation__calc_lines(notes, map, root, start);
+}
+
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
                          struct perf_evsel *evsel, bool print_lines,
                          bool full_paths, int min_pcnt, int max_lines)
 {
         struct dso *dso = map->dso;
         struct rb_root source_line = RB_ROOT;
-        u64 len;
 
-        if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                0, NULL, NULL) < 0)
+        if (symbol__annotate(sym, map, evsel, 0, NULL) < 0)
                 return -1;
 
-        len = symbol__size(sym);
+        symbol__calc_percent(sym, evsel);
 
         if (print_lines) {
                 srcline_full_filename = full_paths;
-                symbol__get_source_line(sym, map, evsel, &source_line, len);
+                symbol__calc_lines(sym, map, &source_line);
                 print_summary(&source_line, dso->long_name);
         }
 
         symbol__annotate_printf(sym, map, evsel, full_paths,
                                 min_pcnt, max_lines, 0);
-        if (print_lines)
-                symbol__free_source_line(sym, len);
 
-        disasm__purge(&symbol__annotation(sym)->src->source);
+        annotated_source__purge(symbol__annotation(sym)->src);
 
         return 0;
 }
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index f6ba3560de5e..ce427445671f 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -59,33 +59,55 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 struct annotation;
 
+struct sym_hist_entry {
+        u64             nr_samples;
+        u64             period;
+};
+
+struct annotation_data {
+        double                   percent;
+        double                   percent_sum;
+        struct sym_hist_entry    he;
+};
+
+struct annotation_line {
+        struct list_head         node;
+        struct rb_node           rb_node;
+        s64                      offset;
+        char                    *line;
+        int                      line_nr;
+        float                    ipc;
+        u64                      cycles;
+        size_t                   privsize;
+        char                    *path;
+        int                      samples_nr;
+        struct annotation_data   samples[0];
+};
+
 struct disasm_line {
-        struct list_head    node;
-        s64                 offset;
-        char                *line;
-        struct ins          ins;
-        int                 line_nr;
-        float               ipc;
-        u64                 cycles;
-        struct ins_operands ops;
+        struct ins               ins;
+        struct ins_operands      ops;
+
+        /* This needs to be at the end. */
+        struct annotation_line   al;
 };
 
+static inline struct disasm_line *disasm_line(struct annotation_line *al)
+{
+        return al ? container_of(al, struct disasm_line, al) : NULL;
+}
+
 static inline bool disasm_line__has_offset(const struct disasm_line *dl)
 {
         return dl->ops.target.offset_avail;
 }
 
-struct sym_hist_entry {
-        u64             nr_samples;
-        u64             period;
-};
-
 void disasm_line__free(struct disasm_line *dl);
-struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
+struct annotation_line *
+annotation_line__next(struct annotation_line *pos, struct list_head *head);
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
-double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-                            s64 end, const char **path, struct sym_hist_entry *sample);
+void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel);
 
 struct sym_hist {
         u64                   nr_samples;
@@ -104,19 +126,6 @@ struct cyc_hist {
         u16     reset;
 };
 
-struct source_line_samples {
-        double          percent;
-        double          percent_sum;
-        u64             nr;
-};
-
-struct source_line {
-        struct rb_node  node;
-        char            *path;
-        int             nr_pcnt;
-        struct source_line_samples samples[1];
-};
-
 /** struct annotated_source - symbols with hits have this attached as in sannotation
  *
  * @histogram: Array of addr hit histograms per event being monitored
@@ -132,7 +141,6 @@ struct source_line {
  */
 struct annotated_source {
         struct list_head   source;
-        struct source_line *lines;
         int                nr_histograms;
         size_t             sizeof_sym_hist;
         struct cyc_hist    *cycles_hist;
@@ -169,9 +177,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *samp
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__disassemble(struct symbol *sym, struct map *map,
-                        const char *arch_name, size_t privsize,
-                        struct arch **parch, char *cpuid);
+int symbol__annotate(struct symbol *sym, struct map *map,
+                     struct perf_evsel *evsel, size_t privsize,
+                     struct arch **parch);
 
 enum symbol_disassemble_errno {
         SYMBOL_ANNOTATE_ERRNO__SUCCESS          = 0,
@@ -198,7 +206,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
                             int min_pcnt, int max_lines, int context);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
-void disasm__purge(struct list_head *head);
+void annotated_source__purge(struct annotated_source *as);
 
 bool ui__has_annotation(void);
 
diff --git a/tools/perf/util/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-pkt-decoder.c
new file mode 100644
index 000000000000..b94001b756c7
--- /dev/null
+++ b/tools/perf/util/arm-spe-pkt-decoder.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+
+#include "arm-spe-pkt-decoder.h"
+
+#define BIT(n)          (1ULL << (n))
+
+#define NS_FLAG         BIT(63)
+#define EL_FLAG         (BIT(62) | BIT(61))
+
+#define SPE_HEADER0_PAD                 0x0
+#define SPE_HEADER0_END                 0x1
+#define SPE_HEADER0_ADDRESS             0x30 /* address packet (short) */
+#define SPE_HEADER0_ADDRESS_MASK        0x38
+#define SPE_HEADER0_COUNTER             0x18 /* counter packet (short) */
+#define SPE_HEADER0_COUNTER_MASK        0x38
+#define SPE_HEADER0_TIMESTAMP           0x71
+#define SPE_HEADER0_TIMESTAMP           0x71
+#define SPE_HEADER0_EVENTS              0x2
+#define SPE_HEADER0_EVENTS_MASK         0xf
+#define SPE_HEADER0_SOURCE              0x3
+#define SPE_HEADER0_SOURCE_MASK         0xf
+#define SPE_HEADER0_CONTEXT             0x24
+#define SPE_HEADER0_CONTEXT_MASK        0x3c
+#define SPE_HEADER0_OP_TYPE             0x8
+#define SPE_HEADER0_OP_TYPE_MASK        0x3c
+#define SPE_HEADER1_ALIGNMENT           0x0
+#define SPE_HEADER1_ADDRESS             0xb0 /* address packet (extended) */
+#define SPE_HEADER1_ADDRESS_MASK        0xf8
+#define SPE_HEADER1_COUNTER             0x98 /* counter packet (extended) */
+#define SPE_HEADER1_COUNTER_MASK        0xf8
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define le16_to_cpu bswap_16
+#define le32_to_cpu bswap_32
+#define le64_to_cpu bswap_64
+#define memcpy_le64(d, s, n) do { \
+        memcpy((d), (s), (n));    \
+        *(d) = le64_to_cpu(*(d)); \
+} while (0)
+#else
+#define le16_to_cpu
+#define le32_to_cpu
+#define le64_to_cpu
+#define memcpy_le64 memcpy
+#endif
+
+static const char * const arm_spe_packet_name[] = {
+        [ARM_SPE_PAD]           = "PAD",
+        [ARM_SPE_END]           = "END",
+        [ARM_SPE_TIMESTAMP]     = "TS",
+        [ARM_SPE_ADDRESS]       = "ADDR",
+        [ARM_SPE_COUNTER]       = "LAT",
+        [ARM_SPE_CONTEXT]       = "CONTEXT",
+        [ARM_SPE_OP_TYPE]       = "OP-TYPE",
+        [ARM_SPE_EVENTS]        = "EVENTS",
+        [ARM_SPE_DATA_SOURCE]   = "DATA-SOURCE",
+};
+
+const char *arm_spe_pkt_name(enum arm_spe_pkt_type type)
+{
+        return arm_spe_packet_name[type];
+}
+
+/* return ARM SPE payload size from its encoding,
+ * which is in bits 5:4 of the byte.
+ * 00 : byte
+ * 01 : halfword (2)
+ * 10 : word (4)
+ * 11 : doubleword (8)
+ */
+static int payloadlen(unsigned char byte)
+{
+        return 1 << ((byte & 0x30) >> 4);
+}
+
+static int arm_spe_get_payload(const unsigned char *buf, size_t len,
+                               struct arm_spe_pkt *packet)
+{
+        size_t payload_len = payloadlen(buf[0]);
+
+        if (len < 1 + payload_len)
+                return ARM_SPE_NEED_MORE_BYTES;
+
+        buf++;
+
+        switch (payload_len) {
+        case 1: packet->payload = *(uint8_t *)buf; break;
+        case 2: packet->payload = le16_to_cpu(*(uint16_t *)buf); break;
+        case 4: packet->payload = le32_to_cpu(*(uint32_t *)buf); break;
+        case 8: packet->payload = le64_to_cpu(*(uint64_t *)buf); break;
+        default: return ARM_SPE_BAD_PACKET;
+        }
+
+        return 1 + payload_len;
+}
+
+static int arm_spe_get_pad(struct arm_spe_pkt *packet)
+{
+        packet->type = ARM_SPE_PAD;
+        return 1;
+}
+
+static int arm_spe_get_alignment(const unsigned char *buf, size_t len,
+                                 struct arm_spe_pkt *packet)
+{
+        unsigned int alignment = 1 << ((buf[0] & 0xf) + 1);
+
+        if (len < alignment)
+                return ARM_SPE_NEED_MORE_BYTES;
+
+        packet->type = ARM_SPE_PAD;
+        return alignment - (((uintptr_t)buf) & (alignment - 1));
+}
+
+static int arm_spe_get_end(struct arm_spe_pkt *packet)
+{
+        packet->type = ARM_SPE_END;
+        return 1;
+}
+
+static int arm_spe_get_timestamp(const unsigned char *buf, size_t len,
+                                 struct arm_spe_pkt *packet)
+{
+        packet->type = ARM_SPE_TIMESTAMP;
+        return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_events(const unsigned char *buf, size_t len,
+                              struct arm_spe_pkt *packet)
+{
+        int ret = arm_spe_get_payload(buf, len, packet);
+
+        packet->type = ARM_SPE_EVENTS;
+
+        /* we use index to identify Events with a less number of
+         * comparisons in arm_spe_pkt_desc(): E.g., the LLC-ACCESS,
+         * LLC-REFILL, and REMOTE-ACCESS events are identified iff
+         * index > 1.
+         */
+        packet->index = ret - 1;
+
+        return ret;
+}
+
+static int arm_spe_get_data_source(const unsigned char *buf, size_t len,
+                                   struct arm_spe_pkt *packet)
+{
+        packet->type = ARM_SPE_DATA_SOURCE;
+        return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_context(const unsigned char *buf, size_t len,
+                               struct arm_spe_pkt *packet)
+{
+        packet->type = ARM_SPE_CONTEXT;
+        packet->index = buf[0] & 0x3;
+
+        return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_op_type(const unsigned char *buf, size_t len,
+                               struct arm_spe_pkt *packet)
+{
+        packet->type = ARM_SPE_OP_TYPE;
+        packet->index = buf[0] & 0x3;
+        return arm_spe_get_payload(buf, len, packet);
+}
+
+static int arm_spe_get_counter(const unsigned char *buf, size_t len,
+                               const unsigned char ext_hdr, struct arm_spe_pkt *packet)
+{
+        if (len < 2)
+                return ARM_SPE_NEED_MORE_BYTES;
+
+        packet->type = ARM_SPE_COUNTER;
+        if (ext_hdr)
+                packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+        else
+                packet->index = buf[0] & 0x7;
+
+        packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
+
+        return 1 + ext_hdr + 2;
+}
+
+static int arm_spe_get_addr(const unsigned char *buf, size_t len,
+                            const unsigned char ext_hdr, struct arm_spe_pkt *packet)
+{
+        if (len < 8)
+                return ARM_SPE_NEED_MORE_BYTES;
+
+        packet->type = ARM_SPE_ADDRESS;
+        if (ext_hdr)
+                packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+        else
+                packet->index = buf[0] & 0x7;
+
+        memcpy_le64(&packet->payload, buf + 1, 8);
+
+        return 1 + ext_hdr + 8;
+}
+
+static int arm_spe_do_get_packet(const unsigned char *buf, size_t len,
+                                 struct arm_spe_pkt *packet)
+{
+        unsigned int byte;
+
+        memset(packet, 0, sizeof(struct arm_spe_pkt));
+
+        if (!len)
+                return ARM_SPE_NEED_MORE_BYTES;
+
+        byte = buf[0];
+        if (byte == SPE_HEADER0_PAD)
+                return arm_spe_get_pad(packet);
+        else if (byte == SPE_HEADER0_END) /* no timestamp at end of record */
+                return arm_spe_get_end(packet);
+        else if (byte & 0xc0 /* 0y11xxxxxx */) {
+                if (byte & 0x80) {
+                        if ((byte & SPE_HEADER0_ADDRESS_MASK) == SPE_HEADER0_ADDRESS)
+                                return arm_spe_get_addr(buf, len, 0, packet);
+                        if ((byte & SPE_HEADER0_COUNTER_MASK) == SPE_HEADER0_COUNTER)
+                                return arm_spe_get_counter(buf, len, 0, packet);
+                } else
+                        if (byte == SPE_HEADER0_TIMESTAMP)
+                                return arm_spe_get_timestamp(buf, len, packet);
+                        else if ((byte & SPE_HEADER0_EVENTS_MASK) == SPE_HEADER0_EVENTS)
+                                return arm_spe_get_events(buf, len, packet);
+                        else if ((byte & SPE_HEADER0_SOURCE_MASK) == SPE_HEADER0_SOURCE)
+                                return arm_spe_get_data_source(buf, len, packet);
+                        else if ((byte & SPE_HEADER0_CONTEXT_MASK) == SPE_HEADER0_CONTEXT)
+                                return arm_spe_get_context(buf, len, packet);
+                        else if ((byte & SPE_HEADER0_OP_TYPE_MASK) == SPE_HEADER0_OP_TYPE)
+                                return arm_spe_get_op_type(buf, len, packet);
+        } else if ((byte & 0xe0) == 0x20 /* 0y001xxxxx */) {
+                /* 16-bit header */
+                byte = buf[1];
+                if (byte == SPE_HEADER1_ALIGNMENT)
+                        return arm_spe_get_alignment(buf, len, packet);
+                else if ((byte & SPE_HEADER1_ADDRESS_MASK) == SPE_HEADER1_ADDRESS)
+                        return arm_spe_get_addr(buf, len, 1, packet);
+                else if ((byte & SPE_HEADER1_COUNTER_MASK) == SPE_HEADER1_COUNTER)
+                        return arm_spe_get_counter(buf, len, 1, packet);
+        }
+
+        return ARM_SPE_BAD_PACKET;
+}
+
+int arm_spe_get_packet(const unsigned char *buf, size_t len,
+                       struct arm_spe_pkt *packet)
+{
+        int ret;
+
+        ret = arm_spe_do_get_packet(buf, len, packet);
+        /* put multiple consecutive PADs on the same line, up to
+         * the fixed-width output format of 16 bytes per line.
+         */
+        if (ret > 0 && packet->type == ARM_SPE_PAD) {
+                while (ret < 16 && len > (size_t)ret && !buf[ret])
+                        ret += 1;
+        }
+        return ret;
+}
+
+int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf,
+                     size_t buf_len)
+{
+        int ret, ns, el, idx = packet->index;
+        unsigned long long payload = packet->payload;
+        const char *name = arm_spe_pkt_name(packet->type);
+
+        switch (packet->type) {
+        case ARM_SPE_BAD:
+        case ARM_SPE_PAD:
+        case ARM_SPE_END:
+                return snprintf(buf, buf_len, "%s", name);
+        case ARM_SPE_EVENTS: {
+                size_t blen = buf_len;
+
+                ret = 0;
+                ret = snprintf(buf, buf_len, "EV");
+                buf += ret;
+                blen -= ret;
+                if (payload & 0x1) {
+                        ret = snprintf(buf, buf_len, " EXCEPTION-GEN");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (payload & 0x2) {
+                        ret = snprintf(buf, buf_len, " RETIRED");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (payload & 0x4) {
+                        ret = snprintf(buf, buf_len, " L1D-ACCESS");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (payload & 0x8) {
+                        ret = snprintf(buf, buf_len, " L1D-REFILL");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (payload & 0x10) {
+                        ret = snprintf(buf, buf_len, " TLB-ACCESS");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (payload & 0x20) {
+                        ret = snprintf(buf, buf_len, " TLB-REFILL");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (payload & 0x40) {
+                        ret = snprintf(buf, buf_len, " NOT-TAKEN");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (payload & 0x80) {
+                        ret = snprintf(buf, buf_len, " MISPRED");
+                        buf += ret;
+                        blen -= ret;
+                }
+                if (idx > 1) {
+                        if (payload & 0x100) {
+                                ret = snprintf(buf, buf_len, " LLC-ACCESS");
+                                buf += ret;
+                                blen -= ret;
+                        }
+                        if (payload & 0x200) {
+                                ret = snprintf(buf, buf_len, " LLC-REFILL");
+                                buf += ret;
+                                blen -= ret;
+                        }
+                        if (payload & 0x400) {
+                                ret = snprintf(buf, buf_len, " REMOTE-ACCESS");
+                                buf += ret;
+                                blen -= ret;
+                        }
+                }
+                if (ret < 0)
+                        return ret;
+                blen -= ret;
+                return buf_len - blen;
+        }
+        case ARM_SPE_OP_TYPE:
+                switch (idx) {
+                case 0: return snprintf(buf, buf_len, "%s", payload & 0x1 ?
+                                        "COND-SELECT" : "INSN-OTHER");
+                case 1: {
+                        size_t blen = buf_len;
+
+                        if (payload & 0x1)
+                                ret = snprintf(buf, buf_len, "ST");
+                        else
+                                ret = snprintf(buf, buf_len, "LD");
+                        buf += ret;
+                        blen -= ret;
+                        if (payload & 0x2) {
+                                if (payload & 0x4) {
+                                        ret = snprintf(buf, buf_len, " AT");
+                                        buf += ret;
+                                        blen -= ret;
+                                }
+                                if (payload & 0x8) {
+                                        ret = snprintf(buf, buf_len, " EXCL");
+                                        buf += ret;
+                                        blen -= ret;
+                                }
+                                if (payload & 0x10) {
+                                        ret = snprintf(buf, buf_len, " AR");
+                                        buf += ret;
+                                        blen -= ret;
+                                }
+                        } else if (payload & 0x4) {
+                                ret = snprintf(buf, buf_len, " SIMD-FP");
+                                buf += ret;
+                                blen -= ret;
+                        }
+                        if (ret < 0)
+                                return ret;
+                        blen -= ret;
+                        return buf_len - blen;
+                }
+                case 2: {
+                        size_t blen = buf_len;
+
+                        ret = snprintf(buf, buf_len, "B");
+                        buf += ret;
+                        blen -= ret;
+                        if (payload & 0x1) {
+                                ret = snprintf(buf, buf_len, " COND");
+                                buf += ret;
+                                blen -= ret;
+                        }
+                        if (payload & 0x2) {
+                                ret = snprintf(buf, buf_len, " IND");
+                                buf += ret;
+                                blen -= ret;
+                        }
+                        if (ret < 0)
+                                return ret;
+                        blen -= ret;
+                        return buf_len - blen;
+                        }
+                default: return 0;
+                }
+        case ARM_SPE_DATA_SOURCE:
+        case ARM_SPE_TIMESTAMP:
+                return snprintf(buf, buf_len, "%s %lld", name, payload);
+        case ARM_SPE_ADDRESS:
+                switch (idx) {
+                case 0:
+                case 1: ns = !!(packet->payload & NS_FLAG);
+                        el = (packet->payload & EL_FLAG) >> 61;
+                        payload &= ~(0xffULL << 56);
+                        return snprintf(buf, buf_len, "%s 0x%llx el%d ns=%d",
+                                        (idx == 1) ? "TGT" : "PC", payload, el, ns);
+                case 2: return snprintf(buf, buf_len, "VA 0x%llx", payload);
+                case 3: ns = !!(packet->payload & NS_FLAG);
+                        payload &= ~(0xffULL << 56);
+                        return snprintf(buf, buf_len, "PA 0x%llx ns=%d",
+                                        payload, ns);
+                default: return 0;
+                }
+        case ARM_SPE_CONTEXT:
+                return snprintf(buf, buf_len, "%s 0x%lx el%d", name,
+                                (unsigned long)payload, idx + 1);
+        case ARM_SPE_COUNTER: {
+                size_t blen = buf_len;
+
+                ret = snprintf(buf, buf_len, "%s %d ", name,
+                               (unsigned short)payload);
+                buf += ret;
+                blen -= ret;
+                switch (idx) {
+                case 0: ret = snprintf(buf, buf_len, "TOT"); break;
+                case 1: ret = snprintf(buf, buf_len, "ISSUE"); break;
+                case 2: ret = snprintf(buf, buf_len, "XLAT"); break;
+                default: ret = 0;
+                }
+                if (ret < 0)
+                        return ret;
+                blen -= ret;
+                return buf_len - blen;
+        }
+        default:
+                break;
+        }
+
+        return snprintf(buf, buf_len, "%s 0x%llx (%d)",
+                        name, payload, packet->index);
+}
diff --git a/tools/perf/util/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-pkt-decoder.h
new file mode 100644
index 000000000000..d786ef65113f
--- /dev/null
+++ b/tools/perf/util/arm-spe-pkt-decoder.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#ifndef INCLUDE__ARM_SPE_PKT_DECODER_H__
+#define INCLUDE__ARM_SPE_PKT_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define ARM_SPE_PKT_DESC_MAX            256
+
+#define ARM_SPE_NEED_MORE_BYTES         -1
+#define ARM_SPE_BAD_PACKET              -2
+
+enum arm_spe_pkt_type {
+        ARM_SPE_BAD,
+        ARM_SPE_PAD,
+        ARM_SPE_END,
+        ARM_SPE_TIMESTAMP,
+        ARM_SPE_ADDRESS,
+        ARM_SPE_COUNTER,
+        ARM_SPE_CONTEXT,
+        ARM_SPE_OP_TYPE,
+        ARM_SPE_EVENTS,
+        ARM_SPE_DATA_SOURCE,
+};
+
+struct arm_spe_pkt {
+        enum arm_spe_pkt_type   type;
+        unsigned char           index;
+        uint64_t                payload;
+};
+
+const char *arm_spe_pkt_name(enum arm_spe_pkt_type);
+
+int arm_spe_get_packet(const unsigned char *buf, size_t len,
+                       struct arm_spe_pkt *packet);
+
+int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf, size_t len);
+#endif
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
new file mode 100644
index 000000000000..6067267cc76c
--- /dev/null
+++ b/tools/perf/util/arm-spe.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <endian.h>
+#include <errno.h>
+#include <byteswap.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "cpumap.h"
+#include "color.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "session.h"
+#include "util.h"
+#include "thread.h"
+#include "debug.h"
+#include "auxtrace.h"
+#include "arm-spe.h"
+#include "arm-spe-pkt-decoder.h"
+
+struct arm_spe {
+        struct auxtrace                 auxtrace;
+        struct auxtrace_queues          queues;
+        struct auxtrace_heap            heap;
+        u32                             auxtrace_type;
+        struct perf_session             *session;
+        struct machine                  *machine;
+        u32                             pmu_type;
+};
+
+struct arm_spe_queue {
+        struct arm_spe          *spe;
+        unsigned int            queue_nr;
+        struct auxtrace_buffer  *buffer;
+        bool                    on_heap;
+        bool                    done;
+        pid_t                   pid;
+        pid_t                   tid;
+        int                     cpu;
+};
+
+static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
+                         unsigned char *buf, size_t len)
+{
+        struct arm_spe_pkt packet;
+        size_t pos = 0;
+        int ret, pkt_len, i;
+        char desc[ARM_SPE_PKT_DESC_MAX];
+        const char *color = PERF_COLOR_BLUE;
+
+        color_fprintf(stdout, color,
+                      ". ... ARM SPE data: size %zu bytes\n",
+                      len);
+
+        while (len) {
+                ret = arm_spe_get_packet(buf, len, &packet);
+                if (ret > 0)
+                        pkt_len = ret;
+                else
+                        pkt_len = 1;
+                printf(".");
+                color_fprintf(stdout, color, "  %08x: ", pos);
+                for (i = 0; i < pkt_len; i++)
+                        color_fprintf(stdout, color, " %02x", buf[i]);
+                for (; i < 16; i++)
+                        color_fprintf(stdout, color, "   ");
+                if (ret > 0) {
+                        ret = arm_spe_pkt_desc(&packet, desc,
+                                               ARM_SPE_PKT_DESC_MAX);
+                        if (ret > 0)
+                                color_fprintf(stdout, color, " %s\n", desc);
+                } else {
+                        color_fprintf(stdout, color, " Bad packet!\n");
+                }
+                pos += pkt_len;
+                buf += pkt_len;
+                len -= pkt_len;
+        }
+}
+
+static void arm_spe_dump_event(struct arm_spe *spe, unsigned char *buf,
+                               size_t len)
+{
+        printf(".\n");
+        arm_spe_dump(spe, buf, len);
+}
+
+static int arm_spe_process_event(struct perf_session *session __maybe_unused,
+                                 union perf_event *event __maybe_unused,
+                                 struct perf_sample *sample __maybe_unused,
+                                 struct perf_tool *tool __maybe_unused)
+{
+        return 0;
+}
+
+static int arm_spe_process_auxtrace_event(struct perf_session *session,
+                                          union perf_event *event,
+                                          struct perf_tool *tool __maybe_unused)
+{
+        struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe,
+                                             auxtrace);
+        struct auxtrace_buffer *buffer;
+        off_t data_offset;
+        int fd = perf_data__fd(session->data);
+        int err;
+
+        if (perf_data__is_pipe(session->data)) {
+                data_offset = 0;
+        } else {
+                data_offset = lseek(fd, 0, SEEK_CUR);
+                if (data_offset == -1)
+                        return -errno;
+        }
+
+        err = auxtrace_queues__add_event(&spe->queues, session, event,
+                                         data_offset, &buffer);
+        if (err)
+                return err;
+
+        /* Dump here now we have copied a piped trace out of the pipe */
+        if (dump_trace) {
+                if (auxtrace_buffer__get_data(buffer, fd)) {
+                        arm_spe_dump_event(spe, buffer->data,
+                                             buffer->size);
+                        auxtrace_buffer__put_data(buffer);
+                }
+        }
+
+        return 0;
+}
+
+static int arm_spe_flush(struct perf_session *session __maybe_unused,
+                         struct perf_tool *tool __maybe_unused)
+{
+        return 0;
+}
+
+static void arm_spe_free_queue(void *priv)
+{
+        struct arm_spe_queue *speq = priv;
+
+        if (!speq)
+                return;
+        free(speq);
+}
+
+static void arm_spe_free_events(struct perf_session *session)
+{
+        struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe,
+                                             auxtrace);
+        struct auxtrace_queues *queues = &spe->queues;
+        unsigned int i;
+
+        for (i = 0; i < queues->nr_queues; i++) {
+                arm_spe_free_queue(queues->queue_array[i].priv);
+                queues->queue_array[i].priv = NULL;
+        }
+        auxtrace_queues__free(queues);
+}
+
+static void arm_spe_free(struct perf_session *session)
+{
+        struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe,
+                                             auxtrace);
+
+        auxtrace_heap__free(&spe->heap);
+        arm_spe_free_events(session);
+        session->auxtrace = NULL;
+        free(spe);
+}
+
+static const char * const arm_spe_info_fmts[] = {
+        [ARM_SPE_PMU_TYPE]              = "  PMU Type           %"PRId64"\n",
+};
+
+static void arm_spe_print_info(u64 *arr)
+{
+        if (!dump_trace)
+                return;
+
+        fprintf(stdout, arm_spe_info_fmts[ARM_SPE_PMU_TYPE], arr[ARM_SPE_PMU_TYPE]);
+}
+
+int arm_spe_process_auxtrace_info(union perf_event *event,
+                                  struct perf_session *session)
+{
+        struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+        size_t min_sz = sizeof(u64) * ARM_SPE_PMU_TYPE;
+        struct arm_spe *spe;
+        int err;
+
+        if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+                                        min_sz)
+                return -EINVAL;
+
+        spe = zalloc(sizeof(struct arm_spe));
+        if (!spe)
+                return -ENOMEM;
+
+        err = auxtrace_queues__init(&spe->queues);
+        if (err)
+                goto err_free;
+
+        spe->session = session;
+        spe->machine = &session->machines.host; /* No kvm support */
+        spe->auxtrace_type = auxtrace_info->type;
+        spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE];
+
+        spe->auxtrace.process_event = arm_spe_process_event;
+        spe->auxtrace.process_auxtrace_event = arm_spe_process_auxtrace_event;
+        spe->auxtrace.flush_events = arm_spe_flush;
+        spe->auxtrace.free_events = arm_spe_free_events;
+        spe->auxtrace.free = arm_spe_free;
+        session->auxtrace = &spe->auxtrace;
+
+        arm_spe_print_info(&auxtrace_info->priv[0]);
+
+        return 0;
+
+err_free:
+        free(spe);
+        return err;
+}
diff --git a/tools/perf/util/arm-spe.h b/tools/perf/util/arm-spe.h
new file mode 100644
index 000000000000..98d3235781c3
--- /dev/null
+++ b/tools/perf/util/arm-spe.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#ifndef INCLUDE__PERF_ARM_SPE_H__
+#define INCLUDE__PERF_ARM_SPE_H__
+
+#define ARM_SPE_PMU_NAME "arm_spe_"
+
+enum {
+        ARM_SPE_PMU_TYPE,
+        ARM_SPE_PER_CPU_MMAPS,
+        ARM_SPE_AUXTRACE_PRIV_MAX,
+};
+
+#define ARM_SPE_AUXTRACE_PRIV_SIZE (ARM_SPE_AUXTRACE_PRIV_MAX * sizeof(u64))
+
+union perf_event;
+struct perf_session;
+struct perf_pmu;
+
+struct auxtrace_record *arm_spe_recording_init(int *err,
+                                               struct perf_pmu *arm_spe_pmu);
+
+int arm_spe_process_auxtrace_info(union perf_event *event,
+                                  struct perf_session *session);
+
+struct perf_event_attr *arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu);
+#endif
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 5547457566a7..9faf3b5367db 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -31,9 +31,6 @@
 #include <sys/param.h>
 #include <stdlib.h>
 #include <stdio.h>
-#include <string.h>
-#include <limits.h>
-#include <errno.h>
 #include <linux/list.h>
 
 #include "../perf.h"
@@ -55,8 +52,10 @@
 #include "debug.h"
 #include <subcmd/parse-options.h>
 
+#include "cs-etm.h"
 #include "intel-pt.h"
 #include "intel-bts.h"
+#include "arm-spe.h"
 
 #include "sane_ctype.h"
 #include "symbol/kallsyms.h"
@@ -208,7 +207,7 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues,
 
 static void *auxtrace_copy_data(u64 size, struct perf_session *session)
 {
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         void *p;
         ssize_t ret;
 
@@ -305,7 +304,7 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
         if (session->one_mmap) {
                 buffer->data = buffer->data_offset - session->one_mmap_offset +
                                session->one_mmap_addr;
-        } else if (perf_data_file__is_pipe(session->file)) {
+        } else if (perf_data__is_pipe(session->data)) {
                 buffer->data = auxtrace_copy_data(buffer->size, session);
                 if (!buffer->data)
                         return -ENOMEM;
@@ -913,7 +912,10 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
                 return intel_pt_process_auxtrace_info(event, session);
         case PERF_AUXTRACE_INTEL_BTS:
                 return intel_bts_process_auxtrace_info(event, session);
+        case PERF_AUXTRACE_ARM_SPE:
+                return arm_spe_process_auxtrace_info(event, session);
         case PERF_AUXTRACE_CS_ETM:
+                return cs_etm__process_auxtrace_info(event, session);
         case PERF_AUXTRACE_UNKNOWN:
         default:
                 return -EINVAL;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 33b5e6cdf38c..453c148d2158 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -43,6 +43,7 @@ enum auxtrace_type {
         PERF_AUXTRACE_INTEL_PT,
         PERF_AUXTRACE_INTEL_BTS,
         PERF_AUXTRACE_CS_ETM,
+        PERF_AUXTRACE_ARM_SPE,
 };
 
 enum itrace_period_type {
@@ -378,7 +379,7 @@ struct addr_filters {
 static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
 {
         struct perf_event_mmap_page *pc = mm->userpg;
-        u64 head = ACCESS_ONCE(pc->aux_head);
+        u64 head = READ_ONCE(pc->aux_head);
 
         /* Ensure all reads are done after we read the head */
         rmb();
@@ -389,7 +390,7 @@ static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
 {
         struct perf_event_mmap_page *pc = mm->userpg;
 #if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
-        u64 head = ACCESS_ONCE(pc->aux_head);
+        u64 head = READ_ONCE(pc->aux_head);
 #else
         u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
 #endif
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 72c107fcbc5a..af7ad814b2c3 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -94,7 +94,7 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
                 err = perf_clang__compile_bpf(filename, &obj_buf, &obj_buf_sz);
                 perf_clang__cleanup();
                 if (err) {
-                        pr_warning("bpf: builtin compilation failed: %d, try external compiler\n", err);
+                        pr_debug("bpf: builtin compilation failed: %d, try external compiler\n", err);
                         err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
                         if (err)
                                 return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
@@ -1533,7 +1533,7 @@ int bpf__apply_obj_config(void)
                         (strcmp("__bpf_stdout__",       \
                                 bpf_map__name(pos)) == 0))
 
-int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
+int bpf__setup_stdout(struct perf_evlist *evlist)
 {
         struct bpf_map_priv *tmpl_priv = NULL;
         struct bpf_object *obj, *tmp;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 6031933d811c..32ef7bdca1cf 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -37,6 +37,15 @@ struct callchain_param callchain_param = {
         CALLCHAIN_PARAM_DEFAULT
 };
 
+/*
+ * Are there any events usind DWARF callchains?
+ *
+ * I.e.
+ *
+ * -e cycles/call-graph=dwarf/
+ */
+bool dwarf_callchain_users;
+
 struct callchain_param callchain_param_default = {
         CALLCHAIN_PARAM_DEFAULT
 };
@@ -265,6 +274,7 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
                         ret = 0;
                         param->record_mode = CALLCHAIN_DWARF;
                         param->dump_size = default_stack_dump_size;
+                        dwarf_callchain_users = true;
 
                         tok = strtok_r(NULL, ",", &saveptr);
                         if (tok) {
@@ -567,6 +577,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
                 call->ip = cursor_node->ip;
                 call->ms.sym = cursor_node->sym;
                 call->ms.map = map__get(cursor_node->map);
+                call->srcline = cursor_node->srcline;
 
                 if (cursor_node->branch) {
                         call->branch_count = 1;
@@ -645,103 +656,120 @@ enum match_result {
         MATCH_GT,
 };
 
-static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
-                                             struct callchain_list *cnode)
+static enum match_result match_chain_strings(const char *left,
+                                             const char *right)
 {
-        char *left = NULL;
-        char *right = NULL;
         enum match_result ret = MATCH_EQ;
         int cmp;
 
-        if (cnode->ms.map)
-                left = get_srcline(cnode->ms.map->dso,
-                                 map__rip_2objdump(cnode->ms.map, cnode->ip),
-                                 cnode->ms.sym, true, false);
-        if (node->map)
-                right = get_srcline(node->map->dso,
-                                  map__rip_2objdump(node->map, node->ip),
-                                  node->sym, true, false);
-
         if (left && right)
                 cmp = strcmp(left, right);
         else if (!left && right)
                 cmp = 1;
         else if (left && !right)
                 cmp = -1;
-        else if (cnode->ip == node->ip)
-                cmp = 0;
         else
-                cmp = (cnode->ip < node->ip) ? -1 : 1;
+                return MATCH_ERROR;
 
         if (cmp != 0)
                 ret = cmp < 0 ? MATCH_LT : MATCH_GT;
 
-        free_srcline(left);
-        free_srcline(right);
         return ret;
 }
 
+/*
+ * We need to always use relative addresses because we're aggregating
+ * callchains from multiple threads, i.e. different address spaces, so
+ * comparing absolute addresses make no sense as a symbol in a DSO may end up
+ * in a different address when used in a different binary or even the same
+ * binary but with some sort of address randomization technique, thus we need
+ * to compare just relative addresses. -acme
+ */
+static enum match_result match_chain_dso_addresses(struct map *left_map, u64 left_ip,
+                                                   struct map *right_map, u64 right_ip)
+{
+        struct dso *left_dso = left_map ? left_map->dso : NULL;
+        struct dso *right_dso = right_map ? right_map->dso : NULL;
+
+        if (left_dso != right_dso)
+                return left_dso < right_dso ? MATCH_LT : MATCH_GT;
+
+        if (left_ip != right_ip)
+                return left_ip < right_ip ? MATCH_LT : MATCH_GT;
+
+        return MATCH_EQ;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
                                      struct callchain_list *cnode)
 {
-        struct symbol *sym = node->sym;
-        u64 left, right;
-        struct dso *left_dso = NULL;
-        struct dso *right_dso = NULL;
-
-        if (callchain_param.key == CCKEY_SRCLINE) {
-                enum match_result match = match_chain_srcline(node, cnode);
+        enum match_result match = MATCH_ERROR;
 
+        switch (callchain_param.key) {
+        case CCKEY_SRCLINE:
+                match = match_chain_strings(cnode->srcline, node->srcline);
                 if (match != MATCH_ERROR)
-                        return match;
-        }
-
-        if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
-                left = cnode->ms.sym->start;
-                right = sym->start;
-                left_dso = cnode->ms.map->dso;
-                right_dso = node->map->dso;
-        } else {
-                left = cnode->ip;
-                right = node->ip;
+                        break;
+                /* otherwise fall-back to symbol-based comparison below */
+                __fallthrough;
+        case CCKEY_FUNCTION:
+                if (node->sym && cnode->ms.sym) {
+                        /*
+                         * Compare inlined frames based on their symbol name
+                         * because different inlined frames will have the same
+                         * symbol start. Otherwise do a faster comparison based
+                         * on the symbol start address.
+                         */
+                        if (cnode->ms.sym->inlined || node->sym->inlined) {
+                                match = match_chain_strings(cnode->ms.sym->name,
+                                                            node->sym->name);
+                                if (match != MATCH_ERROR)
+                                        break;
+                        } else {
+                                match = match_chain_dso_addresses(cnode->ms.map, cnode->ms.sym->start,
+                                                                  node->map, node->sym->start);
+                                break;
+                        }
+                }
+                /* otherwise fall-back to IP-based comparison below */
+                __fallthrough;
+        case CCKEY_ADDRESS:
+        default:
+                match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->map, node->ip);
+                break;
         }
 
-        if (left == right && left_dso == right_dso) {
-                if (node->branch) {
-                        cnode->branch_count++;
+        if (match == MATCH_EQ && node->branch) {
+                cnode->branch_count++;
 
-                        if (node->branch_from) {
-                                /*
-                                 * It's "to" of a branch
-                                 */
-                                cnode->brtype_stat.branch_to = true;
+                if (node->branch_from) {
+                        /*
+                         * It's "to" of a branch
+                         */
+                        cnode->brtype_stat.branch_to = true;
 
-                                if (node->branch_flags.predicted)
-                                        cnode->predicted_count++;
+                        if (node->branch_flags.predicted)
+                                cnode->predicted_count++;
 
-                                if (node->branch_flags.abort)
-                                        cnode->abort_count++;
+                        if (node->branch_flags.abort)
+                                cnode->abort_count++;
 
-                                branch_type_count(&cnode->brtype_stat,
-                                                  &node->branch_flags,
-                                                  node->branch_from,
-                                                  node->ip);
-                        } else {
-                                /*
-                                 * It's "from" of a branch
-                                 */
-                                cnode->brtype_stat.branch_to = false;
-                                cnode->cycles_count +=
-                                        node->branch_flags.cycles;
-                                cnode->iter_count += node->nr_loop_iter;
-                                cnode->iter_cycles += node->iter_cycles;
-                        }
+                        branch_type_count(&cnode->brtype_stat,
+                                          &node->branch_flags,
+                                          node->branch_from,
+                                          node->ip);
+                } else {
+                        /*
+                         * It's "from" of a branch
+                         */
+                        cnode->brtype_stat.branch_to = false;
+                        cnode->cycles_count += node->branch_flags.cycles;
+                        cnode->iter_count += node->nr_loop_iter;
+                        cnode->iter_cycles += node->iter_cycles;
                 }
-
-                return MATCH_EQ;
         }
 
-        return left > right ? MATCH_GT : MATCH_LT;
+        return match;
 }
 
 /*
@@ -970,7 +998,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
         list_for_each_entry_safe(list, next_list, &src->val, list) {
                 callchain_cursor_append(cursor, list->ip,
                                         list->ms.map, list->ms.sym,
-                                        false, NULL, 0, 0, 0);
+                                        false, NULL, 0, 0, 0, list->srcline);
                 list_del(&list->list);
                 map__zput(list->ms.map);
                 free(list);
@@ -1010,7 +1038,8 @@ int callchain_merge(struct callchain_cursor *cursor,
 int callchain_cursor_append(struct callchain_cursor *cursor,
                             u64 ip, struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, u64 iter_cycles, u64 branch_from)
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+                            const char *srcline)
 {
         struct callchain_cursor_node *node = *cursor->last;
 
@@ -1029,6 +1058,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
         node->branch = branch;
         node->nr_loop_iter = nr_loop_iter;
         node->iter_cycles = iter_cycles;
+        node->srcline = srcline;
 
         if (flags)
                 memcpy(&node->branch_flags, flags,
@@ -1071,10 +1101,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 {
         al->map = node->map;
         al->sym = node->sym;
-        if (node->map)
-                al->addr = node->map->map_ip(node->map, node->ip);
-        else
-                al->addr = node->ip;
+        al->srcline = node->srcline;
+        al->addr = node->ip;
 
         if (al->sym == NULL) {
                 if (hide_unresolved)
@@ -1116,16 +1144,15 @@ char *callchain_list__sym_name(struct callchain_list *cl,
         int printed;
 
         if (cl->ms.sym) {
-                if (show_srcline && cl->ms.map && !cl->srcline)
-                        cl->srcline = get_srcline(cl->ms.map->dso,
-                                                  map__rip_2objdump(cl->ms.map,
-                                                                    cl->ip),
-                                                  cl->ms.sym, false, show_addr);
-                if (cl->srcline)
-                        printed = scnprintf(bf, bfsize, "%s %s",
-                                        cl->ms.sym->name, cl->srcline);
+                const char *inlined = cl->ms.sym->inlined ? " (inlined)" : "";
+
+                if (show_srcline && cl->srcline)
+                        printed = scnprintf(bf, bfsize, "%s %s%s",
+                                            cl->ms.sym->name, cl->srcline,
+                                            inlined);
                 else
-                        printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+                        printed = scnprintf(bf, bfsize, "%s%s",
+                                            cl->ms.sym->name, inlined);
         } else
                 printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
 
@@ -1533,7 +1560,7 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
                                              node->branch, &node->branch_flags,
                                              node->nr_loop_iter,
                                              node->iter_cycles,
-                                             node->branch_from);
+                                             node->branch_from, node->srcline);
                 if (rc)
                         break;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index f967aa47d0a1..154560b1eb65 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -89,6 +89,8 @@ enum chain_value {
         CCVAL_COUNT,
 };
 
+extern bool dwarf_callchain_users;
+
 struct callchain_param {
         bool                    enabled;
         enum perf_call_graph_mode record_mode;
@@ -122,7 +124,7 @@ struct callchain_list {
         u64                     iter_count;
         u64                     iter_cycles;
         struct branch_type_stat brtype_stat;
-        char                   *srcline;
+        const char              *srcline;
         struct list_head        list;
 };
 
@@ -136,6 +138,7 @@ struct callchain_cursor_node {
         u64                             ip;
         struct map                      *map;
         struct symbol                   *sym;
+        const char                      *srcline;
         bool                            branch;
         struct branch_flags             branch_flags;
         u64                             branch_from;
@@ -202,7 +205,8 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
                             struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, u64 iter_cycles, u64 branch_from);
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from,
+                            const char *srcline);
 
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index d9ffc1e6eb39..984f69144f87 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -6,6 +6,9 @@
 #include "cgroup.h"
 #include "evlist.h"
 #include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 int nr_cgroups;
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 8808570f8e9c..7798a2cc8a86 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
+#include "rwsem.h"
 
 struct comm_str {
         char *str;
@@ -15,6 +16,7 @@ struct comm_str {
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
+static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,};
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
@@ -26,7 +28,9 @@ static struct comm_str *comm_str__get(struct comm_str *cs)
 static void comm_str__put(struct comm_str *cs)
 {
         if (cs && refcount_dec_and_test(&cs->refcnt)) {
+                down_write(&comm_str_lock);
                 rb_erase(&cs->rb_node, &comm_str_root);
+                up_write(&comm_str_lock);
                 zfree(&cs->str);
                 free(cs);
         }
@@ -51,7 +55,8 @@ static struct comm_str *comm_str__alloc(const char *str)
         return cs;
 }
 
-static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+static
+struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 {
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
@@ -82,6 +87,17 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
         return new;
 }
 
+static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
+{
+        struct comm_str *cs;
+
+        down_write(&comm_str_lock);
+        cs = __comm_str__findnew(str, root);
+        up_write(&comm_str_lock);
+
+        return cs;
+}
+
 struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
         struct comm *comm = zalloc(sizeof(*comm));
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 4b893c622236..84eb9393c7db 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -701,10 +701,7 @@ struct perf_config_set *perf_config_set__new(void)
 
         if (set) {
                 INIT_LIST_HEAD(&set->sections);
-                if (perf_config_set__init(set) < 0) {
-                        perf_config_set__delete(set);
-                        set = NULL;
-                }
+                perf_config_set__init(set);
         }
 
         return set;
diff --git a/tools/perf/util/cs-etm-decoder/Build b/tools/perf/util/cs-etm-decoder/Build
new file mode 100644
index 000000000000..bc22c39c727f
--- /dev/null
+++ b/tools/perf/util/cs-etm-decoder/Build
@@ -0,0 +1 @@
+libperf-$(CONFIG_AUXTRACE) += cs-etm-decoder.o
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
new file mode 100644
index 000000000000..1fb01849f1c7
--- /dev/null
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -0,0 +1,513 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(C) 2015-2018 Linaro Limited.
+ *
+ * Author: Tor Jeremiassen <tor@ti.com>
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#include <linux/err.h>
+#include <linux/list.h>
+#include <stdlib.h>
+#include <opencsd/c_api/opencsd_c_api.h>
+#include <opencsd/etmv4/trc_pkt_types_etmv4.h>
+#include <opencsd/ocsd_if_types.h>
+
+#include "cs-etm.h"
+#include "cs-etm-decoder.h"
+#include "intlist.h"
+#include "util.h"
+
+#define MAX_BUFFER 1024
+
+/* use raw logging */
+#ifdef CS_DEBUG_RAW
+#define CS_LOG_RAW_FRAMES
+#ifdef CS_RAW_PACKED
+#define CS_RAW_DEBUG_FLAGS (OCSD_DFRMTR_UNPACKED_RAW_OUT | \
+                            OCSD_DFRMTR_PACKED_RAW_OUT)
+#else
+#define CS_RAW_DEBUG_FLAGS (OCSD_DFRMTR_UNPACKED_RAW_OUT)
+#endif
+#endif
+
+struct cs_etm_decoder {
+        void *data;
+        void (*packet_printer)(const char *msg);
+        bool trace_on;
+        dcd_tree_handle_t dcd_tree;
+        cs_etm_mem_cb_type mem_access;
+        ocsd_datapath_resp_t prev_return;
+        u32 packet_count;
+        u32 head;
+        u32 tail;
+        struct cs_etm_packet packet_buffer[MAX_BUFFER];
+};
+
+static u32
+cs_etm_decoder__mem_access(const void *context,
+                           const ocsd_vaddr_t address,
+                           const ocsd_mem_space_acc_t mem_space __maybe_unused,
+                           const u32 req_size,
+                           u8 *buffer)
+{
+        struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+
+        return decoder->mem_access(decoder->data,
+                                   address,
+                                   req_size,
+                                   buffer);
+}
+
+int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
+                                      u64 start, u64 end,
+                                      cs_etm_mem_cb_type cb_func)
+{
+        decoder->mem_access = cb_func;
+
+        if (ocsd_dt_add_callback_mem_acc(decoder->dcd_tree, start, end,
+                                         OCSD_MEM_SPACE_ANY,
+                                         cs_etm_decoder__mem_access, decoder))
+                return -1;
+
+        return 0;
+}
+
+int cs_etm_decoder__reset(struct cs_etm_decoder *decoder)
+{
+        ocsd_datapath_resp_t dp_ret;
+
+        dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET,
+                                      0, 0, NULL, NULL);
+        if (OCSD_DATA_RESP_IS_FATAL(dp_ret))
+                return -1;
+
+        return 0;
+}
+
+int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+                               struct cs_etm_packet *packet)
+{
+        if (!decoder || !packet)
+                return -EINVAL;
+
+        /* Nothing to do, might as well just return */
+        if (decoder->packet_count == 0)
+                return 0;
+
+        *packet = decoder->packet_buffer[decoder->head];
+
+        decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
+
+        decoder->packet_count--;
+
+        return 1;
+}
+
+static void cs_etm_decoder__gen_etmv4_config(struct cs_etm_trace_params *params,
+                                             ocsd_etmv4_cfg *config)
+{
+        config->reg_configr = params->etmv4.reg_configr;
+        config->reg_traceidr = params->etmv4.reg_traceidr;
+        config->reg_idr0 = params->etmv4.reg_idr0;
+        config->reg_idr1 = params->etmv4.reg_idr1;
+        config->reg_idr2 = params->etmv4.reg_idr2;
+        config->reg_idr8 = params->etmv4.reg_idr8;
+        config->reg_idr9 = 0;
+        config->reg_idr10 = 0;
+        config->reg_idr11 = 0;
+        config->reg_idr12 = 0;
+        config->reg_idr13 = 0;
+        config->arch_ver = ARCH_V8;
+        config->core_prof = profile_CortexA;
+}
+
+static void cs_etm_decoder__print_str_cb(const void *p_context,
+                                         const char *msg,
+                                         const int str_len)
+{
+        if (p_context && str_len)
+                ((struct cs_etm_decoder *)p_context)->packet_printer(msg);
+}
+
+static int
+cs_etm_decoder__init_def_logger_printing(struct cs_etm_decoder_params *d_params,
+                                         struct cs_etm_decoder *decoder)
+{
+        int ret = 0;
+
+        if (d_params->packet_printer == NULL)
+                return -1;
+
+        decoder->packet_printer = d_params->packet_printer;
+
+        /*
+         * Set up a library default logger to process any printers
+         * (packet/raw frame) we add later.
+         */
+        ret = ocsd_def_errlog_init(OCSD_ERR_SEV_ERROR, 1);
+        if (ret != 0)
+                return -1;
+
+        /* no stdout / err / file output */
+        ret = ocsd_def_errlog_config_output(C_API_MSGLOGOUT_FLG_NONE, NULL);
+        if (ret != 0)
+                return -1;
+
+        /*
+         * Set the string CB for the default logger, passes strings to
+         * perf print logger.
+         */
+        ret = ocsd_def_errlog_set_strprint_cb(decoder->dcd_tree,
+                                              (void *)decoder,
+                                              cs_etm_decoder__print_str_cb);
+        if (ret != 0)
+                ret = -1;
+
+        return 0;
+}
+
+#ifdef CS_LOG_RAW_FRAMES
+static void
+cs_etm_decoder__init_raw_frame_logging(struct cs_etm_decoder_params *d_params,
+                                       struct cs_etm_decoder *decoder)
+{
+        /* Only log these during a --dump operation */
+        if (d_params->operation == CS_ETM_OPERATION_PRINT) {
+                /* set up a library default logger to process the
+                 *  raw frame printer we add later
+                 */
+                ocsd_def_errlog_init(OCSD_ERR_SEV_ERROR, 1);
+
+                /* no stdout / err / file output */
+                ocsd_def_errlog_config_output(C_API_MSGLOGOUT_FLG_NONE, NULL);
+
+                /* set the string CB for the default logger,
+                 * passes strings to perf print logger.
+                 */
+                ocsd_def_errlog_set_strprint_cb(decoder->dcd_tree,
+                                                (void *)decoder,
+                                                cs_etm_decoder__print_str_cb);
+
+                /* use the built in library printer for the raw frames */
+                ocsd_dt_set_raw_frame_printer(decoder->dcd_tree,
+                                              CS_RAW_DEBUG_FLAGS);
+        }
+}
+#else
+static void
+cs_etm_decoder__init_raw_frame_logging(
+                struct cs_etm_decoder_params *d_params __maybe_unused,
+                struct cs_etm_decoder *decoder __maybe_unused)
+{
+}
+#endif
+
+static int cs_etm_decoder__create_packet_printer(struct cs_etm_decoder *decoder,
+                                                 const char *decoder_name,
+                                                 void *trace_config)
+{
+        u8 csid;
+
+        if (ocsd_dt_create_decoder(decoder->dcd_tree, decoder_name,
+                                   OCSD_CREATE_FLG_PACKET_PROC,
+                                   trace_config, &csid))
+                return -1;
+
+        if (ocsd_dt_set_pkt_protocol_printer(decoder->dcd_tree, csid, 0))
+                return -1;
+
+        return 0;
+}
+
+static int
+cs_etm_decoder__create_etm_packet_printer(struct cs_etm_trace_params *t_params,
+                                          struct cs_etm_decoder *decoder)
+{
+        const char *decoder_name;
+        ocsd_etmv4_cfg trace_config_etmv4;
+        void *trace_config;
+
+        switch (t_params->protocol) {
+        case CS_ETM_PROTO_ETMV4i:
+                cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
+                decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
+                trace_config = &trace_config_etmv4;
+                break;
+        default:
+                return -1;
+        }
+
+        return cs_etm_decoder__create_packet_printer(decoder,
+                                                     decoder_name,
+                                                     trace_config);
+}
+
+static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
+{
+        int i;
+
+        decoder->head = 0;
+        decoder->tail = 0;
+        decoder->packet_count = 0;
+        for (i = 0; i < MAX_BUFFER; i++) {
+                decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
+                decoder->packet_buffer[i].end_addr   = 0xdeadbeefdeadbeefUL;
+                decoder->packet_buffer[i].exc        = false;
+                decoder->packet_buffer[i].exc_ret    = false;
+                decoder->packet_buffer[i].cpu        = INT_MIN;
+        }
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
+                              const ocsd_generic_trace_elem *elem,
+                              const u8 trace_chan_id,
+                              enum cs_etm_sample_type sample_type)
+{
+        u32 et = 0;
+        struct int_node *inode = NULL;
+
+        if (decoder->packet_count >= MAX_BUFFER - 1)
+                return OCSD_RESP_FATAL_SYS_ERR;
+
+        /* Search the RB tree for the cpu associated with this traceID */
+        inode = intlist__find(traceid_list, trace_chan_id);
+        if (!inode)
+                return OCSD_RESP_FATAL_SYS_ERR;
+
+        et = decoder->tail;
+        decoder->packet_buffer[et].sample_type = sample_type;
+        decoder->packet_buffer[et].start_addr = elem->st_addr;
+        decoder->packet_buffer[et].end_addr = elem->en_addr;
+        decoder->packet_buffer[et].exc = false;
+        decoder->packet_buffer[et].exc_ret = false;
+        decoder->packet_buffer[et].cpu = *((int *)inode->priv);
+
+        /* Wrap around if need be */
+        et = (et + 1) & (MAX_BUFFER - 1);
+
+        decoder->tail = et;
+        decoder->packet_count++;
+
+        if (decoder->packet_count == MAX_BUFFER - 1)
+                return OCSD_RESP_WAIT;
+
+        return OCSD_RESP_CONT;
+}
+
+static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
+                                const void *context,
+                                const ocsd_trc_index_t indx __maybe_unused,
+                                const u8 trace_chan_id __maybe_unused,
+                                const ocsd_generic_trace_elem *elem)
+{
+        ocsd_datapath_resp_t resp = OCSD_RESP_CONT;
+        struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+
+        switch (elem->elem_type) {
+        case OCSD_GEN_TRC_ELEM_UNKNOWN:
+                break;
+        case OCSD_GEN_TRC_ELEM_NO_SYNC:
+                decoder->trace_on = false;
+                break;
+        case OCSD_GEN_TRC_ELEM_TRACE_ON:
+                decoder->trace_on = true;
+                break;
+        case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
+                resp = cs_etm_decoder__buffer_packet(decoder, elem,
+                                                     trace_chan_id,
+                                                     CS_ETM_RANGE);
+                break;
+        case OCSD_GEN_TRC_ELEM_EXCEPTION:
+                decoder->packet_buffer[decoder->tail].exc = true;
+                break;
+        case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
+                decoder->packet_buffer[decoder->tail].exc_ret = true;
+                break;
+        case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
+        case OCSD_GEN_TRC_ELEM_EO_TRACE:
+        case OCSD_GEN_TRC_ELEM_ADDR_NACC:
+        case OCSD_GEN_TRC_ELEM_TIMESTAMP:
+        case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
+        case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
+        case OCSD_GEN_TRC_ELEM_EVENT:
+        case OCSD_GEN_TRC_ELEM_SWTRACE:
+        case OCSD_GEN_TRC_ELEM_CUSTOM:
+        default:
+                break;
+        }
+
+        return resp;
+}
+
+static int cs_etm_decoder__create_etm_packet_decoder(
+                                        struct cs_etm_trace_params *t_params,
+                                        struct cs_etm_decoder *decoder)
+{
+        const char *decoder_name;
+        ocsd_etmv4_cfg trace_config_etmv4;
+        void *trace_config;
+        u8 csid;
+
+        switch (t_params->protocol) {
+        case CS_ETM_PROTO_ETMV4i:
+                cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
+                decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
+                trace_config = &trace_config_etmv4;
+                break;
+        default:
+                return -1;
+        }
+
+        if (ocsd_dt_create_decoder(decoder->dcd_tree,
+                                     decoder_name,
+                                     OCSD_CREATE_FLG_FULL_DECODER,
+                                     trace_config, &csid))
+                return -1;
+
+        if (ocsd_dt_set_gen_elem_outfn(decoder->dcd_tree,
+                                       cs_etm_decoder__gen_trace_elem_printer,
+                                       decoder))
+                return -1;
+
+        return 0;
+}
+
+static int
+cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params,
+                                   struct cs_etm_trace_params *t_params,
+                                   struct cs_etm_decoder *decoder)
+{
+        if (d_params->operation == CS_ETM_OPERATION_PRINT)
+                return cs_etm_decoder__create_etm_packet_printer(t_params,
+                                                                 decoder);
+        else if (d_params->operation == CS_ETM_OPERATION_DECODE)
+                return cs_etm_decoder__create_etm_packet_decoder(t_params,
+                                                                 decoder);
+
+        return -1;
+}
+
+struct cs_etm_decoder *
+cs_etm_decoder__new(int num_cpu, struct cs_etm_decoder_params *d_params,
+                    struct cs_etm_trace_params t_params[])
+{
+        struct cs_etm_decoder *decoder;
+        ocsd_dcd_tree_src_t format;
+        u32 flags;
+        int i, ret;
+
+        if ((!t_params) || (!d_params))
+                return NULL;
+
+        decoder = zalloc(sizeof(*decoder));
+
+        if (!decoder)
+                return NULL;
+
+        decoder->data = d_params->data;
+        decoder->prev_return = OCSD_RESP_CONT;
+        cs_etm_decoder__clear_buffer(decoder);
+        format = (d_params->formatted ? OCSD_TRC_SRC_FRAME_FORMATTED :
+                                         OCSD_TRC_SRC_SINGLE);
+        flags = 0;
+        flags |= (d_params->fsyncs ? OCSD_DFRMTR_HAS_FSYNCS : 0);
+        flags |= (d_params->hsyncs ? OCSD_DFRMTR_HAS_HSYNCS : 0);
+        flags |= (d_params->frame_aligned ? OCSD_DFRMTR_FRAME_MEM_ALIGN : 0);
+
+        /*
+         * Drivers may add barrier frames when used with perf, set up to
+         * handle this. Barriers const of FSYNC packet repeated 4 times.
+         */
+        flags |= OCSD_DFRMTR_RESET_ON_4X_FSYNC;
+
+        /* Create decode tree for the data source */
+        decoder->dcd_tree = ocsd_create_dcd_tree(format, flags);
+
+        if (decoder->dcd_tree == 0)
+                goto err_free_decoder;
+
+        /* init library print logging support */
+        ret = cs_etm_decoder__init_def_logger_printing(d_params, decoder);
+        if (ret != 0)
+                goto err_free_decoder_tree;
+
+        /* init raw frame logging if required */
+        cs_etm_decoder__init_raw_frame_logging(d_params, decoder);
+
+        for (i = 0; i < num_cpu; i++) {
+                ret = cs_etm_decoder__create_etm_decoder(d_params,
+                                                         &t_params[i],
+                                                         decoder);
+                if (ret != 0)
+                        goto err_free_decoder_tree;
+        }
+
+        return decoder;
+
+err_free_decoder_tree:
+        ocsd_destroy_dcd_tree(decoder->dcd_tree);
+err_free_decoder:
+        free(decoder);
+        return NULL;
+}
+
+int cs_etm_decoder__process_data_block(struct cs_etm_decoder *decoder,
+                                       u64 indx, const u8 *buf,
+                                       size_t len, size_t *consumed)
+{
+        int ret = 0;
+        ocsd_datapath_resp_t cur = OCSD_RESP_CONT;
+        ocsd_datapath_resp_t prev_return = decoder->prev_return;
+        size_t processed = 0;
+        u32 count;
+
+        while (processed < len) {
+                if (OCSD_DATA_RESP_IS_WAIT(prev_return)) {
+                        cur = ocsd_dt_process_data(decoder->dcd_tree,
+                                                   OCSD_OP_FLUSH,
+                                                   0,
+                                                   0,
+                                                   NULL,
+                                                   NULL);
+                } else if (OCSD_DATA_RESP_IS_CONT(prev_return)) {
+                        cur = ocsd_dt_process_data(decoder->dcd_tree,
+                                                   OCSD_OP_DATA,
+                                                   indx + processed,
+                                                   len - processed,
+                                                   &buf[processed],
+                                                   &count);
+                        processed += count;
+                } else {
+                        ret = -EINVAL;
+                        break;
+                }
+
+                /*
+                 * Return to the input code if the packet buffer is full.
+                 * Flushing will get done once the packet buffer has been
+                 * processed.
+                 */
+                if (OCSD_DATA_RESP_IS_WAIT(cur))
+                        break;
+
+                prev_return = cur;
+        }
+
+        decoder->prev_return = cur;
+        *consumed = processed;
+
+        return ret;
+}
+
+void cs_etm_decoder__free(struct cs_etm_decoder *decoder)
+{
+        if (!decoder)
+                return;
+
+        ocsd_destroy_dcd_tree(decoder->dcd_tree);
+        decoder->dcd_tree = NULL;
+        free(decoder);
+}
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
new file mode 100644
index 000000000000..3d2e6205d186
--- /dev/null
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -0,0 +1,105 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(C) 2015-2018 Linaro Limited.
+ *
+ * Author: Tor Jeremiassen <tor@ti.com>
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#ifndef INCLUDE__CS_ETM_DECODER_H__
+#define INCLUDE__CS_ETM_DECODER_H__
+
+#include <linux/types.h>
+#include <stdio.h>
+
+struct cs_etm_decoder;
+
+struct cs_etm_buffer {
+        const unsigned char *buf;
+        size_t len;
+        u64 offset;
+        u64 ref_timestamp;
+};
+
+enum cs_etm_sample_type {
+        CS_ETM_RANGE = 1 << 0,
+};
+
+struct cs_etm_packet {
+        enum cs_etm_sample_type sample_type;
+        u64 start_addr;
+        u64 end_addr;
+        u8 exc;
+        u8 exc_ret;
+        int cpu;
+};
+
+struct cs_etm_queue;
+
+typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u64,
+                                  size_t, u8 *);
+
+struct cs_etmv4_trace_params {
+        u32 reg_idr0;
+        u32 reg_idr1;
+        u32 reg_idr2;
+        u32 reg_idr8;
+        u32 reg_configr;
+        u32 reg_traceidr;
+};
+
+struct cs_etm_trace_params {
+        int protocol;
+        union {
+                struct cs_etmv4_trace_params etmv4;
+        };
+};
+
+struct cs_etm_decoder_params {
+        int operation;
+        void (*packet_printer)(const char *msg);
+        cs_etm_mem_cb_type mem_acc_cb;
+        u8 formatted;
+        u8 fsyncs;
+        u8 hsyncs;
+        u8 frame_aligned;
+        void *data;
+};
+
+/*
+ * The following enums are indexed starting with 1 to align with the
+ * open source coresight trace decoder library.
+ */
+enum {
+        CS_ETM_PROTO_ETMV3 = 1,
+        CS_ETM_PROTO_ETMV4i,
+        CS_ETM_PROTO_ETMV4d,
+};
+
+enum {
+        CS_ETM_OPERATION_PRINT = 1,
+        CS_ETM_OPERATION_DECODE,
+};
+
+int cs_etm_decoder__process_data_block(struct cs_etm_decoder *decoder,
+                                       u64 indx, const u8 *buf,
+                                       size_t len, size_t *consumed);
+
+struct cs_etm_decoder *
+cs_etm_decoder__new(int num_cpu,
+                    struct cs_etm_decoder_params *d_params,
+                    struct cs_etm_trace_params t_params[]);
+
+void cs_etm_decoder__free(struct cs_etm_decoder *decoder);
+
+int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
+                                      u64 start, u64 end,
+                                      cs_etm_mem_cb_type cb_func);
+
+int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+                               struct cs_etm_packet *packet);
+
+int cs_etm_decoder__reset(struct cs_etm_decoder *decoder);
+
+#endif /* INCLUDE__CS_ETM_DECODER_H__ */
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
new file mode 100644
index 000000000000..b9f0a53dfa65
--- /dev/null
+++ b/tools/perf/util/cs-etm.c
@@ -0,0 +1,1023 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(C) 2015-2018 Linaro Limited.
+ *
+ * Author: Tor Jeremiassen <tor@ti.com>
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/types.h>
+
+#include <stdlib.h>
+
+#include "auxtrace.h"
+#include "color.h"
+#include "cs-etm.h"
+#include "cs-etm-decoder/cs-etm-decoder.h"
+#include "debug.h"
+#include "evlist.h"
+#include "intlist.h"
+#include "machine.h"
+#include "map.h"
+#include "perf.h"
+#include "thread.h"
+#include "thread_map.h"
+#include "thread-stack.h"
+#include "util.h"
+
+#define MAX_TIMESTAMP (~0ULL)
+
+struct cs_etm_auxtrace {
+        struct auxtrace auxtrace;
+        struct auxtrace_queues queues;
+        struct auxtrace_heap heap;
+        struct itrace_synth_opts synth_opts;
+        struct perf_session *session;
+        struct machine *machine;
+        struct thread *unknown_thread;
+
+        u8 timeless_decoding;
+        u8 snapshot_mode;
+        u8 data_queued;
+        u8 sample_branches;
+
+        int num_cpu;
+        u32 auxtrace_type;
+        u64 branches_sample_type;
+        u64 branches_id;
+        u64 **metadata;
+        u64 kernel_start;
+        unsigned int pmu_type;
+};
+
+struct cs_etm_queue {
+        struct cs_etm_auxtrace *etm;
+        struct thread *thread;
+        struct cs_etm_decoder *decoder;
+        struct auxtrace_buffer *buffer;
+        const struct cs_etm_state *state;
+        union perf_event *event_buf;
+        unsigned int queue_nr;
+        pid_t pid, tid;
+        int cpu;
+        u64 time;
+        u64 timestamp;
+        u64 offset;
+};
+
+static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
+static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
+                                           pid_t tid, u64 time_);
+
+static void cs_etm__packet_dump(const char *pkt_string)
+{
+        const char *color = PERF_COLOR_BLUE;
+        int len = strlen(pkt_string);
+
+        if (len && (pkt_string[len-1] == '\n'))
+                color_fprintf(stdout, color, "  %s", pkt_string);
+        else
+                color_fprintf(stdout, color, "  %s\n", pkt_string);
+
+        fflush(stdout);
+}
+
+static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
+                               struct auxtrace_buffer *buffer)
+{
+        int i, ret;
+        const char *color = PERF_COLOR_BLUE;
+        struct cs_etm_decoder_params d_params;
+        struct cs_etm_trace_params *t_params;
+        struct cs_etm_decoder *decoder;
+        size_t buffer_used = 0;
+
+        fprintf(stdout, "\n");
+        color_fprintf(stdout, color,
+                     ". ... CoreSight ETM Trace data: size %zu bytes\n",
+                     buffer->size);
+
+        /* Use metadata to fill in trace parameters for trace decoder */
+        t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
+        for (i = 0; i < etm->num_cpu; i++) {
+                t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
+                t_params[i].etmv4.reg_idr0 = etm->metadata[i][CS_ETMV4_TRCIDR0];
+                t_params[i].etmv4.reg_idr1 = etm->metadata[i][CS_ETMV4_TRCIDR1];
+                t_params[i].etmv4.reg_idr2 = etm->metadata[i][CS_ETMV4_TRCIDR2];
+                t_params[i].etmv4.reg_idr8 = etm->metadata[i][CS_ETMV4_TRCIDR8];
+                t_params[i].etmv4.reg_configr =
+                                        etm->metadata[i][CS_ETMV4_TRCCONFIGR];
+                t_params[i].etmv4.reg_traceidr =
+                                        etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
+        }
+
+        /* Set decoder parameters to simply print the trace packets */
+        d_params.packet_printer = cs_etm__packet_dump;
+        d_params.operation = CS_ETM_OPERATION_PRINT;
+        d_params.formatted = true;
+        d_params.fsyncs = false;
+        d_params.hsyncs = false;
+        d_params.frame_aligned = true;
+
+        decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
+
+        zfree(&t_params);
+
+        if (!decoder)
+                return;
+        do {
+                size_t consumed;
+
+                ret = cs_etm_decoder__process_data_block(
+                                decoder, buffer->offset,
+                                &((u8 *)buffer->data)[buffer_used],
+                                buffer->size - buffer_used, &consumed);
+                if (ret)
+                        break;
+
+                buffer_used += consumed;
+        } while (buffer_used < buffer->size);
+
+        cs_etm_decoder__free(decoder);
+}
+
+static int cs_etm__flush_events(struct perf_session *session,
+                                struct perf_tool *tool)
+{
+        int ret;
+        struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+                                                   struct cs_etm_auxtrace,
+                                                   auxtrace);
+        if (dump_trace)
+                return 0;
+
+        if (!tool->ordered_events)
+                return -EINVAL;
+
+        if (!etm->timeless_decoding)
+                return -EINVAL;
+
+        ret = cs_etm__update_queues(etm);
+
+        if (ret < 0)
+                return ret;
+
+        return cs_etm__process_timeless_queues(etm, -1, MAX_TIMESTAMP - 1);
+}
+
+static void cs_etm__free_queue(void *priv)
+{
+        struct cs_etm_queue *etmq = priv;
+
+        free(etmq);
+}
+
+static void cs_etm__free_events(struct perf_session *session)
+{
+        unsigned int i;
+        struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
+                                                   struct cs_etm_auxtrace,
+                                                   auxtrace);
+        struct auxtrace_queues *queues = &aux->queues;
+
+        for (i = 0; i < queues->nr_queues; i++) {
+                cs_etm__free_queue(queues->queue_array[i].priv);
+                queues->queue_array[i].priv = NULL;
+        }
+
+        auxtrace_queues__free(queues);
+}
+
+static void cs_etm__free(struct perf_session *session)
+{
+        int i;
+        struct int_node *inode, *tmp;
+        struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
+                                                   struct cs_etm_auxtrace,
+                                                   auxtrace);
+        cs_etm__free_events(session);
+        session->auxtrace = NULL;
+
+        /* First remove all traceID/CPU# nodes for the RB tree */
+        intlist__for_each_entry_safe(inode, tmp, traceid_list)
+                intlist__remove(traceid_list, inode);
+        /* Then the RB tree itself */
+        intlist__delete(traceid_list);
+
+        for (i = 0; i < aux->num_cpu; i++)
+                zfree(&aux->metadata[i]);
+
+        zfree(&aux->metadata);
+        zfree(&aux);
+}
+
+static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
+                              size_t size, u8 *buffer)
+{
+        u8  cpumode;
+        u64 offset;
+        int len;
+        struct   thread *thread;
+        struct   machine *machine;
+        struct   addr_location al;
+
+        if (!etmq)
+                return -1;
+
+        machine = etmq->etm->machine;
+        if (address >= etmq->etm->kernel_start)
+                cpumode = PERF_RECORD_MISC_KERNEL;
+        else
+                cpumode = PERF_RECORD_MISC_USER;
+
+        thread = etmq->thread;
+        if (!thread) {
+                if (cpumode != PERF_RECORD_MISC_KERNEL)
+                        return -EINVAL;
+                thread = etmq->etm->unknown_thread;
+        }
+
+        thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al);
+
+        if (!al.map || !al.map->dso)
+                return 0;
+
+        if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
+            dso__data_status_seen(al.map->dso, DSO_DATA_STATUS_SEEN_ITRACE))
+                return 0;
+
+        offset = al.map->map_ip(al.map, address);
+
+        map__load(al.map);
+
+        len = dso__data_read_offset(al.map->dso, machine, offset, buffer, size);
+
+        if (len <= 0)
+                return 0;
+
+        return len;
+}
+
+static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
+                                                unsigned int queue_nr)
+{
+        int i;
+        struct cs_etm_decoder_params d_params;
+        struct cs_etm_trace_params  *t_params;
+        struct cs_etm_queue *etmq;
+
+        etmq = zalloc(sizeof(*etmq));
+        if (!etmq)
+                return NULL;
+
+        etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
+        if (!etmq->event_buf)
+                goto out_free;
+
+        etmq->etm = etm;
+        etmq->queue_nr = queue_nr;
+        etmq->pid = -1;
+        etmq->tid = -1;
+        etmq->cpu = -1;
+
+        /* Use metadata to fill in trace parameters for trace decoder */
+        t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
+
+        if (!t_params)
+                goto out_free;
+
+        for (i = 0; i < etm->num_cpu; i++) {
+                t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
+                t_params[i].etmv4.reg_idr0 = etm->metadata[i][CS_ETMV4_TRCIDR0];
+                t_params[i].etmv4.reg_idr1 = etm->metadata[i][CS_ETMV4_TRCIDR1];
+                t_params[i].etmv4.reg_idr2 = etm->metadata[i][CS_ETMV4_TRCIDR2];
+                t_params[i].etmv4.reg_idr8 = etm->metadata[i][CS_ETMV4_TRCIDR8];
+                t_params[i].etmv4.reg_configr =
+                                        etm->metadata[i][CS_ETMV4_TRCCONFIGR];
+                t_params[i].etmv4.reg_traceidr =
+                                        etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
+        }
+
+        /* Set decoder parameters to simply print the trace packets */
+        d_params.packet_printer = cs_etm__packet_dump;
+        d_params.operation = CS_ETM_OPERATION_DECODE;
+        d_params.formatted = true;
+        d_params.fsyncs = false;
+        d_params.hsyncs = false;
+        d_params.frame_aligned = true;
+        d_params.data = etmq;
+
+        etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
+
+        zfree(&t_params);
+
+        if (!etmq->decoder)
+                goto out_free;
+
+        /*
+         * Register a function to handle all memory accesses required by
+         * the trace decoder library.
+         */
+        if (cs_etm_decoder__add_mem_access_cb(etmq->decoder,
+                                              0x0L, ((u64) -1L),
+                                              cs_etm__mem_access))
+                goto out_free_decoder;
+
+        etmq->offset = 0;
+
+        return etmq;
+
+out_free_decoder:
+        cs_etm_decoder__free(etmq->decoder);
+out_free:
+        zfree(&etmq->event_buf);
+        free(etmq);
+
+        return NULL;
+}
+
+static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
+                               struct auxtrace_queue *queue,
+                               unsigned int queue_nr)
+{
+        struct cs_etm_queue *etmq = queue->priv;
+
+        if (list_empty(&queue->head) || etmq)
+                return 0;
+
+        etmq = cs_etm__alloc_queue(etm, queue_nr);
+
+        if (!etmq)
+                return -ENOMEM;
+
+        queue->priv = etmq;
+
+        if (queue->cpu != -1)
+                etmq->cpu = queue->cpu;
+
+        etmq->tid = queue->tid;
+
+        return 0;
+}
+
+static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
+{
+        unsigned int i;
+        int ret;
+
+        for (i = 0; i < etm->queues.nr_queues; i++) {
+                ret = cs_etm__setup_queue(etm, &etm->queues.queue_array[i], i);
+                if (ret)
+                        return ret;
+        }
+
+        return 0;
+}
+
+static int cs_etm__update_queues(struct cs_etm_auxtrace *etm)
+{
+        if (etm->queues.new_data) {
+                etm->queues.new_data = false;
+                return cs_etm__setup_queues(etm);
+        }
+
+        return 0;
+}
+
+static int
+cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
+{
+        struct auxtrace_buffer *aux_buffer = etmq->buffer;
+        struct auxtrace_buffer *old_buffer = aux_buffer;
+        struct auxtrace_queue *queue;
+
+        queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
+
+        aux_buffer = auxtrace_buffer__next(queue, aux_buffer);
+
+        /* If no more data, drop the previous auxtrace_buffer and return */
+        if (!aux_buffer) {
+                if (old_buffer)
+                        auxtrace_buffer__drop_data(old_buffer);
+                buff->len = 0;
+                return 0;
+        }
+
+        etmq->buffer = aux_buffer;
+
+        /* If the aux_buffer doesn't have data associated, try to load it */
+        if (!aux_buffer->data) {
+                /* get the file desc associated with the perf data file */
+                int fd = perf_data__fd(etmq->etm->session->data);
+
+                aux_buffer->data = auxtrace_buffer__get_data(aux_buffer, fd);
+                if (!aux_buffer->data)
+                        return -ENOMEM;
+        }
+
+        /* If valid, drop the previous buffer */
+        if (old_buffer)
+                auxtrace_buffer__drop_data(old_buffer);
+
+        buff->offset = aux_buffer->offset;
+        buff->len = aux_buffer->size;
+        buff->buf = aux_buffer->data;
+
+        buff->ref_timestamp = aux_buffer->reference;
+
+        return buff->len;
+}
+
+static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+                                     struct auxtrace_queue *queue)
+{
+        struct cs_etm_queue *etmq = queue->priv;
+
+        /* CPU-wide tracing isn't supported yet */
+        if (queue->tid == -1)
+                return;
+
+        if ((!etmq->thread) && (etmq->tid != -1))
+                etmq->thread = machine__find_thread(etm->machine, -1,
+                                                    etmq->tid);
+
+        if (etmq->thread) {
+                etmq->pid = etmq->thread->pid_;
+                if (queue->cpu == -1)
+                        etmq->cpu = etmq->thread->cpu;
+        }
+}
+
+/*
+ * The cs etm packet encodes an instruction range between a branch target
+ * and the next taken branch. Generate sample accordingly.
+ */
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
+                                       struct cs_etm_packet *packet)
+{
+        int ret = 0;
+        struct cs_etm_auxtrace *etm = etmq->etm;
+        struct perf_sample sample = {.ip = 0,};
+        union perf_event *event = etmq->event_buf;
+        u64 start_addr = packet->start_addr;
+        u64 end_addr = packet->end_addr;
+
+        event->sample.header.type = PERF_RECORD_SAMPLE;
+        event->sample.header.misc = PERF_RECORD_MISC_USER;
+        event->sample.header.size = sizeof(struct perf_event_header);
+
+        sample.ip = start_addr;
+        sample.pid = etmq->pid;
+        sample.tid = etmq->tid;
+        sample.addr = end_addr;
+        sample.id = etmq->etm->branches_id;
+        sample.stream_id = etmq->etm->branches_id;
+        sample.period = 1;
+        sample.cpu = packet->cpu;
+        sample.flags = 0;
+        sample.cpumode = PERF_RECORD_MISC_USER;
+
+        ret = perf_session__deliver_synth_event(etm->session, event, &sample);
+
+        if (ret)
+                pr_err(
+                "CS ETM Trace: failed to deliver instruction event, error %d\n",
+                ret);
+
+        return ret;
+}
+
+struct cs_etm_synth {
+        struct perf_tool dummy_tool;
+        struct perf_session *session;
+};
+
+static int cs_etm__event_synth(struct perf_tool *tool,
+                               union perf_event *event,
+                               struct perf_sample *sample __maybe_unused,
+                               struct machine *machine __maybe_unused)
+{
+        struct cs_etm_synth *cs_etm_synth =
+                      container_of(tool, struct cs_etm_synth, dummy_tool);
+
+        return perf_session__deliver_synth_event(cs_etm_synth->session,
+                                                 event, NULL);
+}
+
+static int cs_etm__synth_event(struct perf_session *session,
+                               struct perf_event_attr *attr, u64 id)
+{
+        struct cs_etm_synth cs_etm_synth;
+
+        memset(&cs_etm_synth, 0, sizeof(struct cs_etm_synth));
+        cs_etm_synth.session = session;
+
+        return perf_event__synthesize_attr(&cs_etm_synth.dummy_tool, attr, 1,
+                                           &id, cs_etm__event_synth);
+}
+
+static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
+                                struct perf_session *session)
+{
+        struct perf_evlist *evlist = session->evlist;
+        struct perf_evsel *evsel;
+        struct perf_event_attr attr;
+        bool found = false;
+        u64 id;
+        int err;
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (evsel->attr.type == etm->pmu_type) {
+                        found = true;
+                        break;
+                }
+        }
+
+        if (!found) {
+                pr_debug("No selected events with CoreSight Trace data\n");
+                return 0;
+        }
+
+        memset(&attr, 0, sizeof(struct perf_event_attr));
+        attr.size = sizeof(struct perf_event_attr);
+        attr.type = PERF_TYPE_HARDWARE;
+        attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+        attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
+                            PERF_SAMPLE_PERIOD;
+        if (etm->timeless_decoding)
+                attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
+        else
+                attr.sample_type |= PERF_SAMPLE_TIME;
+
+        attr.exclude_user = evsel->attr.exclude_user;
+        attr.exclude_kernel = evsel->attr.exclude_kernel;
+        attr.exclude_hv = evsel->attr.exclude_hv;
+        attr.exclude_host = evsel->attr.exclude_host;
+        attr.exclude_guest = evsel->attr.exclude_guest;
+        attr.sample_id_all = evsel->attr.sample_id_all;
+        attr.read_format = evsel->attr.read_format;
+
+        /* create new id val to be a fixed offset from evsel id */
+        id = evsel->id[0] + 1000000000;
+
+        if (!id)
+                id = 1;
+
+        if (etm->synth_opts.branches) {
+                attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
+                attr.sample_period = 1;
+                attr.sample_type |= PERF_SAMPLE_ADDR;
+                err = cs_etm__synth_event(session, &attr, id);
+                if (err)
+                        return err;
+                etm->sample_branches = true;
+                etm->branches_sample_type = attr.sample_type;
+                etm->branches_id = id;
+        }
+
+        return 0;
+}
+
+static int cs_etm__sample(struct cs_etm_queue *etmq)
+{
+        int ret;
+        struct cs_etm_packet packet;
+
+        while (1) {
+                ret = cs_etm_decoder__get_packet(etmq->decoder, &packet);
+                if (ret <= 0)
+                        return ret;
+
+                /*
+                 * If the packet contains an instruction range, generate an
+                 * instruction sequence event.
+                 */
+                if (packet.sample_type & CS_ETM_RANGE)
+                        cs_etm__synth_branch_sample(etmq, &packet);
+        }
+
+        return 0;
+}
+
+static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
+{
+        struct cs_etm_auxtrace *etm = etmq->etm;
+        struct cs_etm_buffer buffer;
+        size_t buffer_used, processed;
+        int err = 0;
+
+        if (!etm->kernel_start)
+                etm->kernel_start = machine__kernel_start(etm->machine);
+
+        /* Go through each buffer in the queue and decode them one by one */
+more:
+        buffer_used = 0;
+        memset(&buffer, 0, sizeof(buffer));
+        err = cs_etm__get_trace(&buffer, etmq);
+        if (err <= 0)
+                return err;
+        /*
+         * We cannot assume consecutive blocks in the data file are contiguous,
+         * reset the decoder to force re-sync.
+         */
+        err = cs_etm_decoder__reset(etmq->decoder);
+        if (err != 0)
+                return err;
+
+        /* Run trace decoder until buffer consumed or end of trace */
+        do {
+                processed = 0;
+
+                err = cs_etm_decoder__process_data_block(
+                                                etmq->decoder,
+                                                etmq->offset,
+                                                &buffer.buf[buffer_used],
+                                                buffer.len - buffer_used,
+                                                &processed);
+
+                if (err)
+                        return err;
+
+                etmq->offset += processed;
+                buffer_used += processed;
+
+                /*
+                 * Nothing to do with an error condition, let's hope the next
+                 * chunk will be better.
+                 */
+                err = cs_etm__sample(etmq);
+        } while (buffer.len > buffer_used);
+
+goto more;
+
+        return err;
+}
+
+static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
+                                           pid_t tid, u64 time_)
+{
+        unsigned int i;
+        struct auxtrace_queues *queues = &etm->queues;
+
+        for (i = 0; i < queues->nr_queues; i++) {
+                struct auxtrace_queue *queue = &etm->queues.queue_array[i];
+                struct cs_etm_queue *etmq = queue->priv;
+
+                if (etmq && ((tid == -1) || (etmq->tid == tid))) {
+                        etmq->time = time_;
+                        cs_etm__set_pid_tid_cpu(etm, queue);
+                        cs_etm__run_decoder(etmq);
+                }
+        }
+
+        return 0;
+}
+
+static int cs_etm__process_event(struct perf_session *session,
+                                 union perf_event *event,
+                                 struct perf_sample *sample,
+                                 struct perf_tool *tool)
+{
+        int err = 0;
+        u64 timestamp;
+        struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+                                                   struct cs_etm_auxtrace,
+                                                   auxtrace);
+
+        if (dump_trace)
+                return 0;
+
+        if (!tool->ordered_events) {
+                pr_err("CoreSight ETM Trace requires ordered events\n");
+                return -EINVAL;
+        }
+
+        if (!etm->timeless_decoding)
+                return -EINVAL;
+
+        if (sample->time && (sample->time != (u64) -1))
+                timestamp = sample->time;
+        else
+                timestamp = 0;
+
+        if (timestamp || etm->timeless_decoding) {
+                err = cs_etm__update_queues(etm);
+                if (err)
+                        return err;
+        }
+
+        if (event->header.type == PERF_RECORD_EXIT)
+                return cs_etm__process_timeless_queues(etm,
+                                                       event->fork.tid,
+                                                       sample->time);
+
+        return 0;
+}
+
+static int cs_etm__process_auxtrace_event(struct perf_session *session,
+                                          union perf_event *event,
+                                          struct perf_tool *tool __maybe_unused)
+{
+        struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+                                                   struct cs_etm_auxtrace,
+                                                   auxtrace);
+        if (!etm->data_queued) {
+                struct auxtrace_buffer *buffer;
+                off_t  data_offset;
+                int fd = perf_data__fd(session->data);
+                bool is_pipe = perf_data__is_pipe(session->data);
+                int err;
+
+                if (is_pipe)
+                        data_offset = 0;
+                else {
+                        data_offset = lseek(fd, 0, SEEK_CUR);
+                        if (data_offset == -1)
+                                return -errno;
+                }
+
+                err = auxtrace_queues__add_event(&etm->queues, session,
+                                                 event, data_offset, &buffer);
+                if (err)
+                        return err;
+
+                if (dump_trace)
+                        if (auxtrace_buffer__get_data(buffer, fd)) {
+                                cs_etm__dump_event(etm, buffer);
+                                auxtrace_buffer__put_data(buffer);
+                        }
+        }
+
+        return 0;
+}
+
+static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm)
+{
+        struct perf_evsel *evsel;
+        struct perf_evlist *evlist = etm->session->evlist;
+        bool timeless_decoding = true;
+
+        /*
+         * Circle through the list of event and complain if we find one
+         * with the time bit set.
+         */
+        evlist__for_each_entry(evlist, evsel) {
+                if ((evsel->attr.sample_type & PERF_SAMPLE_TIME))
+                        timeless_decoding = false;
+        }
+
+        return timeless_decoding;
+}
+
+static const char * const cs_etm_global_header_fmts[] = {
+        [CS_HEADER_VERSION_0]   = "     Header version                 %llx\n",
+        [CS_PMU_TYPE_CPUS]      = "     PMU type/num cpus              %llx\n",
+        [CS_ETM_SNAPSHOT]       = "     Snapshot                       %llx\n",
+};
+
+static const char * const cs_etm_priv_fmts[] = {
+        [CS_ETM_MAGIC]          = "     Magic number                   %llx\n",
+        [CS_ETM_CPU]            = "     CPU                            %lld\n",
+        [CS_ETM_ETMCR]          = "     ETMCR                          %llx\n",
+        [CS_ETM_ETMTRACEIDR]    = "     ETMTRACEIDR                    %llx\n",
+        [CS_ETM_ETMCCER]        = "     ETMCCER                        %llx\n",
+        [CS_ETM_ETMIDR]         = "     ETMIDR                         %llx\n",
+};
+
+static const char * const cs_etmv4_priv_fmts[] = {
+        [CS_ETM_MAGIC]          = "     Magic number                   %llx\n",
+        [CS_ETM_CPU]            = "     CPU                            %lld\n",
+        [CS_ETMV4_TRCCONFIGR]   = "     TRCCONFIGR                     %llx\n",
+        [CS_ETMV4_TRCTRACEIDR]  = "     TRCTRACEIDR                    %llx\n",
+        [CS_ETMV4_TRCIDR0]      = "     TRCIDR0                        %llx\n",
+        [CS_ETMV4_TRCIDR1]      = "     TRCIDR1                        %llx\n",
+        [CS_ETMV4_TRCIDR2]      = "     TRCIDR2                        %llx\n",
+        [CS_ETMV4_TRCIDR8]      = "     TRCIDR8                        %llx\n",
+        [CS_ETMV4_TRCAUTHSTATUS] = "    TRCAUTHSTATUS                  %llx\n",
+};
+
+static void cs_etm__print_auxtrace_info(u64 *val, int num)
+{
+        int i, j, cpu = 0;
+
+        for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
+                fprintf(stdout, cs_etm_global_header_fmts[i], val[i]);
+
+        for (i = CS_HEADER_VERSION_0_MAX; cpu < num; cpu++) {
+                if (val[i] == __perf_cs_etmv3_magic)
+                        for (j = 0; j < CS_ETM_PRIV_MAX; j++, i++)
+                                fprintf(stdout, cs_etm_priv_fmts[j], val[i]);
+                else if (val[i] == __perf_cs_etmv4_magic)
+                        for (j = 0; j < CS_ETMV4_PRIV_MAX; j++, i++)
+                                fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]);
+                else
+                        /* failure.. return */
+                        return;
+        }
+}
+
+int cs_etm__process_auxtrace_info(union perf_event *event,
+                                  struct perf_session *session)
+{
+        struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+        struct cs_etm_auxtrace *etm = NULL;
+        struct int_node *inode;
+        unsigned int pmu_type;
+        int event_header_size = sizeof(struct perf_event_header);
+        int info_header_size;
+        int total_size = auxtrace_info->header.size;
+        int priv_size = 0;
+        int num_cpu;
+        int err = 0, idx = -1;
+        int i, j, k;
+        u64 *ptr, *hdr = NULL;
+        u64 **metadata = NULL;
+
+        /*
+         * sizeof(auxtrace_info_event::type) +
+         * sizeof(auxtrace_info_event::reserved) == 8
+         */
+        info_header_size = 8;
+
+        if (total_size < (event_header_size + info_header_size))
+                return -EINVAL;
+
+        priv_size = total_size - event_header_size - info_header_size;
+
+        /* First the global part */
+        ptr = (u64 *) auxtrace_info->priv;
+
+        /* Look for version '0' of the header */
+        if (ptr[0] != 0)
+                return -EINVAL;
+
+        hdr = zalloc(sizeof(*hdr) * CS_HEADER_VERSION_0_MAX);
+        if (!hdr)
+                return -ENOMEM;
+
+        /* Extract header information - see cs-etm.h for format */
+        for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
+                hdr[i] = ptr[i];
+        num_cpu = hdr[CS_PMU_TYPE_CPUS] & 0xffffffff;
+        pmu_type = (unsigned int) ((hdr[CS_PMU_TYPE_CPUS] >> 32) &
+                                    0xffffffff);
+
+        /*
+         * Create an RB tree for traceID-CPU# tuple. Since the conversion has
+         * to be made for each packet that gets decoded, optimizing access in
+         * anything other than a sequential array is worth doing.
+         */
+        traceid_list = intlist__new(NULL);
+        if (!traceid_list) {
+                err = -ENOMEM;
+                goto err_free_hdr;
+        }
+
+        metadata = zalloc(sizeof(*metadata) * num_cpu);
+        if (!metadata) {
+                err = -ENOMEM;
+                goto err_free_traceid_list;
+        }
+
+        /*
+         * The metadata is stored in the auxtrace_info section and encodes
+         * the configuration of the ARM embedded trace macrocell which is
+         * required by the trace decoder to properly decode the trace due
+         * to its highly compressed nature.
+         */
+        for (j = 0; j < num_cpu; j++) {
+                if (ptr[i] == __perf_cs_etmv3_magic) {
+                        metadata[j] = zalloc(sizeof(*metadata[j]) *
+                                             CS_ETM_PRIV_MAX);
+                        if (!metadata[j]) {
+                                err = -ENOMEM;
+                                goto err_free_metadata;
+                        }
+                        for (k = 0; k < CS_ETM_PRIV_MAX; k++)
+                                metadata[j][k] = ptr[i + k];
+
+                        /* The traceID is our handle */
+                        idx = metadata[j][CS_ETM_ETMTRACEIDR];
+                        i += CS_ETM_PRIV_MAX;
+                } else if (ptr[i] == __perf_cs_etmv4_magic) {
+                        metadata[j] = zalloc(sizeof(*metadata[j]) *
+                                             CS_ETMV4_PRIV_MAX);
+                        if (!metadata[j]) {
+                                err = -ENOMEM;
+                                goto err_free_metadata;
+                        }
+                        for (k = 0; k < CS_ETMV4_PRIV_MAX; k++)
+                                metadata[j][k] = ptr[i + k];
+
+                        /* The traceID is our handle */
+                        idx = metadata[j][CS_ETMV4_TRCTRACEIDR];
+                        i += CS_ETMV4_PRIV_MAX;
+                }
+
+                /* Get an RB node for this CPU */
+                inode = intlist__findnew(traceid_list, idx);
+
+                /* Something went wrong, no need to continue */
+                if (!inode) {
+                        err = PTR_ERR(inode);
+                        goto err_free_metadata;
+                }
+
+                /*
+                 * The node for that CPU should not be taken.
+                 * Back out if that's the case.
+                 */
+                if (inode->priv) {
+                        err = -EINVAL;
+                        goto err_free_metadata;
+                }
+                /* All good, associate the traceID with the CPU# */
+                inode->priv = &metadata[j][CS_ETM_CPU];
+        }
+
+        /*
+         * Each of CS_HEADER_VERSION_0_MAX, CS_ETM_PRIV_MAX and
+         * CS_ETMV4_PRIV_MAX mark how many double words are in the
+         * global metadata, and each cpu's metadata respectively.
+         * The following tests if the correct number of double words was
+         * present in the auxtrace info section.
+         */
+        if (i * 8 != priv_size) {
+                err = -EINVAL;
+                goto err_free_metadata;
+        }
+
+        etm = zalloc(sizeof(*etm));
+
+        if (!etm) {
+                err = -ENOMEM;
+                goto err_free_metadata;
+        }
+
+        err = auxtrace_queues__init(&etm->queues);
+        if (err)
+                goto err_free_etm;
+
+        etm->session = session;
+        etm->machine = &session->machines.host;
+
+        etm->num_cpu = num_cpu;
+        etm->pmu_type = pmu_type;
+        etm->snapshot_mode = (hdr[CS_ETM_SNAPSHOT] != 0);
+        etm->metadata = metadata;
+        etm->auxtrace_type = auxtrace_info->type;
+        etm->timeless_decoding = cs_etm__is_timeless_decoding(etm);
+
+        etm->auxtrace.process_event = cs_etm__process_event;
+        etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
+        etm->auxtrace.flush_events = cs_etm__flush_events;
+        etm->auxtrace.free_events = cs_etm__free_events;
+        etm->auxtrace.free = cs_etm__free;
+        session->auxtrace = &etm->auxtrace;
+
+        if (dump_trace) {
+                cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
+                return 0;
+        }
+
+        if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+                etm->synth_opts = *session->itrace_synth_opts;
+        } else {
+                itrace_synth_opts__set_default(&etm->synth_opts);
+                etm->synth_opts.callchain = false;
+        }
+
+        err = cs_etm__synth_events(etm, session);
+        if (err)
+                goto err_free_queues;
+
+        err = auxtrace_queues__process_index(&etm->queues, session);
+        if (err)
+                goto err_free_queues;
+
+        etm->data_queued = etm->queues.populated;
+
+        return 0;
+
+err_free_queues:
+        auxtrace_queues__free(&etm->queues);
+        session->auxtrace = NULL;
+err_free_etm:
+        zfree(&etm);
+err_free_metadata:
+        /* No need to check @metadata[j], free(NULL) is supported */
+        for (j = 0; j < num_cpu; j++)
+                free(metadata[j]);
+        zfree(&metadata);
+err_free_traceid_list:
+        intlist__delete(traceid_list);
+err_free_hdr:
+        zfree(&hdr);
+
+        return -EINVAL;
+}
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 3cc6bc3263fe..5864d5dca616 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -18,6 +18,9 @@
 #ifndef INCLUDE__UTIL_PERF_CS_ETM_H__
 #define INCLUDE__UTIL_PERF_CS_ETM_H__
 
+#include "util/event.h"
+#include "util/session.h"
+
 /* Versionning header in case things need tro change in the future.  That way
  * decoding of old snapshot is still possible.
  */
@@ -61,6 +64,9 @@ enum {
         CS_ETMV4_PRIV_MAX,
 };
 
+/* RB tree for quick conversion between traceID and CPUs */
+struct intlist *traceid_list;
+
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
 
@@ -71,4 +77,16 @@ static const u64 __perf_cs_etmv4_magic   = 0x4040404040404040ULL;
 #define CS_ETMV3_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64))
 #define CS_ETMV4_PRIV_SIZE (CS_ETMV4_PRIV_MAX * sizeof(u64))
 
+#ifdef HAVE_CSTRACE_SUPPORT
+int cs_etm__process_auxtrace_info(union perf_event *event,
+                                  struct perf_session *session);
+#else
+static inline int
+cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
+                              struct perf_session *session __maybe_unused)
+{
+        return -1;
+}
+#endif
+
 #endif
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2346cecb8ea2..5744c12641a5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1577,10 +1577,10 @@ int bt_convert__perf2ctf(const char *input, const char *path,
                          struct perf_data_convert_opts *opts)
 {
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = input,
-                .mode = PERF_DATA_MODE_READ,
-                .force = opts->force,
+        struct perf_data data = {
+                .file.path = input,
+                .mode      = PERF_DATA_MODE_READ,
+                .force     = opts->force,
         };
         struct convert c = {
                 .tool = {
@@ -1619,7 +1619,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
         err = -1;
         /* perf.data session */
-        session = perf_session__new(&file, 0, &c.tool);
+        session = perf_session__new(&data, 0, &c.tool);
         if (!session)
                 goto free_writer;
 
@@ -1650,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
         fprintf(stderr,
                 "[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
-                file.path, path);
+                data.file.path, path);
 
         fprintf(stderr,
                 "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 79192758bdb3..d8cfc19ddb10 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -4,6 +4,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
 
@@ -11,66 +12,56 @@
 #include "util.h"
 #include "debug.h"
 
-#ifndef O_CLOEXEC
-#ifdef __sparc__
-#define O_CLOEXEC       0x400000
-#elif defined(__alpha__) || defined(__hppa__)
-#define O_CLOEXEC       010000000
-#else
-#define O_CLOEXEC       02000000
-#endif
-#endif
-
-static bool check_pipe(struct perf_data_file *file)
+static bool check_pipe(struct perf_data *data)
 {
         struct stat st;
         bool is_pipe = false;
-        int fd = perf_data_file__is_read(file) ?
+        int fd = perf_data__is_read(data) ?
                  STDIN_FILENO : STDOUT_FILENO;
 
-        if (!file->path) {
+        if (!data->file.path) {
                 if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
                         is_pipe = true;
         } else {
-                if (!strcmp(file->path, "-"))
+                if (!strcmp(data->file.path, "-"))
                         is_pipe = true;
         }
 
         if (is_pipe)
-                file->fd = fd;
+                data->file.fd = fd;
 
-        return file->is_pipe = is_pipe;
+        return data->is_pipe = is_pipe;
 }
 
-static int check_backup(struct perf_data_file *file)
+static int check_backup(struct perf_data *data)
 {
         struct stat st;
 
-        if (!stat(file->path, &st) && st.st_size) {
+        if (!stat(data->file.path, &st) && st.st_size) {
                 /* TODO check errors properly */
                 char oldname[PATH_MAX];
                 snprintf(oldname, sizeof(oldname), "%s.old",
-                         file->path);
+                         data->file.path);
                 unlink(oldname);
-                rename(file->path, oldname);
+                rename(data->file.path, oldname);
         }
 
         return 0;
 }
 
-static int open_file_read(struct perf_data_file *file)
+static int open_file_read(struct perf_data *data)
 {
         struct stat st;
         int fd;
         char sbuf[STRERR_BUFSIZE];
 
-        fd = open(file->path, O_RDONLY);
+        fd = open(data->file.path, O_RDONLY);
         if (fd < 0) {
                 int err = errno;
 
-                pr_err("failed to open %s: %s", file->path,
+                pr_err("failed to open %s: %s", data->file.path,
                         str_error_r(err, sbuf, sizeof(sbuf)));
-                if (err == ENOENT && !strcmp(file->path, "perf.data"))
+                if (err == ENOENT && !strcmp(data->file.path, "perf.data"))
                         pr_err("  (try 'perf record' first)");
                 pr_err("\n");
                 return -err;
@@ -79,19 +70,19 @@ static int open_file_read(struct perf_data_file *file)
         if (fstat(fd, &st) < 0)
                 goto out_close;
 
-        if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
+        if (!data->force && st.st_uid && (st.st_uid != geteuid())) {
                 pr_err("File %s not owned by current user or root (use -f to override)\n",
-                       file->path);
+                       data->file.path);
                 goto out_close;
         }
 
         if (!st.st_size) {
-                pr_info("zero-sized file (%s), nothing to do!\n",
-                        file->path);
+                pr_info("zero-sized data (%s), nothing to do!\n",
+                        data->file.path);
                 goto out_close;
         }
 
-        file->size = st.st_size;
+        data->size = st.st_size;
         return fd;
 
  out_close:
@@ -99,49 +90,49 @@ static int open_file_read(struct perf_data_file *file)
         return -1;
 }
 
-static int open_file_write(struct perf_data_file *file)
+static int open_file_write(struct perf_data *data)
 {
         int fd;
         char sbuf[STRERR_BUFSIZE];
 
-        if (check_backup(file))
+        if (check_backup(data))
                 return -1;
 
-        fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+        fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
                   S_IRUSR|S_IWUSR);
 
         if (fd < 0)
-                pr_err("failed to open %s : %s\n", file->path,
+                pr_err("failed to open %s : %s\n", data->file.path,
                         str_error_r(errno, sbuf, sizeof(sbuf)));
 
         return fd;
 }
 
-static int open_file(struct perf_data_file *file)
+static int open_file(struct perf_data *data)
 {
         int fd;
 
-        fd = perf_data_file__is_read(file) ?
-             open_file_read(file) : open_file_write(file);
+        fd = perf_data__is_read(data) ?
+             open_file_read(data) : open_file_write(data);
 
-        file->fd = fd;
+        data->file.fd = fd;
         return fd < 0 ? -1 : 0;
 }
 
-int perf_data_file__open(struct perf_data_file *file)
+int perf_data__open(struct perf_data *data)
 {
-        if (check_pipe(file))
+        if (check_pipe(data))
                 return 0;
 
-        if (!file->path)
-                file->path = "perf.data";
+        if (!data->file.path)
+                data->file.path = "perf.data";
 
-        return open_file(file);
+        return open_file(data);
 }
 
-void perf_data_file__close(struct perf_data_file *file)
+void perf_data__close(struct perf_data *data)
 {
-        close(file->fd);
+        close(data->file.fd);
 }
 
 ssize_t perf_data_file__write(struct perf_data_file *file,
@@ -150,42 +141,48 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
         return writen(file->fd, buf, size);
 }
 
-int perf_data_file__switch(struct perf_data_file *file,
+ssize_t perf_data__write(struct perf_data *data,
+                              void *buf, size_t size)
+{
+        return perf_data_file__write(&data->file, buf, size);
+}
+
+int perf_data__switch(struct perf_data *data,
                            const char *postfix,
                            size_t pos, bool at_exit)
 {
         char *new_filepath;
         int ret;
 
-        if (check_pipe(file))
+        if (check_pipe(data))
                 return -EINVAL;
-        if (perf_data_file__is_read(file))
+        if (perf_data__is_read(data))
                 return -EINVAL;
 
-        if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0)
+        if (asprintf(&new_filepath, "%s.%s", data->file.path, postfix) < 0)
                 return -ENOMEM;
 
         /*
          * Only fire a warning, don't return error, continue fill
          * original file.
          */
-        if (rename(file->path, new_filepath))
-                pr_warning("Failed to rename %s to %s\n", file->path, new_filepath);
+        if (rename(data->file.path, new_filepath))
+                pr_warning("Failed to rename %s to %s\n", data->file.path, new_filepath);
 
         if (!at_exit) {
-                close(file->fd);
-                ret = perf_data_file__open(file);
+                close(data->file.fd);
+                ret = perf_data__open(data);
                 if (ret < 0)
                         goto out;
 
-                if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) {
+                if (lseek(data->file.fd, pos, SEEK_SET) == (off_t)-1) {
                         ret = -errno;
                         pr_debug("Failed to lseek to %zu: %s",
                                  pos, strerror(errno));
                         goto out;
                 }
         }
-        ret = file->fd;
+        ret = data->file.fd;
 out:
         free(new_filepath);
         return ret;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 80241ba78101..4828f7feea89 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -10,51 +10,57 @@ enum perf_data_mode {
 };
 
 struct perf_data_file {
-        const char              *path;
-        int                      fd;
+        const char      *path;
+        int              fd;
+};
+
+struct perf_data {
+        struct perf_data_file    file;
         bool                     is_pipe;
         bool                     force;
         unsigned long            size;
         enum perf_data_mode      mode;
 };
 
-static inline bool perf_data_file__is_read(struct perf_data_file *file)
+static inline bool perf_data__is_read(struct perf_data *data)
 {
-        return file->mode == PERF_DATA_MODE_READ;
+        return data->mode == PERF_DATA_MODE_READ;
 }
 
-static inline bool perf_data_file__is_write(struct perf_data_file *file)
+static inline bool perf_data__is_write(struct perf_data *data)
 {
-        return file->mode == PERF_DATA_MODE_WRITE;
+        return data->mode == PERF_DATA_MODE_WRITE;
 }
 
-static inline int perf_data_file__is_pipe(struct perf_data_file *file)
+static inline int perf_data__is_pipe(struct perf_data *data)
 {
-        return file->is_pipe;
+        return data->is_pipe;
 }
 
-static inline int perf_data_file__fd(struct perf_data_file *file)
+static inline int perf_data__fd(struct perf_data *data)
 {
-        return file->fd;
+        return data->file.fd;
 }
 
-static inline unsigned long perf_data_file__size(struct perf_data_file *file)
+static inline unsigned long perf_data__size(struct perf_data *data)
 {
-        return file->size;
+        return data->size;
 }
 
-int perf_data_file__open(struct perf_data_file *file);
-void perf_data_file__close(struct perf_data_file *file);
+int perf_data__open(struct perf_data *data);
+void perf_data__close(struct perf_data *data);
+ssize_t perf_data__write(struct perf_data *data,
+                              void *buf, size_t size);
 ssize_t perf_data_file__write(struct perf_data_file *file,
                               void *buf, size_t size);
 /*
  * If at_exit is set, only rename current perf.data to
- * perf.data.<postfix>, continue write on original file.
+ * perf.data.<postfix>, continue write on original data.
  * Set at_exit when flushing the last output.
  *
  * Return value is fd of new output.
  */
-int perf_data_file__switch(struct perf_data_file *file,
+int perf_data__switch(struct perf_data *data,
                            const char *postfix,
                            size_t pos, bool at_exit);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index dc8b53b6950e..f3a71db83947 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -112,50 +112,53 @@ int dump_printf(const char *fmt, ...)
         return ret;
 }
 
-static void trace_event_printer(enum binary_printer_ops op,
-                                unsigned int val, void *extra)
+static int trace_event_printer(enum binary_printer_ops op,
+                               unsigned int val, void *extra, FILE *fp)
 {
         const char *color = PERF_COLOR_BLUE;
         union perf_event *event = (union perf_event *)extra;
         unsigned char ch = (unsigned char)val;
+        int printed = 0;
 
         switch (op) {
         case BINARY_PRINT_DATA_BEGIN:
-                printf(".");
-                color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-                                event->header.size);
+                printed += fprintf(fp, ".");
+                printed += color_fprintf(fp, color, "\n. ... raw event: size %d bytes\n",
+                                         event->header.size);
                 break;
         case BINARY_PRINT_LINE_BEGIN:
-                printf(".");
+                printed += fprintf(fp, ".");
                 break;
         case BINARY_PRINT_ADDR:
-                color_fprintf(stdout, color, "  %04x: ", val);
+                printed += color_fprintf(fp, color, "  %04x: ", val);
                 break;
         case BINARY_PRINT_NUM_DATA:
-                color_fprintf(stdout, color, " %02x", val);
+                printed += color_fprintf(fp, color, " %02x", val);
                 break;
         case BINARY_PRINT_NUM_PAD:
-                color_fprintf(stdout, color, "   ");
+                printed += color_fprintf(fp, color, "   ");
                 break;
         case BINARY_PRINT_SEP:
-                color_fprintf(stdout, color, "  ");
+                printed += color_fprintf(fp, color, "  ");
                 break;
         case BINARY_PRINT_CHAR_DATA:
-                color_fprintf(stdout, color, "%c",
+                printed += color_fprintf(fp, color, "%c",
                               isprint(ch) ? ch : '.');
                 break;
         case BINARY_PRINT_CHAR_PAD:
-                color_fprintf(stdout, color, " ");
+                printed += color_fprintf(fp, color, " ");
                 break;
         case BINARY_PRINT_LINE_END:
-                color_fprintf(stdout, color, "\n");
+                printed += color_fprintf(fp, color, "\n");
                 break;
         case BINARY_PRINT_DATA_END:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 break;
         default:
                 break;
         }
+
+        return printed;
 }
 
 void trace_event(union perf_event *event)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 00c98c968cb1..36ef45b2e89d 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,9 +7,11 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <errno.h>
+#include <fcntl.h>
 #include "compress.h"
 #include "path.h"
 #include "symbol.h"
+#include "srcline.h"
 #include "dso.h"
 #include "machine.h"
 #include "auxtrace.h"
@@ -444,7 +446,7 @@ static int do_open(char *name)
         char sbuf[STRERR_BUFSIZE];
 
         do {
-                fd = open(name, O_RDONLY);
+                fd = open(name, O_RDONLY|O_CLOEXEC);
                 if (fd >= 0)
                         return fd;
 
@@ -1201,6 +1203,8 @@ struct dso *dso__new(const char *name)
                 for (i = 0; i < MAP__NR_TYPES; ++i)
                         dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
                 dso->data.cache = RB_ROOT;
+                dso->inlined_nodes = RB_ROOT;
+                dso->srclines = RB_ROOT;
                 dso->data.fd = -1;
                 dso->data.status = DSO_DATA_STATUS_UNKNOWN;
                 dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1232,6 +1236,10 @@ void dso__delete(struct dso *dso)
         if (!RB_EMPTY_NODE(&dso->rb_node))
                 pr_err("DSO %s is still in rbtree when being deleted!\n",
                        dso->long_name);
+
+        /* free inlines first, as they reference symbols */
+        inlines__tree_delete(&dso->inlined_nodes);
+        srcline__tree_delete(&dso->srclines);
         for (i = 0; i < MAP__NR_TYPES; ++i)
                 symbols__delete(&dso->symbols[i]);
 
@@ -1366,9 +1374,9 @@ void __dsos__add(struct dsos *dsos, struct dso *dso)
 
 void dsos__add(struct dsos *dsos, struct dso *dso)
 {
-        pthread_rwlock_wrlock(&dsos->lock);
+        down_write(&dsos->lock);
         __dsos__add(dsos, dso);
-        pthread_rwlock_unlock(&dsos->lock);
+        up_write(&dsos->lock);
 }
 
 struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
@@ -1387,9 +1395,9 @@ struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
         struct dso *dso;
-        pthread_rwlock_rdlock(&dsos->lock);
+        down_read(&dsos->lock);
         dso = __dsos__find(dsos, name, cmp_short);
-        pthread_rwlock_unlock(&dsos->lock);
+        up_read(&dsos->lock);
         return dso;
 }
 
@@ -1416,9 +1424,9 @@ struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 struct dso *dsos__findnew(struct dsos *dsos, const char *name)
 {
         struct dso *dso;
-        pthread_rwlock_wrlock(&dsos->lock);
+        down_write(&dsos->lock);
         dso = dso__get(__dsos__findnew(dsos, name));
-        pthread_rwlock_unlock(&dsos->lock);
+        up_write(&dsos->lock);
         return dso;
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 926ff2e7f668..c229dbe0277a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -7,7 +7,7 @@
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
-#include <pthread.h>
+#include "rwsem.h"
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
@@ -130,7 +130,7 @@ struct dso_cache {
 struct dsos {
         struct list_head head;
         struct rb_root   root;  /* rbtree root sorted by long name */
-        pthread_rwlock_t lock;
+        struct rw_semaphore lock;
 };
 
 struct auxtrace_cache;
@@ -142,6 +142,8 @@ struct dso {
         struct rb_root   *root;         /* root of rbtree that rb_node is in */
         struct rb_root   symbols[MAP__NR_TYPES];
         struct rb_root   symbol_names[MAP__NR_TYPES];
+        struct rb_root   inlined_nodes;
+        struct rb_root   srclines;
         struct {
                 u64             addr;
                 struct symbol   *symbol;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6276b340f893..6d311868d850 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "cpumap.h"
 #include "env.h"
+#include "sane_ctype.h"
 #include "util.h"
 #include <errno.h>
+#include <sys/utsname.h>
 
 struct perf_env perf_env;
 
@@ -93,3 +95,48 @@ void cpu_cache_level__free(struct cpu_cache_level *cache)
         free(cache->map);
         free(cache->size);
 }
+
+/*
+ * Return architecture name in a normalized form.
+ * The conversion logic comes from the Makefile.
+ */
+static const char *normalize_arch(char *arch)
+{
+        if (!strcmp(arch, "x86_64"))
+                return "x86";
+        if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
+                return "x86";
+        if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
+                return "sparc";
+        if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
+                return "arm64";
+        if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
+                return "arm";
+        if (!strncmp(arch, "s390", 4))
+                return "s390";
+        if (!strncmp(arch, "parisc", 6))
+                return "parisc";
+        if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
+                return "powerpc";
+        if (!strncmp(arch, "mips", 4))
+                return "mips";
+        if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
+                return "sh";
+
+        return arch;
+}
+
+const char *perf_env__arch(struct perf_env *env)
+{
+        struct utsname uts;
+        char *arch_name;
+
+        if (!env) { /* Assume local operation */
+                if (uname(&uts) < 0)
+                        return NULL;
+                arch_name = uts.machine;
+        } else
+                arch_name = env->arch;
+
+        return normalize_arch(arch_name);
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1eb35b190b34..bf970f57dce0 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -65,4 +65,6 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
 void cpu_cache_level__free(struct cpu_cache_level *cache);
+
+const char *perf_env__arch(struct perf_env *env);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index fc690fecbfd6..44e603c27944 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dirent.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -678,21 +679,21 @@ out:
         return err;
 }
 
-int perf_event__synthesize_threads(struct perf_tool *tool,
-                                   perf_event__handler_t process,
-                                   struct machine *machine,
-                                   bool mmap_data,
-                                   unsigned int proc_map_timeout)
+static int __perf_event__synthesize_threads(struct perf_tool *tool,
+                                            perf_event__handler_t process,
+                                            struct machine *machine,
+                                            bool mmap_data,
+                                            unsigned int proc_map_timeout,
+                                            struct dirent **dirent,
+                                            int start,
+                                            int num)
 {
-        DIR *proc;
-        char proc_path[PATH_MAX];
-        struct dirent *dirent;
         union perf_event *comm_event, *mmap_event, *fork_event;
         union perf_event *namespaces_event;
         int err = -1;
-
-        if (machine__is_default_guest(machine))
-                return 0;
+        char *end;
+        pid_t pid;
+        int i;
 
         comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
         if (comm_event == NULL)
@@ -712,31 +713,25 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
         if (namespaces_event == NULL)
                 goto out_free_fork;
 
-        snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-        proc = opendir(proc_path);
-
-        if (proc == NULL)
-                goto out_free_namespaces;
-
-        while ((dirent = readdir(proc)) != NULL) {
-                char *end;
-                pid_t pid = strtol(dirent->d_name, &end, 10);
+        for (i = start; i < start + num; i++) {
+                if (!isdigit(dirent[i]->d_name[0]))
+                        continue;
 
-                if (*end) /* only interested in proper numerical dirents */
+                pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
+                /* only interested in proper numerical dirents */
+                if (*end)
                         continue;
                 /*
-                 * We may race with exiting thread, so don't stop just because
-                 * one thread couldn't be synthesized.
-                 */
+                 * We may race with exiting thread, so don't stop just because
+                 * one thread couldn't be synthesized.
+                 */
                 __event__synthesize_thread(comm_event, mmap_event, fork_event,
                                            namespaces_event, pid, 1, process,
                                            tool, machine, mmap_data,
                                            proc_map_timeout);
         }
-
         err = 0;
-        closedir(proc);
-out_free_namespaces:
+
         free(namespaces_event);
 out_free_fork:
         free(fork_event);
@@ -748,6 +743,118 @@ out:
         return err;
 }
 
+struct synthesize_threads_arg {
+        struct perf_tool *tool;
+        perf_event__handler_t process;
+        struct machine *machine;
+        bool mmap_data;
+        unsigned int proc_map_timeout;
+        struct dirent **dirent;
+        int num;
+        int start;
+};
+
+static void *synthesize_threads_worker(void *arg)
+{
+        struct synthesize_threads_arg *args = arg;
+
+        __perf_event__synthesize_threads(args->tool, args->process,
+                                         args->machine, args->mmap_data,
+                                         args->proc_map_timeout, args->dirent,
+                                         args->start, args->num);
+        return NULL;
+}
+
+int perf_event__synthesize_threads(struct perf_tool *tool,
+                                   perf_event__handler_t process,
+                                   struct machine *machine,
+                                   bool mmap_data,
+                                   unsigned int proc_map_timeout,
+                                   unsigned int nr_threads_synthesize)
+{
+        struct synthesize_threads_arg *args = NULL;
+        pthread_t *synthesize_threads = NULL;
+        char proc_path[PATH_MAX];
+        struct dirent **dirent;
+        int num_per_thread;
+        int m, n, i, j;
+        int thread_nr;
+        int base = 0;
+        int err = -1;
+
+
+        if (machine__is_default_guest(machine))
+                return 0;
+
+        snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+        n = scandir(proc_path, &dirent, 0, alphasort);
+        if (n < 0)
+                return err;
+
+        if (nr_threads_synthesize == UINT_MAX)
+                thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
+        else
+                thread_nr = nr_threads_synthesize;
+
+        if (thread_nr <= 1) {
+                err = __perf_event__synthesize_threads(tool, process,
+                                                       machine, mmap_data,
+                                                       proc_map_timeout,
+                                                       dirent, base, n);
+                goto free_dirent;
+        }
+        if (thread_nr > n)
+                thread_nr = n;
+
+        synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+        if (synthesize_threads == NULL)
+                goto free_dirent;
+
+        args = calloc(sizeof(*args), thread_nr);
+        if (args == NULL)
+                goto free_threads;
+
+        num_per_thread = n / thread_nr;
+        m = n % thread_nr;
+        for (i = 0; i < thread_nr; i++) {
+                args[i].tool = tool;
+                args[i].process = process;
+                args[i].machine = machine;
+                args[i].mmap_data = mmap_data;
+                args[i].proc_map_timeout = proc_map_timeout;
+                args[i].dirent = dirent;
+        }
+        for (i = 0; i < m; i++) {
+                args[i].num = num_per_thread + 1;
+                args[i].start = i * args[i].num;
+        }
+        if (i != 0)
+                base = args[i-1].start + args[i-1].num;
+        for (j = i; j < thread_nr; j++) {
+                args[j].num = num_per_thread;
+                args[j].start = base + (j - i) * args[i].num;
+        }
+
+        for (i = 0; i < thread_nr; i++) {
+                if (pthread_create(&synthesize_threads[i], NULL,
+                                   synthesize_threads_worker, &args[i]))
+                        goto out_join;
+        }
+        err = 0;
+out_join:
+        for (i = 0; i < thread_nr; i++)
+                pthread_join(synthesize_threads[i], NULL);
+        free(args);
+free_threads:
+        free(synthesize_threads);
+free_dirent:
+        for (i = 0; i < n; i++)
+                free(dirent[i]);
+        free(dirent);
+
+        return err;
+}
+
 struct process_symbol_args {
         const char *name;
         u64        start;
@@ -1328,6 +1435,11 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
                        event->context_switch.next_prev_tid);
 }
 
+static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)
+{
+        return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
         size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -1360,6 +1472,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
         case PERF_RECORD_SWITCH_CPU_WIDE:
                 ret += perf_event__fprintf_switch(event, fp);
                 break;
+        case PERF_RECORD_LOST:
+                ret += perf_event__fprintf_lost(event, fp);
+                break;
         default:
                 ret += fprintf(fp, "\n");
         }
@@ -1498,6 +1613,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
         al->sym = NULL;
         al->cpu = sample->cpu;
         al->socket = -1;
+        al->srcline = NULL;
 
         if (al->cpu >= 0) {
                 struct perf_env *env = machine->env;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5524ee69279c..0f794744919c 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -205,6 +205,7 @@ struct perf_sample {
         u32 flags;
         u16 insn_len;
         u8  cpumode;
+        u16 misc;
         char insn[MAX_INSN];
         void *raw_data;
         struct ip_callchain *callchain;
@@ -681,7 +682,8 @@ int perf_event__synthesize_cpu_map(struct perf_tool *tool,
 int perf_event__synthesize_threads(struct perf_tool *tool,
                                    perf_event__handler_t process,
                                    struct machine *machine, bool mmap_data,
-                                   unsigned int proc_map_timeout);
+                                   unsigned int proc_map_timeout,
+                                   unsigned int nr_threads_synthesize);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
                                        perf_event__handler_t process,
                                        struct machine *machine);
@@ -773,8 +775,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
                                      u64 read_format);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
                                   u64 read_format,
-                                  const struct perf_sample *sample,
-                                  bool swapped);
+                                  const struct perf_sample *sample);
 
 pid_t perf_event__synthesize_comm(struct perf_tool *tool,
                                   union perf_event *event, pid_t pid,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 6a0d7ffbeba0..e5fc14e53c05 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,7 @@
 #include "parse-events.h"
 #include <subcmd/parse-options.h>
 
+#include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
 
@@ -33,9 +34,6 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 
-static void perf_mmap__munmap(struct perf_mmap *map);
-static void perf_mmap__put(struct perf_mmap *map);
-
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
@@ -128,7 +126,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
         zfree(&evlist->mmap);
-        zfree(&evlist->backward_mmap);
+        zfree(&evlist->overwrite_mmap);
         fdarray__exit(&evlist->pollfd);
 }
 
@@ -260,7 +258,7 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist)
                 .config = PERF_COUNT_SW_DUMMY,
                 .size   = sizeof(attr), /* to capture ABI version */
         };
-        struct perf_evsel *evsel = perf_evsel__new(&attr);
+        struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries);
 
         if (evsel == NULL)
                 return -ENOMEM;
@@ -678,11 +676,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 {
         int i;
 
-        if (!evlist->backward_mmap)
+        if (!evlist->overwrite_mmap)
                 return 0;
 
         for (i = 0; i < evlist->nr_mmaps; i++) {
-                int fd = evlist->backward_mmap[i].fd;
+                int fd = evlist->overwrite_mmap[i].fd;
                 int err;
 
                 if (fd < 0)
@@ -704,129 +702,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist)
         return perf_evlist__set_paused(evlist, false);
 }
 
-/* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *
-perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
-                u64 end, u64 *prev)
-{
-        unsigned char *data = md->base + page_size;
-        union perf_event *event = NULL;
-        int diff = end - start;
-
-        if (check_messup) {
-                /*
-                 * If we're further behind than half the buffer, there's a chance
-                 * the writer will bite our tail and mess up the samples under us.
-                 *
-                 * If we somehow ended up ahead of the 'end', we got messed up.
-                 *
-                 * In either case, truncate and restart at 'end'.
-                 */
-                if (diff > md->mask / 2 || diff < 0) {
-                        fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-                        /*
-                         * 'end' points to a known good entry, start there.
-                         */
-                        start = end;
-                        diff = 0;
-                }
-        }
-
-        if (diff >= (int)sizeof(event->header)) {
-                size_t size;
-
-                event = (union perf_event *)&data[start & md->mask];
-                size = event->header.size;
-
-                if (size < sizeof(event->header) || diff < (int)size) {
-                        event = NULL;
-                        goto broken_event;
-                }
-
-                /*
-                 * Event straddles the mmap boundary -- header should always
-                 * be inside due to u64 alignment of output.
-                 */
-                if ((start & md->mask) + size != ((start + size) & md->mask)) {
-                        unsigned int offset = start;
-                        unsigned int len = min(sizeof(*event), size), cpy;
-                        void *dst = md->event_copy;
-
-                        do {
-                                cpy = min(md->mask + 1 - (offset & md->mask), len);
-                                memcpy(dst, &data[offset & md->mask], cpy);
-                                offset += cpy;
-                                dst += cpy;
-                                len -= cpy;
-                        } while (len);
-
-                        event = (union perf_event *) md->event_copy;
-                }
-
-                start += size;
-        }
-
-broken_event:
-        if (prev)
-                *prev = start;
-
-        return event;
-}
-
-union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup)
-{
-        u64 head;
-        u64 old = md->prev;
-
-        /*
-         * Check if event was unmapped due to a POLLHUP/POLLERR.
-         */
-        if (!refcount_read(&md->refcnt))
-                return NULL;
-
-        head = perf_mmap__read_head(md);
-
-        return perf_mmap__read(md, check_messup, old, head, &md->prev);
-}
-
-union perf_event *
-perf_mmap__read_backward(struct perf_mmap *md)
-{
-        u64 head, end;
-        u64 start = md->prev;
-
-        /*
-         * Check if event was unmapped due to a POLLHUP/POLLERR.
-         */
-        if (!refcount_read(&md->refcnt))
-                return NULL;
-
-        head = perf_mmap__read_head(md);
-        if (!head)
-                return NULL;
-
-        /*
-         * 'head' pointer starts from 0. Kernel minus sizeof(record) form
-         * it each time when kernel writes to it, so in fact 'head' is
-         * negative. 'end' pointer is made manually by adding the size of
-         * the ring buffer to 'head' pointer, means the validate data can
-         * read is the whole ring buffer. If 'end' is positive, the ring
-         * buffer has not fully filled, so we must adjust 'end' to 0.
-         *
-         * However, since both 'head' and 'end' is unsigned, we can't
-         * simply compare 'end' against 0. Here we compare '-head' and
-         * the size of the ring buffer, where -head is the number of bytes
-         * kernel write to the ring buffer.
-         */
-        if (-head < (u64)(md->mask + 1))
-                end = 0;
-        else
-                end = head + md->mask + 1;
-
-        return perf_mmap__read(md, false, start, end, &md->prev);
-}
-
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
 {
         struct perf_mmap *md = &evlist->mmap[idx];
@@ -837,19 +712,7 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int
          * No need for read-write ring buffer: kernel stop outputting when
          * it hit md->prev (perf_mmap__consume()).
          */
-        return perf_mmap__read_forward(md, evlist->overwrite);
-}
-
-union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
-{
-        struct perf_mmap *md = &evlist->mmap[idx];
-
-        /*
-         * No need to check messup for backward ring buffer:
-         * We can always read arbitrary long data from a backward
-         * ring buffer unless we forget to pause it before reading.
-         */
-        return perf_mmap__read_backward(md);
+        return perf_mmap__read_forward(md);
 }
 
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
@@ -857,94 +720,9 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
         return perf_evlist__mmap_read_forward(evlist, idx);
 }
 
-void perf_mmap__read_catchup(struct perf_mmap *md)
-{
-        u64 head;
-
-        if (!refcount_read(&md->refcnt))
-                return;
-
-        head = perf_mmap__read_head(md);
-        md->prev = head;
-}
-
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
-{
-        perf_mmap__read_catchup(&evlist->mmap[idx]);
-}
-
-static bool perf_mmap__empty(struct perf_mmap *md)
-{
-        return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
-}
-
-static void perf_mmap__get(struct perf_mmap *map)
-{
-        refcount_inc(&map->refcnt);
-}
-
-static void perf_mmap__put(struct perf_mmap *md)
-{
-        BUG_ON(md->base && refcount_read(&md->refcnt) == 0);
-
-        if (refcount_dec_and_test(&md->refcnt))
-                perf_mmap__munmap(md);
-}
-
-void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
-{
-        if (!overwrite) {
-                u64 old = md->prev;
-
-                perf_mmap__write_tail(md, old);
-        }
-
-        if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md))
-                perf_mmap__put(md);
-}
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
-        perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
-}
-
-int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
-                               struct auxtrace_mmap_params *mp __maybe_unused,
-                               void *userpg __maybe_unused,
-                               int fd __maybe_unused)
-{
-        return 0;
-}
-
-void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
-{
-}
-
-void __weak auxtrace_mmap_params__init(
-                        struct auxtrace_mmap_params *mp __maybe_unused,
-                        off_t auxtrace_offset __maybe_unused,
-                        unsigned int auxtrace_pages __maybe_unused,
-                        bool auxtrace_overwrite __maybe_unused)
-{
-}
-
-void __weak auxtrace_mmap_params__set_idx(
-                        struct auxtrace_mmap_params *mp __maybe_unused,
-                        struct perf_evlist *evlist __maybe_unused,
-                        int idx __maybe_unused,
-                        bool per_cpu __maybe_unused)
-{
-}
-
-static void perf_mmap__munmap(struct perf_mmap *map)
-{
-        if (map->base != NULL) {
-                munmap(map->base, perf_mmap__mmap_len(map));
-                map->base = NULL;
-                map->fd = -1;
-                refcount_set(&map->refcnt, 0);
-        }
-        auxtrace_mmap__munmap(&map->auxtrace_mmap);
+        perf_mmap__consume(&evlist->mmap[idx], false);
 }
 
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
@@ -955,16 +733,16 @@ static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
                 for (i = 0; i < evlist->nr_mmaps; i++)
                         perf_mmap__munmap(&evlist->mmap[i]);
 
-        if (evlist->backward_mmap)
+        if (evlist->overwrite_mmap)
                 for (i = 0; i < evlist->nr_mmaps; i++)
-                        perf_mmap__munmap(&evlist->backward_mmap[i]);
+                        perf_mmap__munmap(&evlist->overwrite_mmap[i]);
 }
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
         perf_evlist__munmap_nofree(evlist);
         zfree(&evlist->mmap);
-        zfree(&evlist->backward_mmap);
+        zfree(&evlist->overwrite_mmap);
 }
 
 static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
@@ -995,48 +773,6 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
         return map;
 }
 
-struct mmap_params {
-        int prot;
-        int mask;
-        struct auxtrace_mmap_params auxtrace_mp;
-};
-
-static int perf_mmap__mmap(struct perf_mmap *map,
-                           struct mmap_params *mp, int fd)
-{
-        /*
-         * The last one will be done at perf_evlist__mmap_consume(), so that we
-         * make sure we don't prevent tools from consuming every last event in
-         * the ring buffer.
-         *
-         * I.e. we can get the POLLHUP meaning that the fd doesn't exist
-         * anymore, but the last events for it are still in the ring buffer,
-         * waiting to be consumed.
-         *
-         * Tools can chose to ignore this at their own discretion, but the
-         * evlist layer can't just drop it when filtering events in
-         * perf_evlist__filter_pollfd().
-         */
-        refcount_set(&map->refcnt, 2);
-        map->prev = 0;
-        map->mask = mp->mask;
-        map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
-                         MAP_SHARED, fd, 0);
-        if (map->base == MAP_FAILED) {
-                pr_debug2("failed to mmap perf event ring buffer, error %d\n",
-                          errno);
-                map->base = NULL;
-                return -1;
-        }
-        map->fd = fd;
-
-        if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
-                                &mp->auxtrace_mp, map->base, fd))
-                return -1;
-
-        return 0;
-}
-
 static bool
 perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
                          struct perf_evsel *evsel)
@@ -1048,7 +784,7 @@ perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
                                        struct mmap_params *mp, int cpu_idx,
-                                       int thread, int *_output, int *_output_backward)
+                                       int thread, int *_output, int *_output_overwrite)
 {
         struct perf_evsel *evsel;
         int revent;
@@ -1060,18 +796,20 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
                 int fd;
                 int cpu;
 
+                mp->prot = PROT_READ | PROT_WRITE;
                 if (evsel->attr.write_backward) {
-                        output = _output_backward;
-                        maps = evlist->backward_mmap;
+                        output = _output_overwrite;
+                        maps = evlist->overwrite_mmap;
 
                         if (!maps) {
                                 maps = perf_evlist__alloc_mmap(evlist);
                                 if (!maps)
                                         return -1;
-                                evlist->backward_mmap = maps;
+                                evlist->overwrite_mmap = maps;
                                 if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
                                         perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
                         }
+                        mp->prot &= ~PROT_WRITE;
                 }
 
                 if (evsel->system_wide && thread)
@@ -1132,14 +870,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
         pr_debug2("perf event ring buffer mmapped per cpu\n");
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 int output = -1;
-                int output_backward = -1;
+                int output_overwrite = -1;
 
                 auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
                                               true);
 
                 for (thread = 0; thread < nr_threads; thread++) {
                         if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-                                                        thread, &output, &output_backward))
+                                                        thread, &output, &output_overwrite))
                                 goto out_unmap;
                 }
         }
@@ -1160,13 +898,13 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
         pr_debug2("perf event ring buffer mmapped per thread\n");
         for (thread = 0; thread < nr_threads; thread++) {
                 int output = -1;
-                int output_backward = -1;
+                int output_overwrite = -1;
 
                 auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
                                               false);
 
                 if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-                                                &output, &output_backward))
+                                                &output, &output_overwrite))
                         goto out_unmap;
         }
 
@@ -1300,15 +1038,18 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  * Return: %0 on success, negative error code otherwise.
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-                         bool overwrite, unsigned int auxtrace_pages,
+                         unsigned int auxtrace_pages,
                          bool auxtrace_overwrite)
 {
         struct perf_evsel *evsel;
         const struct cpu_map *cpus = evlist->cpus;
         const struct thread_map *threads = evlist->threads;
-        struct mmap_params mp = {
-                .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
-        };
+        /*
+         * Delay setting mp.prot: set it before calling perf_mmap__mmap.
+         * Its value is decided by evsel's write_backward.
+         * So &mp should not be passed through const pointer.
+         */
+        struct mmap_params mp;
 
         if (!evlist->mmap)
                 evlist->mmap = perf_evlist__alloc_mmap(evlist);
@@ -1318,7 +1059,6 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
         if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
                 return -ENOMEM;
 
-        evlist->overwrite = overwrite;
         evlist->mmap_len = perf_evlist__mmap_size(pages);
         pr_debug("mmap size %zuB\n", evlist->mmap_len);
         mp.mask = evlist->mmap_len - page_size - 1;
@@ -1339,10 +1079,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
         return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-                      bool overwrite)
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-        return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+        return perf_evlist__mmap_ex(evlist, pages, 0, false);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
@@ -1350,7 +1089,8 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
         struct cpu_map *cpus;
         struct thread_map *threads;
 
-        threads = thread_map__new_str(target->pid, target->tid, target->uid);
+        threads = thread_map__new_str(target->pid, target->tid, target->uid,
+                                      target->per_thread);
 
         if (!threads)
                 return -1;
@@ -1830,6 +1570,17 @@ int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *even
         return perf_evsel__parse_sample(evsel, event, sample);
 }
 
+int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist,
+                                        union perf_event *event,
+                                        u64 *timestamp)
+{
+        struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+        if (!evsel)
+                return -EFAULT;
+        return perf_evsel__parse_sample_timestamp(evsel, event, timestamp);
+}
+
 size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 {
         struct perf_evsel *evsel;
@@ -1987,13 +1738,13 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
                 RESUME,
         } action = NONE;
 
-        if (!evlist->backward_mmap)
+        if (!evlist->overwrite_mmap)
                 return;
 
         switch (old_state) {
         case BKW_MMAP_NOTREADY: {
                 if (state != BKW_MMAP_RUNNING)
-                        goto state_err;;
+                        goto state_err;
                 break;
         }
         case BKW_MMAP_RUNNING: {
@@ -2034,3 +1785,15 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 state_err:
         return;
 }
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (!evsel->attr.exclude_kernel)
+                        return false;
+        }
+
+        return true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index c1750a400bb7..336b838e6957 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -11,8 +11,8 @@
 #include "../perf.h"
 #include "event.h"
 #include "evsel.h"
+#include "mmap.h"
 #include "util.h"
-#include "auxtrace.h"
 #include <signal.h>
 #include <unistd.h>
 
@@ -24,62 +24,12 @@ struct record_opts;
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
 
-/**
- * struct perf_mmap - perf's ring buffer mmap details
- *
- * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
- */
-struct perf_mmap {
-        void             *base;
-        int              mask;
-        int              fd;
-        refcount_t       refcnt;
-        u64              prev;
-        struct auxtrace_mmap auxtrace_mmap;
-        char             event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
-};
-
-static inline size_t
-perf_mmap__mmap_len(struct perf_mmap *map)
-{
-        return map->mask + 1 + page_size;
-}
-
-/*
- * State machine of bkw_mmap_state:
- *
- *                     .________________(forbid)_____________.
- *                     |                                     V
- * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
- *                     ^  ^              |   ^               |
- *                     |  |__(forbid)____/   |___(forbid)___/|
- *                     |                                     |
- *                      \_________________(3)_______________/
- *
- * NOTREADY     : Backward ring buffers are not ready
- * RUNNING      : Backward ring buffers are recording
- * DATA_PENDING : We are required to collect data from backward ring buffers
- * EMPTY        : We have collected data from backward ring buffers.
- *
- * (0): Setup backward ring buffer
- * (1): Pause ring buffers for reading
- * (2): Read from ring buffers
- * (3): Resume ring buffers for recording
- */
-enum bkw_mmap_state {
-        BKW_MMAP_NOTREADY,
-        BKW_MMAP_RUNNING,
-        BKW_MMAP_DATA_PENDING,
-        BKW_MMAP_EMPTY,
-};
-
 struct perf_evlist {
         struct list_head entries;
         struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
         int              nr_entries;
         int              nr_groups;
         int              nr_mmaps;
-        bool             overwrite;
         bool             enabled;
         bool             has_user_cpus;
         size_t           mmap_len;
@@ -93,12 +43,14 @@ struct perf_evlist {
         } workload;
         struct fdarray   pollfd;
         struct perf_mmap *mmap;
-        struct perf_mmap *backward_mmap;
+        struct perf_mmap *overwrite_mmap;
         struct thread_map *threads;
         struct cpu_map    *cpus;
         struct perf_evsel *selected;
         struct events_stats stats;
         struct perf_env *env;
+        u64             first_sample_time;
+        u64             last_sample_time;
 };
 
 struct perf_evsel_str_handler {
@@ -177,20 +129,10 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
 void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
-
-void perf_mmap__read_catchup(struct perf_mmap *md);
-void perf_mmap__consume(struct perf_mmap *md, bool overwrite);
-
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
                                                  int idx);
-union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist,
-                                                  int idx);
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
@@ -223,10 +165,9 @@ int perf_evlist__parse_mmap_pages(const struct option *opt,
 unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
-                         bool overwrite, unsigned int auxtrace_pages,
+                         unsigned int auxtrace_pages,
                          bool auxtrace_overwrite);
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-                      bool overwrite);
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 size_t perf_evlist__mmap_size(unsigned long pages);
@@ -259,6 +200,10 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
                               struct perf_sample *sample);
 
+int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist,
+                                        union perf_event *event,
+                                        u64 *timestamp);
+
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
 bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
@@ -286,25 +231,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
 int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
 
-static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
-{
-        struct perf_event_mmap_page *pc = mm->base;
-        u64 head = ACCESS_ONCE(pc->data_head);
-        rmb();
-        return head;
-}
-
-static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
-{
-        struct perf_event_mmap_page *pc = md->base;
-
-        /*
-         * ensure all reads are done before we write the tail out.
-         */
-        mb();
-        pc->data_tail = tail;
-}
-
 bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
 void perf_evlist__to_front(struct perf_evlist *evlist,
                            struct perf_evsel *move_evsel);
@@ -385,4 +311,6 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
 struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
                                             union perf_event *event);
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0dccdb89572c..ef351688b797 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -36,21 +36,12 @@
 #include "debug.h"
 #include "trace-event.h"
 #include "stat.h"
+#include "memswap.h"
 #include "util/parse-branch-options.h"
 
 #include "sane_ctype.h"
 
-static struct {
-        bool sample_id_all;
-        bool exclude_guest;
-        bool mmap2;
-        bool cloexec;
-        bool clockid;
-        bool clockid_wrong;
-        bool lbr_flags;
-        bool write_backward;
-        bool group_read;
-} perf_missing_features;
+struct perf_missing_features perf_missing_features;
 
 static clockid_t clockid;
 
@@ -650,9 +641,9 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
         return ret;
 }
 
-void perf_evsel__config_callchain(struct perf_evsel *evsel,
-                                  struct record_opts *opts,
-                                  struct callchain_param *param)
+static void __perf_evsel__config_callchain(struct perf_evsel *evsel,
+                                           struct record_opts *opts,
+                                           struct callchain_param *param)
 {
         bool function = perf_evsel__is_function_event(evsel);
         struct perf_event_attr *attr = &evsel->attr;
@@ -683,7 +674,7 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
                 if (!function) {
                         perf_evsel__set_sample_bit(evsel, REGS_USER);
                         perf_evsel__set_sample_bit(evsel, STACK_USER);
-                        attr->sample_regs_user = PERF_REGS_MASK;
+                        attr->sample_regs_user |= PERF_REGS_MASK;
                         attr->sample_stack_user = param->dump_size;
                         attr->exclude_callchain_user = 1;
                 } else {
@@ -698,6 +689,14 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
         }
 }
 
+void perf_evsel__config_callchain(struct perf_evsel *evsel,
+                                  struct record_opts *opts,
+                                  struct callchain_param *param)
+{
+        if (param->enabled)
+                return __perf_evsel__config_callchain(evsel, opts, param);
+}
+
 static void
 perf_evsel__reset_callgraph(struct perf_evsel *evsel,
                             struct callchain_param *param)
@@ -717,28 +716,34 @@ perf_evsel__reset_callgraph(struct perf_evsel *evsel,
 }
 
 static void apply_config_terms(struct perf_evsel *evsel,
-                               struct record_opts *opts)
+                               struct record_opts *opts, bool track)
 {
         struct perf_evsel_config_term *term;
         struct list_head *config_terms = &evsel->config_terms;
         struct perf_event_attr *attr = &evsel->attr;
-        struct callchain_param param;
+        /* callgraph default */
+        struct callchain_param param = {
+                .record_mode = callchain_param.record_mode,
+        };
         u32 dump_size = 0;
         int max_stack = 0;
         const char *callgraph_buf = NULL;
 
-        /* callgraph default */
-        param.record_mode = callchain_param.record_mode;
-
         list_for_each_entry(term, config_terms, list) {
                 switch (term->type) {
                 case PERF_EVSEL__CONFIG_TERM_PERIOD:
-                        attr->sample_period = term->val.period;
-                        attr->freq = 0;
+                        if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
+                                attr->sample_period = term->val.period;
+                                attr->freq = 0;
+                                perf_evsel__reset_sample_bit(evsel, PERIOD);
+                        }
                         break;
                 case PERF_EVSEL__CONFIG_TERM_FREQ:
-                        attr->sample_freq = term->val.freq;
-                        attr->freq = 1;
+                        if (!(term->weak && opts->user_freq != UINT_MAX)) {
+                                attr->sample_freq = term->val.freq;
+                                attr->freq = 1;
+                                perf_evsel__set_sample_bit(evsel, PERIOD);
+                        }
                         break;
                 case PERF_EVSEL__CONFIG_TERM_TIME:
                         if (term->val.time)
@@ -775,6 +780,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
                 case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
                         attr->write_backward = term->val.overwrite ? 1 : 0;
                         break;
+                case PERF_EVSEL__CONFIG_TERM_DRV_CFG:
+                        break;
                 default:
                         break;
                 }
@@ -782,6 +789,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
 
         /* User explicitly set per-event callgraph, clear the old setting and reset. */
         if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) {
+                bool sample_address = false;
+
                 if (max_stack) {
                         param.max_stack = max_stack;
                         if (callgraph_buf == NULL)
@@ -801,6 +810,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
                                                evsel->name);
                                         return;
                                 }
+                                if (param.record_mode == CALLCHAIN_DWARF)
+                                        sample_address = true;
                         }
                 }
                 if (dump_size > 0) {
@@ -813,8 +824,14 @@ static void apply_config_terms(struct perf_evsel *evsel,
                         perf_evsel__reset_callgraph(evsel, &callchain_param);
 
                 /* set perf-event callgraph */
-                if (param.enabled)
+                if (param.enabled) {
+                        if (sample_address) {
+                                perf_evsel__set_sample_bit(evsel, ADDR);
+                                perf_evsel__set_sample_bit(evsel, DATA_SRC);
+                                evsel->attr.mmap_data = track;
+                        }
                         perf_evsel__config_callchain(evsel, opts, &param);
+                }
         }
 }
 
@@ -936,12 +953,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
                 perf_evsel__set_sample_bit(evsel, REGS_INTR);
         }
 
+        if (opts->sample_user_regs) {
+                attr->sample_regs_user |= opts->sample_user_regs;
+                perf_evsel__set_sample_bit(evsel, REGS_USER);
+        }
+
         if (target__has_cpu(&opts->target) || opts->sample_cpu)
                 perf_evsel__set_sample_bit(evsel, CPU);
 
-        if (opts->period)
-                perf_evsel__set_sample_bit(evsel, PERIOD);
-
         /*
          * When the user explicitly disabled time don't force it here.
          */
@@ -1040,9 +1059,17 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
          * Apply event specific term settings,
          * it overloads any global configuration.
          */
-        apply_config_terms(evsel, opts);
+        apply_config_terms(evsel, opts, track);
 
         evsel->ignore_missing_thread = opts->ignore_missing_thread;
+
+        /* The --period option takes the precedence. */
+        if (opts->period_set) {
+                if (opts->period)
+                        perf_evsel__set_sample_bit(evsel, PERIOD);
+                else
+                        perf_evsel__reset_sample_bit(evsel, PERIOD);
+        }
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -1366,7 +1393,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader,
 static int
 perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
 {
-        struct perf_stat_evsel *ps = leader->priv;
+        struct perf_stat_evsel *ps = leader->stats;
         u64 read_format = leader->attr.read_format;
         int size = perf_evsel__read_size(leader);
         u64 *data = ps->group_data;
@@ -1565,6 +1592,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
         PRINT_ATTRf(use_clockid, p_unsigned);
         PRINT_ATTRf(context_switch, p_unsigned);
         PRINT_ATTRf(write_backward, p_unsigned);
+        PRINT_ATTRf(namespaces, p_unsigned);
 
         PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
         PRINT_ATTRf(bp_type, p_unsigned);
@@ -1587,10 +1615,46 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
         return fprintf(fp, "  %-32s %s\n", name, val);
 }
 
+static void perf_evsel__remove_fd(struct perf_evsel *pos,
+                                  int nr_cpus, int nr_threads,
+                                  int thread_idx)
+{
+        for (int cpu = 0; cpu < nr_cpus; cpu++)
+                for (int thread = thread_idx; thread < nr_threads - 1; thread++)
+                        FD(pos, cpu, thread) = FD(pos, cpu, thread + 1);
+}
+
+static int update_fds(struct perf_evsel *evsel,
+                      int nr_cpus, int cpu_idx,
+                      int nr_threads, int thread_idx)
+{
+        struct perf_evsel *pos;
+
+        if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
+                return -EINVAL;
+
+        evlist__for_each_entry(evsel->evlist, pos) {
+                nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
+
+                perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
+
+                /*
+                 * Since fds for next evsel has not been created,
+                 * there is no need to iterate whole event list.
+                 */
+                if (pos == evsel)
+                        break;
+        }
+        return 0;
+}
+
 static bool ignore_missing_thread(struct perf_evsel *evsel,
+                                  int nr_cpus, int cpu,
                                   struct thread_map *threads,
                                   int thread, int err)
 {
+        pid_t ignore_pid = thread_map__pid(threads, thread);
+
         if (!evsel->ignore_missing_thread)
                 return false;
 
@@ -1606,11 +1670,18 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
         if (threads->nr == 1)
                 return false;
 
+        /*
+         * We should remove fd for missing_thread first
+         * because thread_map__remove() will decrease threads->nr.
+         */
+        if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
+                return false;
+
         if (thread_map__remove(threads, thread))
                 return false;
 
         pr_warning("WARNING: Ignored open failure for pid %d\n",
-                   thread_map__pid(threads, thread));
+                   ignore_pid);
         return true;
 }
 
@@ -1715,7 +1786,7 @@ retry_open:
                         if (fd < 0) {
                                 err = -errno;
 
-                                if (ignore_missing_thread(evsel, threads, thread, err)) {
+                                if (ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
                                         /*
                                          * We just removed 1 thread, so take a step
                                          * back on thread index and lower the upper
@@ -1951,6 +2022,20 @@ static inline bool overflow(const void *endp, u16 max_size, const void *offset,
 #define OVERFLOW_CHECK_u64(offset) \
         OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
 
+static int
+perf_event__check_size(union perf_event *event, unsigned int sample_size)
+{
+        /*
+         * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
+         * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
+         * check the format does not go past the end of the event.
+         */
+        if (sample_size + sizeof(event->header) > event->header.size)
+                return -EFAULT;
+
+        return 0;
+}
+
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                              struct perf_sample *data)
 {
@@ -1972,6 +2057,9 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
         data->stream_id = data->id = data->time = -1ULL;
         data->period = evsel->attr.sample_period;
         data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+        data->misc    = event->header.misc;
+        data->id = -1ULL;
+        data->data_src = PERF_MEM_DATA_SRC_NONE;
 
         if (event->header.type != PERF_RECORD_SAMPLE) {
                 if (!evsel->attr.sample_id_all)
@@ -1981,15 +2069,9 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 
         array = event->sample.array;
 
-        /*
-         * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
-         * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
-         * check the format does not go past the end of the event.
-         */
-        if (evsel->sample_size + sizeof(event->header) > event->header.size)
+        if (perf_event__check_size(event, evsel->sample_size))
                 return -EFAULT;
 
-        data->id = -1ULL;
         if (type & PERF_SAMPLE_IDENTIFIER) {
                 data->id = *array;
                 array++;
@@ -2019,7 +2101,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 array++;
         }
 
-        data->addr = 0;
         if (type & PERF_SAMPLE_ADDR) {
                 data->addr = *array;
                 array++;
@@ -2111,14 +2192,27 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
         if (type & PERF_SAMPLE_RAW) {
                 OVERFLOW_CHECK_u64(array);
                 u.val64 = *array;
-                if (WARN_ONCE(swapped,
-                              "Endianness of raw data not corrected!\n")) {
-                        /* undo swap of u64, then swap on individual u32s */
+
+                /*
+                 * Undo swap of u64, then swap on individual u32s,
+                 * get the size of the raw area and undo all of the
+                 * swap. The pevent interface handles endianity by
+                 * itself.
+                 */
+                if (swapped) {
                         u.val64 = bswap_64(u.val64);
                         u.val32[0] = bswap_32(u.val32[0]);
                         u.val32[1] = bswap_32(u.val32[1]);
                 }
                 data->raw_size = u.val32[0];
+
+                /*
+                 * The raw data is aligned on 64bits including the
+                 * u32 size, so it's safe to use mem_bswap_64.
+                 */
+                if (swapped)
+                        mem_bswap_64((void *) array, data->raw_size);
+
                 array = (void *)array + sizeof(u32);
 
                 OVERFLOW_CHECK(array, data->raw_size, max_size);
@@ -2183,14 +2277,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 array++;
         }
 
-        data->data_src = PERF_MEM_DATA_SRC_NONE;
         if (type & PERF_SAMPLE_DATA_SRC) {
                 OVERFLOW_CHECK_u64(array);
                 data->data_src = *array;
                 array++;
         }
 
-        data->transaction = 0;
         if (type & PERF_SAMPLE_TRANSACTION) {
                 OVERFLOW_CHECK_u64(array);
                 data->transaction = *array;
@@ -2223,6 +2315,50 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
         return 0;
 }
 
+int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel,
+                                       union perf_event *event,
+                                       u64 *timestamp)
+{
+        u64 type = evsel->attr.sample_type;
+        const u64 *array;
+
+        if (!(type & PERF_SAMPLE_TIME))
+                return -1;
+
+        if (event->header.type != PERF_RECORD_SAMPLE) {
+                struct perf_sample data = {
+                        .time = -1ULL,
+                };
+
+                if (!evsel->attr.sample_id_all)
+                        return -1;
+                if (perf_evsel__parse_id_sample(evsel, event, &data))
+                        return -1;
+
+                *timestamp = data.time;
+                return 0;
+        }
+
+        array = event->sample.array;
+
+        if (perf_event__check_size(event, evsel->sample_size))
+                return -EFAULT;
+
+        if (type & PERF_SAMPLE_IDENTIFIER)
+                array++;
+
+        if (type & PERF_SAMPLE_IP)
+                array++;
+
+        if (type & PERF_SAMPLE_TID)
+                array++;
+
+        if (type & PERF_SAMPLE_TIME)
+                *timestamp = *array;
+
+        return 0;
+}
+
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
                                      u64 read_format)
 {
@@ -2333,8 +2469,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
                                   u64 read_format,
-                                  const struct perf_sample *sample,
-                                  bool swapped)
+                                  const struct perf_sample *sample)
 {
         u64 *array;
         size_t sz;
@@ -2359,15 +2494,6 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
         if (type & PERF_SAMPLE_TID) {
                 u.val32[0] = sample->pid;
                 u.val32[1] = sample->tid;
-                if (swapped) {
-                        /*
-                         * Inverse of what is done in perf_evsel__parse_sample
-                         */
-                        u.val32[0] = bswap_32(u.val32[0]);
-                        u.val32[1] = bswap_32(u.val32[1]);
-                        u.val64 = bswap_64(u.val64);
-                }
-
                 *array = u.val64;
                 array++;
         }
@@ -2394,13 +2520,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
         if (type & PERF_SAMPLE_CPU) {
                 u.val32[0] = sample->cpu;
-                if (swapped) {
-                        /*
-                         * Inverse of what is done in perf_evsel__parse_sample
-                         */
-                        u.val32[0] = bswap_32(u.val32[0]);
-                        u.val64 = bswap_64(u.val64);
-                }
+                u.val32[1] = 0;
                 *array = u.val64;
                 array++;
         }
@@ -2447,15 +2567,6 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
         if (type & PERF_SAMPLE_RAW) {
                 u.val32[0] = sample->raw_size;
-                if (WARN_ONCE(swapped,
-                              "Endianness of raw data not corrected!\n")) {
-                        /*
-                         * Inverse of what is done in perf_evsel__parse_sample
-                         */
-                        u.val32[0] = bswap_32(u.val32[0]);
-                        u.val32[1] = bswap_32(u.val32[1]);
-                        u.val64 = bswap_64(u.val64);
-                }
                 *array = u.val64;
                 array = (void *)array + sizeof(u32);
 
@@ -2734,8 +2845,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
                 break;
         case EOPNOTSUPP:
                 if (evsel->attr.sample_period != 0)
-                        return scnprintf(msg, size, "%s",
-        "PMU Hardware doesn't support sampling/overflow-interrupts.");
+                        return scnprintf(msg, size,
+        "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
+                                         perf_evsel__name(evsel));
                 if (evsel->attr.precise_ip)
                         return scnprintf(msg, size, "%s",
         "\'precise\' request may not be supported. Try removing 'p' modifier.");
@@ -2772,16 +2884,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
                          perf_evsel__name(evsel));
 }
 
-char *perf_evsel__env_arch(struct perf_evsel *evsel)
-{
-        if (evsel && evsel->evlist && evsel->evlist->env)
-                return evsel->evlist->env->arch;
-        return NULL;
-}
-
-char *perf_evsel__env_cpuid(struct perf_evsel *evsel)
+struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
 {
-        if (evsel && evsel->evlist && evsel->evlist->env)
-                return evsel->evlist->env->cpuid;
+        if (evsel && evsel->evlist)
+                return evsel->evlist->env;
         return NULL;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b4df79d72329..a7487c6d1866 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -38,7 +38,7 @@ struct cgroup_sel;
  * It is allocated within event parsing and attached to
  * perf_evsel::config_terms list head.
 */
-enum {
+enum term_type {
         PERF_EVSEL__CONFIG_TERM_PERIOD,
         PERF_EVSEL__CONFIG_TERM_FREQ,
         PERF_EVSEL__CONFIG_TERM_TIME,
@@ -49,12 +49,11 @@ enum {
         PERF_EVSEL__CONFIG_TERM_OVERWRITE,
         PERF_EVSEL__CONFIG_TERM_DRV_CFG,
         PERF_EVSEL__CONFIG_TERM_BRANCH,
-        PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
 struct perf_evsel_config_term {
         struct list_head        list;
-        int     type;
+        enum term_type  type;
         union {
                 u64     period;
                 u64     freq;
@@ -67,8 +66,11 @@ struct perf_evsel_config_term {
                 bool    overwrite;
                 char    *branch;
         } val;
+        bool weak;
 };
 
+struct perf_stat_evsel;
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -102,6 +104,7 @@ struct perf_evsel {
         const char              *unit;
         struct event_format     *tp_format;
         off_t                   id_offset;
+        struct perf_stat_evsel  *stats;
         void                    *priv;
         u64                     db_id;
         struct cgroup_sel       *cgrp;
@@ -138,6 +141,7 @@ struct perf_evsel {
         const char *            metric_name;
         struct perf_evsel       **metric_events;
         bool                    collect_stat;
+        bool                    weak_group;
 };
 
 union u64_swap {
@@ -145,6 +149,20 @@ union u64_swap {
         u32 val32[2];
 };
 
+struct perf_missing_features {
+        bool sample_id_all;
+        bool exclude_guest;
+        bool mmap2;
+        bool cloexec;
+        bool clockid;
+        bool clockid_wrong;
+        bool lbr_flags;
+        bool write_backward;
+        bool group_read;
+};
+
+extern struct perf_missing_features perf_missing_features;
+
 struct cpu_map;
 struct target;
 struct thread_map;
@@ -334,6 +352,10 @@ static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                              struct perf_sample *sample);
 
+int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel,
+                                       union perf_event *event,
+                                       u64 *timestamp);
+
 static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 {
         return list_entry(evsel->node.next, struct perf_evsel, node);
@@ -438,7 +460,6 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
                              attr__fprintf_f attr__fprintf, void *priv);
 
-char *perf_evsel__env_arch(struct perf_evsel *evsel);
-char *perf_evsel__env_cpuid(struct perf_evsel *evsel);
+struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
 
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 1fd7c2e46db2..06dfb027879d 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -158,7 +158,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
                                 }
                         }
 
-                        if (print_dso) {
+                        if (print_dso && (!node->sym || !node->sym->inlined)) {
                                 printed += fprintf(fp, " (");
                                 printed += map__fprintf_dsoname(node->map, fp);
                                 printed += fprintf(fp, ")");
@@ -167,41 +167,12 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
                         if (print_srcline)
                                 printed += map__fprintf_srcline(node->map, addr, "\n  ", fp);
 
+                        if (node->sym && node->sym->inlined)
+                                printed += fprintf(fp, " (inlined)");
+
                         if (!print_oneline)
                                 printed += fprintf(fp, "\n");
 
-                        if (symbol_conf.inline_name && node->map) {
-                                struct inline_node *inode;
-
-                                addr = map__rip_2objdump(node->map, node->ip),
-                                inode = dso__parse_addr_inlines(node->map->dso, addr);
-
-                                if (inode) {
-                                        struct inline_list *ilist;
-
-                                        list_for_each_entry(ilist, &inode->val, list) {
-                                                if (print_arrow)
-                                                        printed += fprintf(fp, " <-");
-
-                                                /* IP is same, just skip it */
-                                                if (print_ip)
-                                                        printed += fprintf(fp, "%c%16s",
-                                                                           s, "");
-                                                if (print_sym)
-                                                        printed += fprintf(fp, " %s",
-                                                                           ilist->funcname);
-                                                if (print_srcline)
-                                                        printed += fprintf(fp, "\n  %s:%d",
-                                                                           ilist->filename,
-                                                                           ilist->line_nr);
-                                                if (!print_oneline)
-                                                        printed += fprintf(fp, "\n");
-                                        }
-
-                                        inline_node__delete(inode);
-                                }
-                        }
-
                         if (symbol_conf.bt_stop_list &&
                             node->sym &&
                             strlist__has_entry(symbol_conf.bt_stop_list,
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 9bbcec4e3365..ff17920a5ebc 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -38,7 +38,7 @@ do
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
 
-echo "#ifdef HAVE_LIBAUDIT_SUPPORT"
+echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)"
 sed -n -e 's/^perf-\([^         ]*\)[   ].* audit*/\1/p' command-list.txt |
 sort |
 while read cmd
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ba0cea8fef72..a326e0d8b5b6 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -15,9 +15,8 @@
 #include <linux/bitops.h>
 #include <linux/stringify.h>
 #include <sys/stat.h>
-#include <sys/types.h>
 #include <sys/utsname.h>
-#include <unistd.h>
+#include <linux/time64.h>
 
 #include "evlist.h"
 #include "evsel.h"
@@ -37,6 +36,7 @@
 #include <api/fs/fs.h>
 #include "asm/bug.h"
 #include "tool.h"
+#include "time-utils.h"
 
 #include "sane_ctype.h"
 
@@ -1182,6 +1182,20 @@ static int write_stat(struct feat_fd *ff __maybe_unused,
         return 0;
 }
 
+static int write_sample_time(struct feat_fd *ff,
+                             struct perf_evlist *evlist)
+{
+        int ret;
+
+        ret = do_write(ff, &evlist->first_sample_time,
+                       sizeof(evlist->first_sample_time));
+        if (ret < 0)
+                return ret;
+
+        return do_write(ff, &evlist->last_sample_time,
+                        sizeof(evlist->last_sample_time));
+}
+
 static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
         fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1507,6 +1521,28 @@ static void print_group_desc(struct feat_fd *ff, FILE *fp)
         }
 }
 
+static void print_sample_time(struct feat_fd *ff, FILE *fp)
+{
+        struct perf_session *session;
+        char time_buf[32];
+        double d;
+
+        session = container_of(ff->ph, struct perf_session, header);
+
+        timestamp__scnprintf_usec(session->evlist->first_sample_time,
+                                  time_buf, sizeof(time_buf));
+        fprintf(fp, "# time of first sample : %s\n", time_buf);
+
+        timestamp__scnprintf_usec(session->evlist->last_sample_time,
+                                  time_buf, sizeof(time_buf));
+        fprintf(fp, "# time of last sample : %s\n", time_buf);
+
+        d = (double)(session->evlist->last_sample_time -
+                session->evlist->first_sample_time) / NSEC_PER_MSEC;
+
+        fprintf(fp, "# sample duration : %10.3f ms\n", d);
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
                                     char *filename,
                                     struct perf_session *session)
@@ -1763,7 +1799,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 
         session = container_of(ff->ph, struct perf_session, header);
 
-        if (session->file->is_pipe) {
+        if (session->data->is_pipe) {
                 /* Save events for reading later by print_event_desc,
                  * since they can't be read again in pipe mode. */
                 ff->events = events;
@@ -1772,7 +1808,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
         for (evsel = events; evsel->attr.size; evsel++)
                 perf_evlist__set_event_name(session->evlist, evsel);
 
-        if (!session->file->is_pipe)
+        if (!session->data->is_pipe)
                 free_event_desc(events);
 
         return 0;
@@ -2148,6 +2184,27 @@ out_free_caches:
         return -1;
 }
 
+static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused)
+{
+        struct perf_session *session;
+        u64 first_sample_time, last_sample_time;
+        int ret;
+
+        session = container_of(ff->ph, struct perf_session, header);
+
+        ret = do_read_u64(ff, &first_sample_time);
+        if (ret)
+                return -1;
+
+        ret = do_read_u64(ff, &last_sample_time);
+        if (ret)
+                return -1;
+
+        session->evlist->first_sample_time = first_sample_time;
+        session->evlist->last_sample_time = last_sample_time;
+        return 0;
+}
+
 struct feature_ops {
         int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
         void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2205,6 +2262,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
         FEAT_OPN(AUXTRACE,      auxtrace,       false),
         FEAT_OPN(STAT,          stat,           false),
         FEAT_OPN(CACHE,         cache,          true),
+        FEAT_OPR(SAMPLE_TIME,   sample_time,    false),
 };
 
 struct header_print_data {
@@ -2249,7 +2307,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 {
         struct header_print_data hd;
         struct perf_header *header = &session->header;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         struct stat st;
         int ret, bit;
 
@@ -2265,7 +2323,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
         perf_header__process_sections(header, fd, &hd,
                                       perf_file_section__fprintf_info);
 
-        if (session->file->is_pipe)
+        if (session->data->is_pipe)
                 return 0;
 
         fprintf(fp, "# missing features: ");
@@ -2758,7 +2816,7 @@ static int perf_header__read_pipe(struct perf_session *session)
         struct perf_pipe_file_header f_header;
 
         if (perf_file_header__read_pipe(&f_header, header,
-                                        perf_data_file__fd(session->file),
+                                        perf_data__fd(session->data),
                                         session->repipe) < 0) {
                 pr_debug("incompatible file format\n");
                 return -EINVAL;
@@ -2861,13 +2919,13 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 
 int perf_session__read_header(struct perf_session *session)
 {
-        struct perf_data_file *file = session->file;
+        struct perf_data *data = session->data;
         struct perf_header *header = &session->header;
         struct perf_file_header f_header;
         struct perf_file_attr   f_attr;
         u64                     f_id;
         int nr_attrs, nr_ids, i, j;
-        int fd = perf_data_file__fd(file);
+        int fd = perf_data__fd(data);
 
         session->evlist = perf_evlist__new();
         if (session->evlist == NULL)
@@ -2875,7 +2933,7 @@ int perf_session__read_header(struct perf_session *session)
 
         session->evlist->env = &header->env;
         session->machines.host.env = &header->env;
-        if (perf_data_file__is_pipe(file))
+        if (perf_data__is_pipe(data))
                 return perf_header__read_pipe(session);
 
         if (perf_file_header__read(&f_header, header, fd) < 0)
@@ -2890,7 +2948,7 @@ int perf_session__read_header(struct perf_session *session)
         if (f_header.data.size == 0) {
                 pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
                            "Was the 'perf record' command properly terminated?\n",
-                           file->path);
+                           data->file.path);
         }
 
         nr_attrs = f_header.attrs.size / f_header.attr_size;
@@ -3258,6 +3316,74 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
         return err;
 }
 
+static bool has_unit(struct perf_evsel *counter)
+{
+        return counter->unit && *counter->unit;
+}
+
+static bool has_scale(struct perf_evsel *counter)
+{
+        return counter->scale != 1;
+}
+
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+                                      struct perf_evlist *evsel_list,
+                                      perf_event__handler_t process,
+                                      bool is_pipe)
+{
+        struct perf_evsel *counter;
+        int err;
+
+        /*
+         * Synthesize other events stuff not carried within
+         * attr event - unit, scale, name
+         */
+        evlist__for_each_entry(evsel_list, counter) {
+                if (!counter->supported)
+                        continue;
+
+                /*
+                 * Synthesize unit and scale only if it's defined.
+                 */
+                if (has_unit(counter)) {
+                        err = perf_event__synthesize_event_update_unit(tool, counter, process);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel unit.\n");
+                                return err;
+                        }
+                }
+
+                if (has_scale(counter)) {
+                        err = perf_event__synthesize_event_update_scale(tool, counter, process);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel counter.\n");
+                                return err;
+                        }
+                }
+
+                if (counter->own_cpus) {
+                        err = perf_event__synthesize_event_update_cpus(tool, counter, process);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel cpus.\n");
+                                return err;
+                        }
+                }
+
+                /*
+                 * Name is needed only for pipe output,
+                 * perf.data carries event names.
+                 */
+                if (is_pipe) {
+                        err = perf_event__synthesize_event_update_name(tool, counter, process);
+                        if (err < 0) {
+                                pr_err("Couldn't synthesize evsel name.\n");
+                                return err;
+                        }
+                }
+        }
+        return 0;
+}
+
 int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
                              union perf_event *event,
                              struct perf_evlist **pevlist)
@@ -3398,7 +3524,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
                                      struct perf_session *session)
 {
         ssize_t size_read, padding, size = event->tracing_data.size;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         off_t offset = lseek(fd, 0, SEEK_CUR);
         char buf[BUFSIZ];
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 29ccbfdf8724..f28aaaa3a440 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "env.h"
+#include "pmu.h"
 
 enum {
         HEADER_RESERVED         = 0,    /* always cleared */
@@ -34,6 +35,7 @@ enum {
         HEADER_AUXTRACE,
         HEADER_STAT,
         HEADER_CACHE,
+        HEADER_SAMPLE_TIME,
         HEADER_LAST_FEATURE,
         HEADER_FEAT_BITS        = 256,
 };
@@ -107,6 +109,11 @@ int perf_event__synthesize_features(struct perf_tool *tool,
                                     struct perf_evlist *evlist,
                                     perf_event__handler_t process);
 
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+                                      struct perf_evlist *evsel_list,
+                                      perf_event__handler_t process,
+                                      bool is_pipe);
+
 int perf_event__process_feature(struct perf_tool *tool,
                                 union perf_event *event,
                                 struct perf_session *session);
@@ -166,5 +173,5 @@ int write_padded(struct feat_fd *fd, const void *bf,
  */
 int get_cpuid(char *buffer, size_t sz);
 
-char *get_cpuid_str(void);
+char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 097473600d94..b6140950301e 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -597,6 +597,7 @@ __hists__add_entry(struct hists *hists,
                         .map    = al->map,
                         .sym    = al->sym,
                 },
+                .srcline = al->srcline ? strdup(al->srcline) : NULL,
                 .socket  = al->socket,
                 .cpu     = al->cpu,
                 .cpumode = al->cpumode,
@@ -951,6 +952,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
                         .map = al->map,
                         .sym = al->sym,
                 },
+                .srcline = al->srcline ? strdup(al->srcline) : NULL,
                 .parent = iter->parent,
                 .raw_data = sample->raw_data,
                 .raw_size = sample->raw_size,
@@ -1142,11 +1144,6 @@ void hist_entry__delete(struct hist_entry *he)
                 zfree(&he->mem_info);
         }
 
-        if (he->inline_node) {
-                inline_node__delete(he->inline_node);
-                he->inline_node = NULL;
-        }
-
         zfree(&he->stat_acc);
         free_srcline(he->srcline);
         if (he->srcfile && he->srcfile[0])
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index f6630cb95eff..02721b579746 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -430,7 +430,8 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                   struct hist_browser_timer *hbt,
                                   float min_pcnt,
-                                  struct perf_env *env);
+                                  struct perf_env *env,
+                                  bool warn_lost_event);
 int script_browse(const char *script_opt);
 #else
 static inline
@@ -438,7 +439,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
                                   const char *help __maybe_unused,
                                   struct hist_browser_timer *hbt __maybe_unused,
                                   float min_pcnt __maybe_unused,
-                                  struct perf_env *env __maybe_unused)
+                                  struct perf_env *env __maybe_unused,
+                                  bool warn_lost_event __maybe_unused)
 {
         return 0;
 }
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 218ee2bac9a5..72db2744876d 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -67,7 +67,6 @@ struct intel_bts {
         u64                             branches_sample_type;
         u64                             branches_id;
         size_t                          branches_event_size;
-        bool                            synth_needs_swap;
         unsigned long                   num_events;
 };
 
@@ -303,8 +302,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
                 event.sample.header.size = bts->branches_event_size;
                 ret = perf_event__synthesize_sample(&event,
                                                     bts->branches_sample_type,
-                                                    0, &sample,
-                                                    bts->synth_needs_swap);
+                                                    0, &sample);
                 if (ret)
                         return ret;
         }
@@ -500,7 +498,7 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
         }
 
         if (!buffer->data) {
-                int fd = perf_data_file__fd(btsq->bts->session->file);
+                int fd = perf_data__fd(btsq->bts->session->data);
 
                 buffer->data = auxtrace_buffer__get_data(buffer, fd);
                 if (!buffer->data) {
@@ -664,10 +662,10 @@ static int intel_bts_process_auxtrace_event(struct perf_session *session,
         if (!bts->data_queued) {
                 struct auxtrace_buffer *buffer;
                 off_t data_offset;
-                int fd = perf_data_file__fd(session->file);
+                int fd = perf_data__fd(session->data);
                 int err;
 
-                if (perf_data_file__is_pipe(session->file)) {
+                if (perf_data__is_pipe(session->data)) {
                         data_offset = 0;
                 } else {
                         data_offset = lseek(fd, 0, SEEK_CUR);
@@ -841,8 +839,6 @@ static int intel_bts_synth_events(struct intel_bts *bts,
                                 __perf_evsel__sample_size(attr.sample_type);
         }
 
-        bts->synth_needs_swap = evsel->needs_swap;
-
         return 0;
 }
 
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 10e0814bb8d2..1b704fbea9de 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -11,15 +11,21 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
         @(diff -I 2>&1 | grep -q 'option requires an argument' && \
-        test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
-        diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
-        diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
-        diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
-        diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
-        diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
-        diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
-        diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
-        || echo "Warning: Intel PT: x86 instruction decoder differs from kernel" >&2 )) || true
+        test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+        ((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \
+        (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \
+        ((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \
+        (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \
+        ((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \
+        (echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \
+        ((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \
+        (echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \
+        ((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \
+        (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \
+        ((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \
+        (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \
+        ((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \
+        (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 125ecd2a300d..52dc8d911173 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)    ((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)      (imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE     0
+#define INAT_SEG_REG_DEFAULT    1
+#define INAT_SEG_REG_CS         2
+#define INAT_SEG_REG_SS         3
+#define INAT_SEG_REG_DS         4
+#define INAT_SEG_REG_ES         5
+#define INAT_SEG_REG_FS         6
+#define INAT_SEG_REG_GS         7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index 12e377184ee4..e0b85930dd77 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
 fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
 fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
 fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
 EndTable
 
 Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
 7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
 83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
 88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -896,7 +896,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb
@@ -970,6 +970,15 @@ GrpTable: Grp9
 EndTable
 
 GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
 EndTable
 
 # Grp11A and Grp11B are expressed as Grp11 in Intel SDM
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index b58f9fd1e2ee..3773d9c54f45 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -104,8 +104,6 @@ struct intel_pt {
         u64 pwrx_id;
         u64 cbr_id;
 
-        bool synth_needs_swap;
-
         u64 tsc_bit;
         u64 mtc_bit;
         u64 mtc_freq_bits;
@@ -271,7 +269,7 @@ next:
         ptq->buffer = buffer;
 
         if (!buffer->data) {
-                int fd = perf_data_file__fd(ptq->pt->session->file);
+                int fd = perf_data__fd(ptq->pt->session->data);
 
                 buffer->data = auxtrace_buffer__get_data(buffer, fd);
                 if (!buffer->data)
@@ -1101,11 +1099,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 }
 
 static int intel_pt_inject_event(union perf_event *event,
-                                 struct perf_sample *sample, u64 type,
-                                 bool swapped)
+                                 struct perf_sample *sample, u64 type)
 {
         event->header.size = perf_event__sample_event_size(sample, type, 0);
-        return perf_event__synthesize_sample(event, type, 0, sample, swapped);
+        return perf_event__synthesize_sample(event, type, 0, sample);
 }
 
 static inline int intel_pt_opt_inject(struct intel_pt *pt,
@@ -1115,7 +1112,7 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
         if (!pt->synth_opts.inject)
                 return 0;
 
-        return intel_pt_inject_event(event, sample, type, pt->synth_needs_swap);
+        return intel_pt_inject_event(event, sample, type);
 }
 
 static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
@@ -2084,10 +2081,10 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session,
         if (!pt->data_queued) {
                 struct auxtrace_buffer *buffer;
                 off_t data_offset;
-                int fd = perf_data_file__fd(session->file);
+                int fd = perf_data__fd(session->data);
                 int err;
 
-                if (perf_data_file__is_pipe(session->file)) {
+                if (perf_data__is_pipe(session->data)) {
                         data_offset = 0;
                 } else {
                         data_offset = lseek(fd, 0, SEEK_CUR);
@@ -2329,8 +2326,6 @@ static int intel_pt_synth_events(struct intel_pt *pt,
                 id += 1;
         }
 
-        pt->synth_needs_swap = evsel->needs_swap;
-
         return 0;
 }
 
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
index c2582fa9fe21..6817ffc2a059 100644
--- a/tools/perf/util/jit.h
+++ b/tools/perf/util/jit.h
@@ -4,7 +4,7 @@
 
 #include <data.h>
 
-int jit_process(struct perf_session *session, struct perf_data_file *output,
+int jit_process(struct perf_session *session, struct perf_data *output,
                 struct machine *machine, char *filename, pid_t pid, u64 *nbytes);
 
 int jit_inject_record(const char *filename);
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 36483db032e8..a1863000e972 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -30,7 +30,7 @@
 #include "sane_ctype.h"
 
 struct jit_buf_desc {
-        struct perf_data_file *output;
+        struct perf_data *output;
         struct perf_session *session;
         struct machine *machine;
         union jr_entry   *entry;
@@ -61,8 +61,8 @@ struct debug_line_info {
 
 struct jit_tool {
         struct perf_tool tool;
-        struct perf_data_file   output;
-        struct perf_data_file   input;
+        struct perf_data        output;
+        struct perf_data        input;
         u64 bytes_written;
 };
 
@@ -357,7 +357,7 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
 {
         ssize_t size;
 
-        size = perf_data_file__write(jd->output, event, event->header.size);
+        size = perf_data__write(jd->output, event, event->header.size);
         if (size < 0)
                 return -1;
 
@@ -752,7 +752,7 @@ jit_detect(char *mmap_name, pid_t pid)
 
 int
 jit_process(struct perf_session *session,
-            struct perf_data_file *output,
+            struct perf_data *output,
             struct machine *machine,
             char *filename,
             pid_t pid,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index bd5d5b5e2218..b05a67464c03 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -31,7 +31,21 @@ static void dsos__init(struct dsos *dsos)
 {
         INIT_LIST_HEAD(&dsos->head);
         dsos->root = RB_ROOT;
-        pthread_rwlock_init(&dsos->lock, NULL);
+        init_rwsem(&dsos->lock);
+}
+
+static void machine__threads_init(struct machine *machine)
+{
+        int i;
+
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+                threads->entries = RB_ROOT;
+                init_rwsem(&threads->lock);
+                threads->nr = 0;
+                INIT_LIST_HEAD(&threads->dead);
+                threads->last_match = NULL;
+        }
 }
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
@@ -41,11 +55,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
         RB_CLEAR_NODE(&machine->rb_node);
         dsos__init(&machine->dsos);
 
-        machine->threads = RB_ROOT;
-        pthread_rwlock_init(&machine->threads_lock, NULL);
-        machine->nr_threads = 0;
-        INIT_LIST_HEAD(&machine->dead_threads);
-        machine->last_match = NULL;
+        machine__threads_init(machine);
 
         machine->vdso_info = NULL;
         machine->env = NULL;
@@ -121,7 +131,7 @@ static void dsos__purge(struct dsos *dsos)
 {
         struct dso *pos, *n;
 
-        pthread_rwlock_wrlock(&dsos->lock);
+        down_write(&dsos->lock);
 
         list_for_each_entry_safe(pos, n, &dsos->head, node) {
                 RB_CLEAR_NODE(&pos->rb_node);
@@ -130,39 +140,52 @@ static void dsos__purge(struct dsos *dsos)
                 dso__put(pos);
         }
 
-        pthread_rwlock_unlock(&dsos->lock);
+        up_write(&dsos->lock);
 }
 
 static void dsos__exit(struct dsos *dsos)
 {
         dsos__purge(dsos);
-        pthread_rwlock_destroy(&dsos->lock);
+        exit_rwsem(&dsos->lock);
 }
 
 void machine__delete_threads(struct machine *machine)
 {
         struct rb_node *nd;
+        int i;
 
-        pthread_rwlock_wrlock(&machine->threads_lock);
-        nd = rb_first(&machine->threads);
-        while (nd) {
-                struct thread *t = rb_entry(nd, struct thread, rb_node);
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+                down_write(&threads->lock);
+                nd = rb_first(&threads->entries);
+                while (nd) {
+                        struct thread *t = rb_entry(nd, struct thread, rb_node);
 
-                nd = rb_next(nd);
-                __machine__remove_thread(machine, t, false);
+                        nd = rb_next(nd);
+                        __machine__remove_thread(machine, t, false);
+                }
+                up_write(&threads->lock);
         }
-        pthread_rwlock_unlock(&machine->threads_lock);
 }
 
 void machine__exit(struct machine *machine)
 {
+        int i;
+
+        if (machine == NULL)
+                return;
+
         machine__destroy_kernel_maps(machine);
         map_groups__exit(&machine->kmaps);
         dsos__exit(&machine->dsos);
         machine__exit_vdso(machine);
         zfree(&machine->root_dir);
         zfree(&machine->current_tid);
-        pthread_rwlock_destroy(&machine->threads_lock);
+
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+                exit_rwsem(&threads->lock);
+        }
 }
 
 void machine__delete(struct machine *machine)
@@ -380,10 +403,11 @@ out_err:
  * lookup/new thread inserted.
  */
 static struct thread *____machine__findnew_thread(struct machine *machine,
+                                                  struct threads *threads,
                                                   pid_t pid, pid_t tid,
                                                   bool create)
 {
-        struct rb_node **p = &machine->threads.rb_node;
+        struct rb_node **p = &threads->entries.rb_node;
         struct rb_node *parent = NULL;
         struct thread *th;
 
@@ -392,14 +416,14 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
          * so most of the time we dont have to look up
          * the full rbtree:
          */
-        th = machine->last_match;
+        th = threads->last_match;
         if (th != NULL) {
                 if (th->tid == tid) {
                         machine__update_thread_pid(machine, th, pid);
                         return thread__get(th);
                 }
 
-                machine->last_match = NULL;
+                threads->last_match = NULL;
         }
 
         while (*p != NULL) {
@@ -407,7 +431,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                 th = rb_entry(parent, struct thread, rb_node);
 
                 if (th->tid == tid) {
-                        machine->last_match = th;
+                        threads->last_match = th;
                         machine__update_thread_pid(machine, th, pid);
                         return thread__get(th);
                 }
@@ -424,7 +448,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
         th = thread__new(pid, tid);
         if (th != NULL) {
                 rb_link_node(&th->rb_node, parent, p);
-                rb_insert_color(&th->rb_node, &machine->threads);
+                rb_insert_color(&th->rb_node, &threads->entries);
 
                 /*
                  * We have to initialize map_groups separately
@@ -435,7 +459,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                  * leader and that would screwed the rb tree.
                  */
                 if (thread__init_map_groups(th, machine)) {
-                        rb_erase_init(&th->rb_node, &machine->threads);
+                        rb_erase_init(&th->rb_node, &threads->entries);
                         RB_CLEAR_NODE(&th->rb_node);
                         thread__put(th);
                         return NULL;
@@ -444,8 +468,8 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
                  * It is now in the rbtree, get a ref
                  */
                 thread__get(th);
-                machine->last_match = th;
-                ++machine->nr_threads;
+                threads->last_match = th;
+                ++threads->nr;
         }
 
         return th;
@@ -453,27 +477,30 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
 {
-        return ____machine__findnew_thread(machine, pid, tid, true);
+        return ____machine__findnew_thread(machine, machine__threads(machine, tid), pid, tid, true);
 }
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
                                        pid_t tid)
 {
+        struct threads *threads = machine__threads(machine, tid);
         struct thread *th;
 
-        pthread_rwlock_wrlock(&machine->threads_lock);
+        down_write(&threads->lock);
         th = __machine__findnew_thread(machine, pid, tid);
-        pthread_rwlock_unlock(&machine->threads_lock);
+        up_write(&threads->lock);
         return th;
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
                                     pid_t tid)
 {
+        struct threads *threads = machine__threads(machine, tid);
         struct thread *th;
-        pthread_rwlock_rdlock(&machine->threads_lock);
-        th =  ____machine__findnew_thread(machine, pid, tid, false);
-        pthread_rwlock_unlock(&machine->threads_lock);
+
+        down_read(&threads->lock);
+        th =  ____machine__findnew_thread(machine, threads, pid, tid, false);
+        up_read(&threads->lock);
         return th;
 }
 
@@ -565,7 +592,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 {
         struct dso *dso;
 
-        pthread_rwlock_wrlock(&machine->dsos.lock);
+        down_write(&machine->dsos.lock);
 
         dso = __dsos__find(&machine->dsos, m->name, true);
         if (!dso) {
@@ -579,7 +606,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 
         dso__get(dso);
 out_unlock:
-        pthread_rwlock_unlock(&machine->dsos.lock);
+        up_write(&machine->dsos.lock);
         return dso;
 }
 
@@ -720,21 +747,25 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 
 size_t machine__fprintf(struct machine *machine, FILE *fp)
 {
-        size_t ret;
         struct rb_node *nd;
+        size_t ret;
+        int i;
 
-        pthread_rwlock_rdlock(&machine->threads_lock);
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
 
-        ret = fprintf(fp, "Threads: %u\n", machine->nr_threads);
+                down_read(&threads->lock);
 
-        for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-                struct thread *pos = rb_entry(nd, struct thread, rb_node);
+                ret = fprintf(fp, "Threads: %u\n", threads->nr);
 
-                ret += thread__fprintf(pos, fp);
-        }
+                for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+                        struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
-        pthread_rwlock_unlock(&machine->threads_lock);
+                        ret += thread__fprintf(pos, fp);
+                }
 
+                up_read(&threads->lock);
+        }
         return ret;
 }
 
@@ -1293,7 +1324,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                 struct dso *kernel = NULL;
                 struct dso *dso;
 
-                pthread_rwlock_rdlock(&machine->dsos.lock);
+                down_read(&machine->dsos.lock);
 
                 list_for_each_entry(dso, &machine->dsos.head, node) {
 
@@ -1323,7 +1354,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
                         break;
                 }
 
-                pthread_rwlock_unlock(&machine->dsos.lock);
+                up_read(&machine->dsos.lock);
 
                 if (kernel == NULL)
                         kernel = machine__findnew_dso(machine, kmmap_prefix);
@@ -1480,23 +1511,25 @@ out_problem:
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
-        if (machine->last_match == th)
-                machine->last_match = NULL;
+        struct threads *threads = machine__threads(machine, th->tid);
+
+        if (threads->last_match == th)
+                threads->last_match = NULL;
 
         BUG_ON(refcount_read(&th->refcnt) == 0);
         if (lock)
-                pthread_rwlock_wrlock(&machine->threads_lock);
-        rb_erase_init(&th->rb_node, &machine->threads);
+                down_write(&threads->lock);
+        rb_erase_init(&th->rb_node, &threads->entries);
         RB_CLEAR_NODE(&th->rb_node);
-        --machine->nr_threads;
+        --threads->nr;
         /*
          * Move it first to the dead_threads list, then drop the reference,
          * if this is the last reference, then the thread__delete destructor
          * will be called and we will remove it from the dead_threads list.
          */
-        list_add_tail(&th->node, &machine->dead_threads);
+        list_add_tail(&th->node, &threads->dead);
         if (lock)
-                pthread_rwlock_unlock(&machine->threads_lock);
+                up_write(&threads->lock);
         thread__put(th);
 }
 
@@ -1680,6 +1713,26 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
         return mi;
 }
 
+static char *callchain_srcline(struct map *map, struct symbol *sym, u64 ip)
+{
+        char *srcline = NULL;
+
+        if (!map || callchain_param.key == CCKEY_FUNCTION)
+                return srcline;
+
+        srcline = srcline__tree_find(&map->dso->srclines, ip);
+        if (!srcline) {
+                bool show_sym = false;
+                bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+
+                srcline = get_srcline(map->dso, map__rip_2objdump(map, ip),
+                                      sym, show_sym, show_addr, ip);
+                srcline__tree_insert(&map->dso->srclines, ip, srcline);
+        }
+
+        return srcline;
+}
+
 struct iterations {
         int nr_loop_iter;
         u64 cycles;
@@ -1699,6 +1752,7 @@ static int add_callchain_ip(struct thread *thread,
         struct addr_location al;
         int nr_loop_iter = 0;
         u64 iter_cycles = 0;
+        const char *srcline = NULL;
 
         al.filtered = 0;
         al.sym = NULL;
@@ -1754,9 +1808,10 @@ static int add_callchain_ip(struct thread *thread,
                 iter_cycles = iter->cycles;
         }
 
+        srcline = callchain_srcline(al.map, al.sym, al.addr);
         return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
                                        branch, flags, nr_loop_iter,
-                                       iter_cycles, branch_from);
+                                       iter_cycles, branch_from, srcline);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -2069,15 +2124,54 @@ check_calls:
         return 0;
 }
 
+static int append_inlines(struct callchain_cursor *cursor,
+                          struct map *map, struct symbol *sym, u64 ip)
+{
+        struct inline_node *inline_node;
+        struct inline_list *ilist;
+        u64 addr;
+        int ret = 1;
+
+        if (!symbol_conf.inline_name || !map || !sym)
+                return ret;
+
+        addr = map__rip_2objdump(map, ip);
+
+        inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
+        if (!inline_node) {
+                inline_node = dso__parse_addr_inlines(map->dso, addr, sym);
+                if (!inline_node)
+                        return ret;
+                inlines__tree_insert(&map->dso->inlined_nodes, inline_node);
+        }
+
+        list_for_each_entry(ilist, &inline_node->val, list) {
+                ret = callchain_cursor_append(cursor, ip, map,
+                                              ilist->symbol, false,
+                                              NULL, 0, 0, 0, ilist->srcline);
+
+                if (ret != 0)
+                        return ret;
+        }
+
+        return ret;
+}
+
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
         struct callchain_cursor *cursor = arg;
+        const char *srcline = NULL;
 
         if (symbol_conf.hide_unresolved && entry->sym == NULL)
                 return 0;
+
+        if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
+                return 0;
+
+        srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
         return callchain_cursor_append(cursor, entry->ip,
                                        entry->map, entry->sym,
-                                       false, NULL, 0, 0, 0);
+                                       false, NULL, 0, 0, 0, srcline);
 }
 
 static int thread__resolve_callchain_unwind(struct thread *thread,
@@ -2110,7 +2204,7 @@ int thread__resolve_callchain(struct thread *thread,
 {
         int ret = 0;
 
-        callchain_cursor_reset(&callchain_cursor);
+        callchain_cursor_reset(cursor);
 
         if (callchain_param.order == ORDER_CALLEE) {
                 ret = thread__resolve_callchain_sample(thread, cursor,
@@ -2141,21 +2235,26 @@ int machine__for_each_thread(struct machine *machine,
                              int (*fn)(struct thread *thread, void *p),
                              void *priv)
 {
+        struct threads *threads;
         struct rb_node *nd;
         struct thread *thread;
         int rc = 0;
+        int i;
 
-        for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-                thread = rb_entry(nd, struct thread, rb_node);
-                rc = fn(thread, priv);
-                if (rc != 0)
-                        return rc;
-        }
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                threads = &machine->threads[i];
+                for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+                        thread = rb_entry(nd, struct thread, rb_node);
+                        rc = fn(thread, priv);
+                        if (rc != 0)
+                                return rc;
+                }
 
-        list_for_each_entry(thread, &machine->dead_threads, node) {
-                rc = fn(thread, priv);
-                if (rc != 0)
-                        return rc;
+                list_for_each_entry(thread, &threads->dead, node) {
+                        rc = fn(thread, priv);
+                        if (rc != 0)
+                                return rc;
+                }
         }
         return rc;
 }
@@ -2184,12 +2283,16 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
                                   struct target *target, struct thread_map *threads,
                                   perf_event__handler_t process, bool data_mmap,
-                                  unsigned int proc_map_timeout)
+                                  unsigned int proc_map_timeout,
+                                  unsigned int nr_threads_synthesize)
 {
         if (target__has_task(target))
                 return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
         else if (target__has_cpu(target))
-                return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout);
+                return perf_event__synthesize_threads(tool, process,
+                                                      machine, data_mmap,
+                                                      proc_map_timeout,
+                                                      nr_threads_synthesize);
         /* command specified */
         return 0;
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index d551aa80a59b..5ce860b64c74 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -7,6 +7,7 @@
 #include "map.h"
 #include "dso.h"
 #include "event.h"
+#include "rwsem.h"
 
 struct addr_location;
 struct branch_stack;
@@ -24,6 +25,17 @@ extern const char *ref_reloc_sym_names[];
 
 struct vdso_info;
 
+#define THREADS__TABLE_BITS     8
+#define THREADS__TABLE_SIZE     (1 << THREADS__TABLE_BITS)
+
+struct threads {
+        struct rb_root    entries;
+        struct rw_semaphore lock;
+        unsigned int      nr;
+        struct list_head  dead;
+        struct thread     *last_match;
+};
+
 struct machine {
         struct rb_node    rb_node;
         pid_t             pid;
@@ -31,11 +43,7 @@ struct machine {
         bool              comm_exec;
         bool              kptr_restrict_warned;
         char              *root_dir;
-        struct rb_root    threads;
-        pthread_rwlock_t  threads_lock;
-        unsigned int      nr_threads;
-        struct list_head  dead_threads;
-        struct thread     *last_match;
+        struct threads    threads[THREADS__TABLE_SIZE];
         struct vdso_info  *vdso_info;
         struct perf_env   *env;
         struct dsos       dsos;
@@ -49,6 +57,12 @@ struct machine {
         };
 };
 
+static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
+{
+        /* Cast it to handle tid == -1 */
+        return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
+}
+
 static inline
 struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
 {
@@ -244,15 +258,18 @@ int machines__for_each_thread(struct machines *machines,
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
                                   struct target *target, struct thread_map *threads,
                                   perf_event__handler_t process, bool data_mmap,
-                                  unsigned int proc_map_timeout);
+                                  unsigned int proc_map_timeout,
+                                  unsigned int nr_threads_synthesize);
 static inline
 int machine__synthesize_threads(struct machine *machine, struct target *target,
                                 struct thread_map *threads, bool data_mmap,
-                                unsigned int proc_map_timeout)
+                                unsigned int proc_map_timeout,
+                                unsigned int nr_threads_synthesize)
 {
         return __machine__synthesize_threads(machine, NULL, target, threads,
                                              perf_event__process, data_mmap,
-                                             proc_map_timeout);
+                                             proc_map_timeout,
+                                             nr_threads_synthesize);
 }
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4e7bd2750122..8fe57031e1a8 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -419,7 +419,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
         if (map && map->dso) {
                 srcline = get_srcline(map->dso,
                                       map__rip_2objdump(map, addr), NULL,
-                                      true, true);
+                                      true, true, addr);
                 if (srcline != SRCLINE_UNKNOWN)
                         ret = fprintf(fp, "%s%s", prefix, srcline);
                 free_srcline(srcline);
@@ -489,7 +489,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 static void maps__init(struct maps *maps)
 {
         maps->entries = RB_ROOT;
-        pthread_rwlock_init(&maps->lock, NULL);
+        init_rwsem(&maps->lock);
 }
 
 void map_groups__init(struct map_groups *mg, struct machine *machine)
@@ -518,9 +518,9 @@ static void __maps__purge(struct maps *maps)
 
 static void maps__exit(struct maps *maps)
 {
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
         __maps__purge(maps);
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 void map_groups__exit(struct map_groups *mg)
@@ -587,7 +587,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
         struct symbol *sym;
         struct rb_node *nd;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
                 struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -603,7 +603,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 
         sym = NULL;
 out:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return sym;
 }
 
@@ -639,7 +639,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
         size_t printed = 0;
         struct rb_node *nd;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
                 struct map *pos = rb_entry(nd, struct map, rb_node);
@@ -651,7 +651,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
                 }
         }
 
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
 
         return printed;
 }
@@ -683,7 +683,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
         struct rb_node *next;
         int err = 0;
 
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
 
         root = &maps->entries;
         next = rb_first(root);
@@ -751,7 +751,7 @@ put_map:
 
         err = 0;
 out:
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
         return err;
 }
 
@@ -772,7 +772,7 @@ int map_groups__clone(struct thread *thread,
         struct map *map;
         struct maps *maps = &parent->maps[type];
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (map = maps__first(maps); map; map = map__next(map)) {
                 struct map *new = map__clone(map);
@@ -789,7 +789,7 @@ int map_groups__clone(struct thread *thread,
 
         err = 0;
 out_unlock:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return err;
 }
 
@@ -816,9 +816,9 @@ static void __maps__insert(struct maps *maps, struct map *map)
 
 void maps__insert(struct maps *maps, struct map *map)
 {
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
         __maps__insert(maps, map);
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 static void __maps__remove(struct maps *maps, struct map *map)
@@ -829,9 +829,9 @@ static void __maps__remove(struct maps *maps, struct map *map)
 
 void maps__remove(struct maps *maps, struct map *map)
 {
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
         __maps__remove(maps, map);
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 struct map *maps__find(struct maps *maps, u64 ip)
@@ -839,7 +839,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
         struct rb_node **p, *parent = NULL;
         struct map *m;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         p = &maps->entries.rb_node;
         while (*p != NULL) {
@@ -855,7 +855,7 @@ struct map *maps__find(struct maps *maps, u64 ip)
 
         m = NULL;
 out:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return m;
 }
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 1fb9b8589adc..edeb7291c8e1 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -10,6 +10,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include "rwsem.h"
 
 enum map_type {
         MAP__FUNCTION = 0,
@@ -62,7 +63,7 @@ struct kmap {
 
 struct maps {
         struct rb_root   entries;
-        pthread_rwlock_t lock;
+        struct rw_semaphore lock;
 };
 
 struct map_groups {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
new file mode 100644
index 000000000000..1ddc3d1d0147
--- /dev/null
+++ b/tools/perf/util/metricgroup.c
@@ -0,0 +1,492 @@
+/*
+ * Copyright (c) 2017, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+/* Manage metrics and groups of metrics from JSON files */
+
+#include "metricgroup.h"
+#include "evlist.h"
+#include "strbuf.h"
+#include "pmu.h"
+#include "expr.h"
+#include "rblist.h"
+#include <string.h>
+#include <stdbool.h>
+#include <errno.h>
+#include "pmu-events/pmu-events.h"
+#include "strlist.h"
+#include <assert.h>
+#include <ctype.h>
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+                                         struct perf_evsel *evsel,
+                                         bool create)
+{
+        struct rb_node *nd;
+        struct metric_event me = {
+                .evsel = evsel
+        };
+
+        if (!metric_events)
+                return NULL;
+
+        nd = rblist__find(metric_events, &me);
+        if (nd)
+                return container_of(nd, struct metric_event, nd);
+        if (create) {
+                rblist__add_node(metric_events, &me);
+                nd = rblist__find(metric_events, &me);
+                if (nd)
+                        return container_of(nd, struct metric_event, nd);
+        }
+        return NULL;
+}
+
+static int metric_event_cmp(struct rb_node *rb_node, const void *entry)
+{
+        struct metric_event *a = container_of(rb_node,
+                                              struct metric_event,
+                                              nd);
+        const struct metric_event *b = entry;
+
+        if (a->evsel == b->evsel)
+                return 0;
+        if ((char *)a->evsel < (char *)b->evsel)
+                return -1;
+        return +1;
+}
+
+static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused,
+                                        const void *entry)
+{
+        struct metric_event *me = malloc(sizeof(struct metric_event));
+
+        if (!me)
+                return NULL;
+        memcpy(me, entry, sizeof(struct metric_event));
+        me->evsel = ((struct metric_event *)entry)->evsel;
+        INIT_LIST_HEAD(&me->head);
+        return &me->nd;
+}
+
+static void metricgroup__rblist_init(struct rblist *metric_events)
+{
+        rblist__init(metric_events);
+        metric_events->node_cmp = metric_event_cmp;
+        metric_events->node_new = metric_event_new;
+}
+
+struct egroup {
+        struct list_head nd;
+        int idnum;
+        const char **ids;
+        const char *metric_name;
+        const char *metric_expr;
+};
+
+static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
+                                     const char **ids,
+                                     int idnum,
+                                     struct perf_evsel **metric_events)
+{
+        struct perf_evsel *ev, *start = NULL;
+        int ind = 0;
+
+        evlist__for_each_entry (perf_evlist, ev) {
+                if (!strcmp(ev->name, ids[ind])) {
+                        metric_events[ind] = ev;
+                        if (ind == 0)
+                                start = ev;
+                        if (++ind == idnum) {
+                                metric_events[ind] = NULL;
+                                return start;
+                        }
+                } else {
+                        ind = 0;
+                        start = NULL;
+                }
+        }
+        /*
+         * This can happen when an alias expands to multiple
+         * events, like for uncore events.
+         * We don't support this case for now.
+         */
+        return NULL;
+}
+
+static int metricgroup__setup_events(struct list_head *groups,
+                                     struct perf_evlist *perf_evlist,
+                                     struct rblist *metric_events_list)
+{
+        struct metric_event *me;
+        struct metric_expr *expr;
+        int i = 0;
+        int ret = 0;
+        struct egroup *eg;
+        struct perf_evsel *evsel;
+
+        list_for_each_entry (eg, groups, nd) {
+                struct perf_evsel **metric_events;
+
+                metric_events = calloc(sizeof(void *), eg->idnum + 1);
+                if (!metric_events) {
+                        ret = -ENOMEM;
+                        break;
+                }
+                evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
+                                   metric_events);
+                if (!evsel) {
+                        pr_debug("Cannot resolve %s: %s\n",
+                                        eg->metric_name, eg->metric_expr);
+                        continue;
+                }
+                for (i = 0; i < eg->idnum; i++)
+                        metric_events[i]->collect_stat = true;
+                me = metricgroup__lookup(metric_events_list, evsel, true);
+                if (!me) {
+                        ret = -ENOMEM;
+                        break;
+                }
+                expr = malloc(sizeof(struct metric_expr));
+                if (!expr) {
+                        ret = -ENOMEM;
+                        break;
+                }
+                expr->metric_expr = eg->metric_expr;
+                expr->metric_name = eg->metric_name;
+                expr->metric_events = metric_events;
+                list_add(&expr->nd, &me->head);
+        }
+        return ret;
+}
+
+static bool match_metric(const char *n, const char *list)
+{
+        int len;
+        char *m;
+
+        if (!list)
+                return false;
+        if (!strcmp(list, "all"))
+                return true;
+        if (!n)
+                return !strcasecmp(list, "No_group");
+        len = strlen(list);
+        m = strcasestr(n, list);
+        if (!m)
+                return false;
+        if ((m == n || m[-1] == ';' || m[-1] == ' ') &&
+            (m[len] == 0 || m[len] == ';'))
+                return true;
+        return false;
+}
+
+struct mep {
+        struct rb_node nd;
+        const char *name;
+        struct strlist *metrics;
+};
+
+static int mep_cmp(struct rb_node *rb_node, const void *entry)
+{
+        struct mep *a = container_of(rb_node, struct mep, nd);
+        struct mep *b = (struct mep *)entry;
+
+        return strcmp(a->name, b->name);
+}
+
+static struct rb_node *mep_new(struct rblist *rl __maybe_unused,
+                                        const void *entry)
+{
+        struct mep *me = malloc(sizeof(struct mep));
+
+        if (!me)
+                return NULL;
+        memcpy(me, entry, sizeof(struct mep));
+        me->name = strdup(me->name);
+        if (!me->name)
+                goto out_me;
+        me->metrics = strlist__new(NULL, NULL);
+        if (!me->metrics)
+                goto out_name;
+        return &me->nd;
+out_name:
+        free((char *)me->name);
+out_me:
+        free(me);
+        return NULL;
+}
+
+static struct mep *mep_lookup(struct rblist *groups, const char *name)
+{
+        struct rb_node *nd;
+        struct mep me = {
+                .name = name
+        };
+        nd = rblist__find(groups, &me);
+        if (nd)
+                return container_of(nd, struct mep, nd);
+        rblist__add_node(groups, &me);
+        nd = rblist__find(groups, &me);
+        if (nd)
+                return container_of(nd, struct mep, nd);
+        return NULL;
+}
+
+static void mep_delete(struct rblist *rl __maybe_unused,
+                       struct rb_node *nd)
+{
+        struct mep *me = container_of(nd, struct mep, nd);
+
+        strlist__delete(me->metrics);
+        free((void *)me->name);
+        free(me);
+}
+
+static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
+{
+        struct str_node *sn;
+        int n = 0;
+
+        strlist__for_each_entry (sn, metrics) {
+                if (raw)
+                        printf("%s%s", n > 0 ? " " : "", sn->s);
+                else
+                        printf("  %s\n", sn->s);
+                n++;
+        }
+        if (raw)
+                putchar('\n');
+}
+
+void metricgroup__print(bool metrics, bool metricgroups, char *filter,
+                        bool raw)
+{
+        struct pmu_events_map *map = perf_pmu__find_map(NULL);
+        struct pmu_event *pe;
+        int i;
+        struct rblist groups;
+        struct rb_node *node, *next;
+        struct strlist *metriclist = NULL;
+
+        if (!map)
+                return;
+
+        if (!metricgroups) {
+                metriclist = strlist__new(NULL, NULL);
+                if (!metriclist)
+                        return;
+        }
+
+        rblist__init(&groups);
+        groups.node_new = mep_new;
+        groups.node_cmp = mep_cmp;
+        groups.node_delete = mep_delete;
+        for (i = 0; ; i++) {
+                const char *g;
+                pe = &map->table[i];
+
+                if (!pe->name && !pe->metric_group && !pe->metric_name)
+                        break;
+                if (!pe->metric_expr)
+                        continue;
+                g = pe->metric_group;
+                if (!g && pe->metric_name) {
+                        if (pe->name)
+                                continue;
+                        g = "No_group";
+                }
+                if (g) {
+                        char *omg;
+                        char *mg = strdup(g);
+
+                        if (!mg)
+                                return;
+                        omg = mg;
+                        while ((g = strsep(&mg, ";")) != NULL) {
+                                struct mep *me;
+                                char *s;
+
+                                if (*g == 0)
+                                        g = "No_group";
+                                while (isspace(*g))
+                                        g++;
+                                if (filter && !strstr(g, filter))
+                                        continue;
+                                if (raw)
+                                        s = (char *)pe->metric_name;
+                                else {
+                                        if (asprintf(&s, "%s\n\t[%s]",
+                                                     pe->metric_name, pe->desc) < 0)
+                                                return;
+                                }
+
+                                if (!s)
+                                        continue;
+
+                                if (!metricgroups) {
+                                        strlist__add(metriclist, s);
+                                } else {
+                                        me = mep_lookup(&groups, g);
+                                        if (!me)
+                                                continue;
+                                        strlist__add(me->metrics, s);
+                                }
+                        }
+                        free(omg);
+                }
+        }
+
+        if (metricgroups && !raw)
+                printf("\nMetric Groups:\n\n");
+        else if (metrics && !raw)
+                printf("\nMetrics:\n\n");
+
+        for (node = rb_first(&groups.entries); node; node = next) {
+                struct mep *me = container_of(node, struct mep, nd);
+
+                if (metricgroups)
+                        printf("%s%s%s", me->name, metrics ? ":" : "", raw ? " " : "\n");
+                if (metrics)
+                        metricgroup__print_strlist(me->metrics, raw);
+                next = rb_next(node);
+                rblist__remove_node(&groups, node);
+        }
+        if (!metricgroups)
+                metricgroup__print_strlist(metriclist, raw);
+        strlist__delete(metriclist);
+}
+
+static int metricgroup__add_metric(const char *metric, struct strbuf *events,
+                                   struct list_head *group_list)
+{
+        struct pmu_events_map *map = perf_pmu__find_map(NULL);
+        struct pmu_event *pe;
+        int ret = -EINVAL;
+        int i, j;
+
+        if (!map)
+                return 0;
+
+        for (i = 0; ; i++) {
+                pe = &map->table[i];
+
+                if (!pe->name && !pe->metric_group && !pe->metric_name)
+                        break;
+                if (!pe->metric_expr)
+                        continue;
+                if (match_metric(pe->metric_group, metric) ||
+                    match_metric(pe->metric_name, metric)) {
+                        const char **ids;
+                        int idnum;
+                        struct egroup *eg;
+
+                        pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
+
+                        if (expr__find_other(pe->metric_expr,
+                                             NULL, &ids, &idnum) < 0)
+                                continue;
+                        if (events->len > 0)
+                                strbuf_addf(events, ",");
+                        for (j = 0; j < idnum; j++) {
+                                pr_debug("found event %s\n", ids[j]);
+                                strbuf_addf(events, "%s%s",
+                                        j == 0 ? "{" : ",",
+                                        ids[j]);
+                        }
+                        strbuf_addf(events, "}:W");
+
+                        eg = malloc(sizeof(struct egroup));
+                        if (!eg) {
+                                ret = -ENOMEM;
+                                break;
+                        }
+                        eg->ids = ids;
+                        eg->idnum = idnum;
+                        eg->metric_name = pe->metric_name;
+                        eg->metric_expr = pe->metric_expr;
+                        list_add_tail(&eg->nd, group_list);
+                        ret = 0;
+                }
+        }
+        return ret;
+}
+
+static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
+                                        struct list_head *group_list)
+{
+        char *llist, *nlist, *p;
+        int ret = -EINVAL;
+
+        nlist = strdup(list);
+        if (!nlist)
+                return -ENOMEM;
+        llist = nlist;
+
+        strbuf_init(events, 100);
+        strbuf_addf(events, "%s", "");
+
+        while ((p = strsep(&llist, ",")) != NULL) {
+                ret = metricgroup__add_metric(p, events, group_list);
+                if (ret == -EINVAL) {
+                        fprintf(stderr, "Cannot find metric or group `%s'\n",
+                                        p);
+                        break;
+                }
+        }
+        free(nlist);
+        return ret;
+}
+
+static void metricgroup__free_egroups(struct list_head *group_list)
+{
+        struct egroup *eg, *egtmp;
+        int i;
+
+        list_for_each_entry_safe (eg, egtmp, group_list, nd) {
+                for (i = 0; i < eg->idnum; i++)
+                        free((char *)eg->ids[i]);
+                free(eg->ids);
+                free(eg);
+        }
+}
+
+int metricgroup__parse_groups(const struct option *opt,
+                           const char *str,
+                           struct rblist *metric_events)
+{
+        struct parse_events_error parse_error;
+        struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value;
+        struct strbuf extra_events;
+        LIST_HEAD(group_list);
+        int ret;
+
+        if (metric_events->nr_entries == 0)
+                metricgroup__rblist_init(metric_events);
+        ret = metricgroup__add_metric_list(str, &extra_events, &group_list);
+        if (ret)
+                return ret;
+        pr_debug("adding %s\n", extra_events.buf);
+        memset(&parse_error, 0, sizeof(struct parse_events_error));
+        ret = parse_events(perf_evlist, extra_events.buf, &parse_error);
+        if (ret) {
+                parse_events_print_error(&parse_error, extra_events.buf);
+                goto out;
+        }
+        strbuf_release(&extra_events);
+        ret = metricgroup__setup_events(&group_list, perf_evlist,
+                                        metric_events);
+out:
+        metricgroup__free_egroups(&group_list);
+        return ret;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
new file mode 100644
index 000000000000..06854e125ee7
--- /dev/null
+++ b/tools/perf/util/metricgroup.h
@@ -0,0 +1,31 @@
+#ifndef METRICGROUP_H
+#define METRICGROUP_H 1
+
+#include "linux/list.h"
+#include "rblist.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "strbuf.h"
+
+struct metric_event {
+        struct rb_node nd;
+        struct perf_evsel *evsel;
+        struct list_head head; /* list of metric_expr */
+};
+
+struct metric_expr {
+        struct list_head nd;
+        const char *metric_expr;
+        const char *metric_name;
+        struct perf_evsel **metric_events;
+};
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+                                         struct perf_evsel *evsel,
+                                         bool create);
+int metricgroup__parse_groups(const struct option *opt,
+                        const char *str,
+                        struct rblist *metric_events);
+
+void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+#endif
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
new file mode 100644
index 000000000000..91531a7c8fbf
--- /dev/null
+++ b/tools/perf/util/mmap.c
@@ -0,0 +1,348 @@
+/*
+ * Copyright (C) 2011-2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from evlist.c builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <sys/mman.h>
+#include <inttypes.h>
+#include <asm/bug.h>
+#include "debug.h"
+#include "event.h"
+#include "mmap.h"
+#include "util.h" /* page_size */
+
+size_t perf_mmap__mmap_len(struct perf_mmap *map)
+{
+        return map->mask + 1 + page_size;
+}
+
+/* When check_messup is true, 'end' must points to a good entry */
+static union perf_event *perf_mmap__read(struct perf_mmap *map,
+                                         u64 *startp, u64 end)
+{
+        unsigned char *data = map->base + page_size;
+        union perf_event *event = NULL;
+        int diff = end - *startp;
+
+        if (diff >= (int)sizeof(event->header)) {
+                size_t size;
+
+                event = (union perf_event *)&data[*startp & map->mask];
+                size = event->header.size;
+
+                if (size < sizeof(event->header) || diff < (int)size)
+                        return NULL;
+
+                /*
+                 * Event straddles the mmap boundary -- header should always
+                 * be inside due to u64 alignment of output.
+                 */
+                if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
+                        unsigned int offset = *startp;
+                        unsigned int len = min(sizeof(*event), size), cpy;
+                        void *dst = map->event_copy;
+
+                        do {
+                                cpy = min(map->mask + 1 - (offset & map->mask), len);
+                                memcpy(dst, &data[offset & map->mask], cpy);
+                                offset += cpy;
+                                dst += cpy;
+                                len -= cpy;
+                        } while (len);
+
+                        event = (union perf_event *)map->event_copy;
+                }
+
+                *startp += size;
+        }
+
+        return event;
+}
+
+/*
+ * legacy interface for mmap read.
+ * Don't use it. Use perf_mmap__read_event().
+ */
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
+{
+        u64 head;
+
+        /*
+         * Check if event was unmapped due to a POLLHUP/POLLERR.
+         */
+        if (!refcount_read(&map->refcnt))
+                return NULL;
+
+        head = perf_mmap__read_head(map);
+
+        return perf_mmap__read(map, &map->prev, head);
+}
+
+/*
+ * Read event from ring buffer one by one.
+ * Return one event for each call.
+ *
+ * Usage:
+ * perf_mmap__read_init()
+ * while(event = perf_mmap__read_event()) {
+ *      //process the event
+ *      perf_mmap__consume()
+ * }
+ * perf_mmap__read_done()
+ */
+union perf_event *perf_mmap__read_event(struct perf_mmap *map,
+                                        bool overwrite,
+                                        u64 *startp, u64 end)
+{
+        union perf_event *event;
+
+        /*
+         * Check if event was unmapped due to a POLLHUP/POLLERR.
+         */
+        if (!refcount_read(&map->refcnt))
+                return NULL;
+
+        if (startp == NULL)
+                return NULL;
+
+        /* non-overwirte doesn't pause the ringbuffer */
+        if (!overwrite)
+                end = perf_mmap__read_head(map);
+
+        event = perf_mmap__read(map, startp, end);
+
+        if (!overwrite)
+                map->prev = *startp;
+
+        return event;
+}
+
+static bool perf_mmap__empty(struct perf_mmap *map)
+{
+        return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base;
+}
+
+void perf_mmap__get(struct perf_mmap *map)
+{
+        refcount_inc(&map->refcnt);
+}
+
+void perf_mmap__put(struct perf_mmap *map)
+{
+        BUG_ON(map->base && refcount_read(&map->refcnt) == 0);
+
+        if (refcount_dec_and_test(&map->refcnt))
+                perf_mmap__munmap(map);
+}
+
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite)
+{
+        if (!overwrite) {
+                u64 old = map->prev;
+
+                perf_mmap__write_tail(map, old);
+        }
+
+        if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map))
+                perf_mmap__put(map);
+}
+
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+                               struct auxtrace_mmap_params *mp __maybe_unused,
+                               void *userpg __maybe_unused,
+                               int fd __maybe_unused)
+{
+        return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_unused,
+                                       off_t auxtrace_offset __maybe_unused,
+                                       unsigned int auxtrace_pages __maybe_unused,
+                                       bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused,
+                                          struct perf_evlist *evlist __maybe_unused,
+                                          int idx __maybe_unused,
+                                          bool per_cpu __maybe_unused)
+{
+}
+
+void perf_mmap__munmap(struct perf_mmap *map)
+{
+        if (map->base != NULL) {
+                munmap(map->base, perf_mmap__mmap_len(map));
+                map->base = NULL;
+                map->fd = -1;
+                refcount_set(&map->refcnt, 0);
+        }
+        auxtrace_mmap__munmap(&map->auxtrace_mmap);
+}
+
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
+{
+        /*
+         * The last one will be done at perf_evlist__mmap_consume(), so that we
+         * make sure we don't prevent tools from consuming every last event in
+         * the ring buffer.
+         *
+         * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+         * anymore, but the last events for it are still in the ring buffer,
+         * waiting to be consumed.
+         *
+         * Tools can chose to ignore this at their own discretion, but the
+         * evlist layer can't just drop it when filtering events in
+         * perf_evlist__filter_pollfd().
+         */
+        refcount_set(&map->refcnt, 2);
+        map->prev = 0;
+        map->mask = mp->mask;
+        map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+                         MAP_SHARED, fd, 0);
+        if (map->base == MAP_FAILED) {
+                pr_debug2("failed to mmap perf event ring buffer, error %d\n",
+                          errno);
+                map->base = NULL;
+                return -1;
+        }
+        map->fd = fd;
+
+        if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
+                                &mp->auxtrace_mp, map->base, fd))
+                return -1;
+
+        return 0;
+}
+
+static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+{
+        struct perf_event_header *pheader;
+        u64 evt_head = head;
+        int size = mask + 1;
+
+        pr_debug2("overwrite_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
+        pheader = (struct perf_event_header *)(buf + (head & mask));
+        *start = head;
+        while (true) {
+                if (evt_head - head >= (unsigned int)size) {
+                        pr_debug("Finished reading overwrite ring buffer: rewind\n");
+                        if (evt_head - head > (unsigned int)size)
+                                evt_head -= pheader->size;
+                        *end = evt_head;
+                        return 0;
+                }
+
+                pheader = (struct perf_event_header *)(buf + (evt_head & mask));
+
+                if (pheader->size == 0) {
+                        pr_debug("Finished reading overwrite ring buffer: get start\n");
+                        *end = evt_head;
+                        return 0;
+                }
+
+                evt_head += pheader->size;
+                pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
+        }
+        WARN_ONCE(1, "Shouldn't get here\n");
+        return -1;
+}
+
+/*
+ * Report the start and end of the available data in ringbuffer
+ */
+int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
+                         u64 *startp, u64 *endp)
+{
+        u64 head = perf_mmap__read_head(md);
+        u64 old = md->prev;
+        unsigned char *data = md->base + page_size;
+        unsigned long size;
+
+        *startp = overwrite ? head : old;
+        *endp = overwrite ? old : head;
+
+        if (*startp == *endp)
+                return -EAGAIN;
+
+        size = *endp - *startp;
+        if (size > (unsigned long)(md->mask) + 1) {
+                if (!overwrite) {
+                        WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
+
+                        md->prev = head;
+                        perf_mmap__consume(md, overwrite);
+                        return -EAGAIN;
+                }
+
+                /*
+                 * Backward ring buffer is full. We still have a chance to read
+                 * most of data from it.
+                 */
+                if (overwrite_rb_find_range(data, md->mask, head, startp, endp))
+                        return -EINVAL;
+        }
+
+        return 0;
+}
+
+int perf_mmap__push(struct perf_mmap *md, bool overwrite,
+                    void *to, int push(void *to, void *buf, size_t size))
+{
+        u64 head = perf_mmap__read_head(md);
+        u64 end, start;
+        unsigned char *data = md->base + page_size;
+        unsigned long size;
+        void *buf;
+        int rc = 0;
+
+        rc = perf_mmap__read_init(md, overwrite, &start, &end);
+        if (rc < 0)
+                return (rc == -EAGAIN) ? 0 : -1;
+
+        size = end - start;
+
+        if ((start & md->mask) + size != (end & md->mask)) {
+                buf = &data[start & md->mask];
+                size = md->mask + 1 - (start & md->mask);
+                start += size;
+
+                if (push(to, buf, size) < 0) {
+                        rc = -1;
+                        goto out;
+                }
+        }
+
+        buf = &data[start & md->mask];
+        size = end - start;
+        start += size;
+
+        if (push(to, buf, size) < 0) {
+                rc = -1;
+                goto out;
+        }
+
+        md->prev = head;
+        perf_mmap__consume(md, overwrite);
+out:
+        return rc;
+}
+
+/*
+ * Mandatory for overwrite mode
+ * The direction of overwrite mode is backward.
+ * The last perf_mmap__read() will set tail to map->prev.
+ * Need to correct the map->prev to head which is the end of next read.
+ */
+void perf_mmap__read_done(struct perf_mmap *map)
+{
+        map->prev = perf_mmap__read_head(map);
+}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
new file mode 100644
index 000000000000..ec7d3a24e276
--- /dev/null
+++ b/tools/perf/util/mmap.h
@@ -0,0 +1,101 @@
+#ifndef __PERF_MMAP_H
+#define __PERF_MMAP_H 1
+
+#include <linux/compiler.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <stdbool.h>
+#include "auxtrace.h"
+#include "event.h"
+
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
+struct perf_mmap {
+        void             *base;
+        int              mask;
+        int              fd;
+        refcount_t       refcnt;
+        u64              prev;
+        struct auxtrace_mmap auxtrace_mmap;
+        char             event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+};
+
+/*
+ * State machine of bkw_mmap_state:
+ *
+ *                     .________________(forbid)_____________.
+ *                     |                                     V
+ * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ *                     ^  ^              |   ^               |
+ *                     |  |__(forbid)____/   |___(forbid)___/|
+ *                     |                                     |
+ *                      \_________________(3)_______________/
+ *
+ * NOTREADY     : Backward ring buffers are not ready
+ * RUNNING      : Backward ring buffers are recording
+ * DATA_PENDING : We are required to collect data from backward ring buffers
+ * EMPTY        : We have collected data from backward ring buffers.
+ *
+ * (0): Setup backward ring buffer
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum bkw_mmap_state {
+        BKW_MMAP_NOTREADY,
+        BKW_MMAP_RUNNING,
+        BKW_MMAP_DATA_PENDING,
+        BKW_MMAP_EMPTY,
+};
+
+struct mmap_params {
+        int                         prot, mask;
+        struct auxtrace_mmap_params auxtrace_mp;
+};
+
+int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd);
+void perf_mmap__munmap(struct perf_mmap *map);
+
+void perf_mmap__get(struct perf_mmap *map);
+void perf_mmap__put(struct perf_mmap *map);
+
+void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
+
+static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
+{
+        struct perf_event_mmap_page *pc = mm->base;
+        u64 head = READ_ONCE(pc->data_head);
+        rmb();
+        return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
+{
+        struct perf_event_mmap_page *pc = md->base;
+
+        /*
+         * ensure all reads are done before we write the tail out.
+         */
+        mb();
+        pc->data_tail = tail;
+}
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
+
+union perf_event *perf_mmap__read_event(struct perf_mmap *map,
+                                        bool overwrite,
+                                        u64 *startp, u64 end);
+
+int perf_mmap__push(struct perf_mmap *md, bool backward,
+                    void *to, int push(void *to, void *buf, size_t size));
+
+size_t perf_mmap__mmap_len(struct perf_mmap *map);
+
+int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
+                         u64 *startp, u64 *endp);
+void perf_mmap__read_done(struct perf_mmap *map);
+#endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index a58e91197729..5be021701f34 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -11,6 +11,7 @@
 #include "event.h"
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <fcntl.h>
 #include <limits.h>
 #include <sched.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 05d82601c9a6..760558dcfd18 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -9,9 +9,10 @@
 #ifndef __PERF_NAMESPACES_H
 #define __PERF_NAMESPACES_H
 
-#include "../perf.h"
-#include <linux/list.h>
+#include <sys/types.h>
+#include <linux/perf_event.h>
 #include <linux/refcount.h>
+#include <linux/types.h>
 
 struct namespaces_event;
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 8e09fd2d842f..bad9e0296e9a 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -157,9 +157,8 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve
 }
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
-                          struct perf_sample *sample, u64 file_offset)
+                          u64 timestamp, u64 file_offset)
 {
-        u64 timestamp = sample->time;
         struct ordered_event *oevent;
 
         if (!timestamp || timestamp == ~0ULL)
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 96e5292d88e2..8c7a2948593e 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -45,7 +45,7 @@ struct ordered_events {
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
-                          struct perf_sample *sample, u64 file_offset);
+                          u64 timestamp, u64 file_offset);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
 int ordered_events__flush(struct ordered_events *oe, enum oe_flush how);
 void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 56694e3409ea..34589c427e52 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -4,6 +4,9 @@
 #include <dirent.h>
 #include <errno.h>
 #include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include <sys/param.h>
 #include "term.h"
 #include "../perf.h"
@@ -29,6 +32,7 @@
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
+#include "metricgroup.h"
 
 #define MAX_NAME_LEN 100
 
@@ -1115,6 +1119,7 @@ do {								\
         INIT_LIST_HEAD(&__t->list);                             \
         __t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;   \
         __t->val.__name = __val;                                \
+        __t->weak       = term->weak;                           \
         list_add_tail(&__t->list, head_terms);                  \
 } while (0)
 
@@ -1220,11 +1225,17 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
         struct perf_pmu_info info;
         struct perf_pmu *pmu;
         struct perf_evsel *evsel;
+        struct parse_events_error *err = parse_state->error;
         LIST_HEAD(config_terms);
 
         pmu = perf_pmu__find(name);
-        if (!pmu)
+        if (!pmu) {
+                if (asprintf(&err->str,
+                                "Cannot find PMU `%s'. Missing kernel support?",
+                                name) < 0)
+                        err->str = NULL;
                 return -EINVAL;
+        }
 
         if (pmu->default_config) {
                 memcpy(&attr, pmu->default_config,
@@ -1368,6 +1379,7 @@ struct event_modifier {
         int exclude_GH;
         int sample_read;
         int pinned;
+        int weak;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -1386,6 +1398,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 
         int exclude = eu | ek | eh;
         int exclude_GH = evsel ? evsel->exclude_GH : 0;
+        int weak = 0;
 
         memset(mod, 0, sizeof(*mod));
 
@@ -1423,6 +1436,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
                         sample_read = 1;
                 } else if (*str == 'D') {
                         pinned = 1;
+                } else if (*str == 'W') {
+                        weak = 1;
                 } else
                         break;
 
@@ -1453,6 +1468,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
         mod->exclude_GH = exclude_GH;
         mod->sample_read = sample_read;
         mod->pinned = pinned;
+        mod->weak = weak;
 
         return 0;
 }
@@ -1466,7 +1482,7 @@ static int check_modifier(char *str)
         char *p = str;
 
         /* The sizeof includes 0 byte as well. */
-        if (strlen(str) > (sizeof("ukhGHpppPSDI") - 1))
+        if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1))
                 return -1;
 
         while (*p) {
@@ -1506,6 +1522,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
                 evsel->exclude_GH          = mod.exclude_GH;
                 evsel->sample_read         = mod.sample_read;
                 evsel->precise_max         = mod.precise_max;
+                evsel->weak_group          = mod.weak;
 
                 if (perf_evsel__is_group_leader(evsel))
                         evsel->attr.pinned = mod.pinned;
@@ -1728,8 +1745,8 @@ static int get_term_width(void)
         return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
 }
 
-static void parse_events_print_error(struct parse_events_error *err,
-                                     const char *event)
+void parse_events_print_error(struct parse_events_error *err,
+                              const char *event)
 {
         const char *str = "invalid or unsupported event: ";
         char _buf[MAX_WIDTH];
@@ -1784,8 +1801,6 @@ static void parse_events_print_error(struct parse_events_error *err,
                 zfree(&err->str);
                 zfree(&err->help);
         }
-
-        fprintf(stderr, "Run 'perf list' for a list of valid events\n");
 }
 
 #undef MAX_WIDTH
@@ -1797,8 +1812,10 @@ int parse_events_option(const struct option *opt, const char *str,
         struct parse_events_error err = { .idx = 0, };
         int ret = parse_events(evlist, str, &err);
 
-        if (ret)
+        if (ret) {
                 parse_events_print_error(&err, str);
+                fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+        }
 
         return ret;
 }
@@ -2376,6 +2393,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
         print_tracepoint_events(NULL, NULL, name_only);
 
         print_sdt_events(NULL, NULL, name_only);
+
+        metricgroup__print(true, true, NULL, name_only);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
@@ -2395,6 +2414,7 @@ static int new_term(struct parse_events_term **_term,
 
         *term = *temp;
         INIT_LIST_HEAD(&term->list);
+        term->weak = false;
 
         switch (term->type_val) {
         case PARSE_EVENTS__TERM_TYPE_NUM:
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index eed50b54bab3..88108cd11b4c 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -101,6 +101,9 @@ struct parse_events_term {
         /* error string indexes for within parsed string */
         int err_term;
         int err_val;
+
+        /* Coming from implicit alias */
+        bool weak;
 };
 
 struct parse_events_error {
@@ -203,6 +206,9 @@ int is_valid_tracepoint(const char *event_string);
 int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
+void parse_events_print_error(struct parse_events_error *err,
+                              const char *event);
+
 #ifdef HAVE_LIBELF_SUPPORT
 /*
  * If the probe point starts with '%',
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 6680e4fb7967..655ecff636a8 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -5,6 +5,7 @@
 %option stack
 %option bison-locations
 %option yylineno
+%option reject
 
 %{
 #include <errno.h>
@@ -178,7 +179,7 @@ name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
 name_minus      [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term    [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
-modifier_event  [ukhpPGHSDI]+
+modifier_event  [ukhpPGHSDIW]+
 modifier_bp     [rwx]{1,3}
 
 %%
@@ -305,6 +306,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy                                           { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time                                   { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 bpf-output                                      { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
         /*
@@ -339,8 +341,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}               { return value(yyscanner, 16); }
 
 {modifier_event}        { return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}            { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}            { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object}            { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}            { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); }
 {name}                  { return pmu_str_check(yyscanner); }
 "/"                     { BEGIN(config); return '/'; }
 -                       { return '-'; }
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 933f5c6bffb4..ca56ba2dd3da 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -18,6 +18,7 @@
 #include <stdio.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <dirent.h>
 #include <unistd.h>
 
 static char bad_path[] = "/bad-path/";
@@ -77,3 +78,16 @@ bool is_regular_file(const char *file)
 
         return S_ISREG(st.st_mode);
 }
+
+/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
+bool is_directory(const char *base_path, const struct dirent *dent)
+{
+        char path[PATH_MAX];
+        struct stat st;
+
+        sprintf(path, "%s/%s", base_path, dent->d_name);
+        if (stat(path, &st))
+                return false;
+
+        return S_ISDIR(st.st_mode);
+}
diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h
index 14a254ada7eb..f014f905df50 100644
--- a/tools/perf/util/path.h
+++ b/tools/perf/util/path.h
@@ -2,9 +2,12 @@
 #ifndef _PERF_PATH_H
 #define _PERF_PATH_H
 
+struct dirent;
+
 int path__join(char *bf, size_t size, const char *path1, const char *path2);
 int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3);
 
 bool is_regular_file(const char *file);
+bool is_directory(const char *base_path, const struct dirent *dent);
 
 #endif /* _PERF_PATH_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b10b35a63138..57e38fdf0b34 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,6 +3,7 @@
 #include <linux/compiler.h>
 #include <sys/types.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -11,6 +12,7 @@
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
+#include <regex.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
@@ -404,6 +406,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
                         parse_events_terms__purge(&list);
                         return ret;
                 }
+                /*
+                 * Weak terms don't override command line options,
+                 * which we don't want for implicit terms in aliases.
+                 */
+                cloned->weak = true;
                 list_add_tail(&cloned->list, &list);
         }
         list_splice(&list, terms);
@@ -531,26 +538,46 @@ static bool pmu_is_uncore(const char *name)
 }
 
 /*
+ *  PMU CORE devices have different name other than cpu in sysfs on some
+ *  platforms. looking for possible sysfs files to identify as core device.
+ */
+static int is_pmu_core(const char *name)
+{
+        struct stat st;
+        char path[PATH_MAX];
+        const char *sysfs = sysfs__mountpoint();
+
+        if (!sysfs)
+                return 0;
+
+        /* Look for cpu sysfs (x86 and others) */
+        scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
+        if ((stat(path, &st) == 0) &&
+                        (strncmp(name, "cpu", strlen("cpu")) == 0))
+                return 1;
+
+        /* Look for cpu sysfs (specific to arm) */
+        scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
+                                sysfs, name);
+        if (stat(path, &st) == 0)
+                return 1;
+
+        return 0;
+}
+
+/*
  * Return the CPU id as a raw string.
  *
  * Each architecture should provide a more precise id string that
  * can be use to match the architecture's "mapfile".
  */
-char * __weak get_cpuid_str(void)
+char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
         return NULL;
 }
 
-/*
- * From the pmu_events_map, find the table of PMU events that corresponds
- * to the current running CPU. Then, add all PMU events from that table
- * as aliases.
- */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 {
-        int i;
-        struct pmu_events_map *map;
-        struct pmu_event *pe;
         char *cpuid;
         static bool printed;
 
@@ -558,39 +585,97 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
         if (cpuid)
                 cpuid = strdup(cpuid);
         if (!cpuid)
-                cpuid = get_cpuid_str();
+                cpuid = get_cpuid_str(pmu);
         if (!cpuid)
-                return;
+                return NULL;
 
         if (!printed) {
                 pr_debug("Using CPUID %s\n", cpuid);
                 printed = true;
         }
+        return cpuid;
+}
+
+struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
+{
+        struct pmu_events_map *map;
+        char *cpuid = perf_pmu__getcpuid(pmu);
+        int i;
+
+        /* on some platforms which uses cpus map, cpuid can be NULL for
+         * PMUs other than CORE PMUs.
+         */
+        if (!cpuid)
+                return NULL;
 
         i = 0;
-        while (1) {
+        for (;;) {
+                regex_t re;
+                regmatch_t pmatch[1];
+                int match;
+
                 map = &pmu_events_map[i++];
-                if (!map->table)
-                        goto out;
+                if (!map->table) {
+                        map = NULL;
+                        break;
+                }
 
-                if (!strcmp(map->cpuid, cpuid))
+                if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
+                        /* Warn unable to generate match particular string. */
+                        pr_info("Invalid regular expression %s\n", map->cpuid);
                         break;
+                }
+
+                match = !regexec(&re, cpuid, 1, pmatch, 0);
+                regfree(&re);
+                if (match) {
+                        size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+                        /* Verify the entire string matched. */
+                        if (match_len == strlen(cpuid))
+                                break;
+                }
         }
+        free(cpuid);
+        return map;
+}
+
+/*
+ * From the pmu_events_map, find the table of PMU events that corresponds
+ * to the current running CPU. Then, add all PMU events from that table
+ * as aliases.
+ */
+static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
+{
+        int i;
+        struct pmu_events_map *map;
+        struct pmu_event *pe;
+        const char *name = pmu->name;
+
+        map = perf_pmu__find_map(pmu);
+        if (!map)
+                return;
 
         /*
          * Found a matching PMU events table. Create aliases
          */
         i = 0;
         while (1) {
-                const char *pname;
 
                 pe = &map->table[i++];
-                if (!pe->name)
+                if (!pe->name) {
+                        if (pe->metric_group || pe->metric_name)
+                                continue;
                         break;
+                }
 
-                pname = pe->pmu ? pe->pmu : "cpu";
-                if (strncmp(pname, name, strlen(pname)))
-                        continue;
+                if (!is_pmu_core(name)) {
+                        /* check for uncore devices */
+                        if (pe->pmu == NULL)
+                                continue;
+                        if (strncmp(pe->pmu, name, strlen(pe->pmu)))
+                                continue;
+                }
 
                 /* need type casts to override 'const' */
                 __perf_pmu__new_alias(head, NULL, (char *)pe->name,
@@ -600,9 +685,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
                                 (char *)pe->metric_expr,
                                 (char *)pe->metric_name);
         }
-
-out:
-        free(cpuid);
 }
 
 struct perf_event_attr * __weak
@@ -635,21 +717,20 @@ static struct perf_pmu *pmu_lookup(const char *name)
         if (pmu_aliases(name, &aliases))
                 return NULL;
 
-        pmu_add_cpu_aliases(&aliases, name);
         pmu = zalloc(sizeof(*pmu));
         if (!pmu)
                 return NULL;
 
         pmu->cpus = pmu_cpumask(name);
-
+        pmu->name = strdup(name);
+        pmu->type = type;
         pmu->is_uncore = pmu_is_uncore(name);
+        pmu_add_cpu_aliases(&aliases, pmu);
 
         INIT_LIST_HEAD(&pmu->format);
         INIT_LIST_HEAD(&pmu->aliases);
         list_splice(&format, &pmu->format);
         list_splice(&aliases, &pmu->aliases);
-        pmu->name = strdup(name);
-        pmu->type = type;
         list_add_tail(&pmu->list, &pmus);
 
         pmu->default_config = perf_pmu__get_default_config(pmu);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index eca99435f4a0..76fecec7b3f9 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -92,4 +92,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
+struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c
index 779e35c9e566..23e367063446 100644
--- a/tools/perf/util/print_binary.c
+++ b/tools/perf/util/print_binary.c
@@ -3,40 +3,42 @@
 #include <linux/log2.h>
 #include "sane_ctype.h"
 
-void print_binary(unsigned char *data, size_t len,
-                  size_t bytes_per_line, print_binary_t printer,
-                  void *extra)
+int binary__fprintf(unsigned char *data, size_t len,
+                    size_t bytes_per_line, binary__fprintf_t printer,
+                    void *extra, FILE *fp)
 {
         size_t i, j, mask;
+        int printed = 0;
 
         if (!printer)
-                return;
+                return 0;
 
         bytes_per_line = roundup_pow_of_two(bytes_per_line);
         mask = bytes_per_line - 1;
 
-        printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+        printed += printer(BINARY_PRINT_DATA_BEGIN, 0, extra, fp);
         for (i = 0; i < len; i++) {
                 if ((i & mask) == 0) {
-                        printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
-                        printer(BINARY_PRINT_ADDR, i, extra);
+                        printed += printer(BINARY_PRINT_LINE_BEGIN, -1, extra, fp);
+                        printed += printer(BINARY_PRINT_ADDR, i, extra, fp);
                 }
 
-                printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+                printed += printer(BINARY_PRINT_NUM_DATA, data[i], extra, fp);
 
                 if (((i & mask) == mask) || i == len - 1) {
                         for (j = 0; j < mask-(i & mask); j++)
-                                printer(BINARY_PRINT_NUM_PAD, -1, extra);
+                                printed += printer(BINARY_PRINT_NUM_PAD, -1, extra, fp);
 
-                        printer(BINARY_PRINT_SEP, i, extra);
+                        printer(BINARY_PRINT_SEP, i, extra, fp);
                         for (j = i & ~mask; j <= i; j++)
-                                printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+                                printed += printer(BINARY_PRINT_CHAR_DATA, data[j], extra, fp);
                         for (j = 0; j < mask-(i & mask); j++)
-                                printer(BINARY_PRINT_CHAR_PAD, i, extra);
-                        printer(BINARY_PRINT_LINE_END, -1, extra);
+                                printed += printer(BINARY_PRINT_CHAR_PAD, i, extra, fp);
+                        printed += printer(BINARY_PRINT_LINE_END, -1, extra, fp);
                 }
         }
-        printer(BINARY_PRINT_DATA_END, -1, extra);
+        printed += printer(BINARY_PRINT_DATA_END, -1, extra, fp);
+        return printed;
 }
 
 int is_printable_array(char *p, unsigned int len)
diff --git a/tools/perf/util/print_binary.h b/tools/perf/util/print_binary.h
index 2be3075e2b05..2a1554afc957 100644
--- a/tools/perf/util/print_binary.h
+++ b/tools/perf/util/print_binary.h
@@ -3,6 +3,7 @@
 #define PERF_PRINT_BINARY_H
 
 #include <stddef.h>
+#include <stdio.h>
 
 enum binary_printer_ops {
         BINARY_PRINT_DATA_BEGIN,
@@ -17,12 +18,19 @@ enum binary_printer_ops {
         BINARY_PRINT_DATA_END,
 };
 
-typedef void (*print_binary_t)(enum binary_printer_ops op,
-                               unsigned int val, void *extra);
+typedef int (*binary__fprintf_t)(enum binary_printer_ops op,
+                                 unsigned int val, void *extra, FILE *fp);
 
-void print_binary(unsigned char *data, size_t len,
-                  size_t bytes_per_line, print_binary_t printer,
-                  void *extra);
+int binary__fprintf(unsigned char *data, size_t len,
+                    size_t bytes_per_line, binary__fprintf_t printer,
+                    void *extra, FILE *fp);
+
+static inline void print_binary(unsigned char *data, size_t len,
+                                size_t bytes_per_line, binary__fprintf_t printer,
+                                void *extra)
+{
+        binary__fprintf(data, len, bytes_per_line, printer, extra, stdout);
+}
 
 int is_printable_array(char *p, unsigned int len);
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b7aaf9b2294d..e1dbc9821617 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1325,27 +1325,30 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
 {
         char *ptr;
 
-        ptr = strchr(*arg, ':');
+        ptr = strpbrk_esc(*arg, ":");
         if (ptr) {
                 *ptr = '\0';
                 if (!pev->sdt && !is_c_func_name(*arg))
                         goto ng_name;
-                pev->group = strdup(*arg);
+                pev->group = strdup_esc(*arg);
                 if (!pev->group)
                         return -ENOMEM;
                 *arg = ptr + 1;
         } else
                 pev->group = NULL;
-        if (!pev->sdt && !is_c_func_name(*arg)) {
+
+        pev->event = strdup_esc(*arg);
+        if (pev->event == NULL)
+                return -ENOMEM;
+
+        if (!pev->sdt && !is_c_func_name(pev->event)) {
+                zfree(&pev->event);
 ng_name:
+                zfree(&pev->group);
                 semantic_error("%s is bad for event name -it must "
                                "follow C symbol-naming rule.\n", *arg);
                 return -EINVAL;
         }
-        pev->event = strdup(*arg);
-        if (pev->event == NULL)
-                return -ENOMEM;
-
         return 0;
 }
 
@@ -1373,7 +1376,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
                         arg++;
         }
 
-        ptr = strpbrk(arg, ";=@+%");
+        ptr = strpbrk_esc(arg, ";=@+%");
         if (pev->sdt) {
                 if (ptr) {
                         if (*ptr != '@') {
@@ -1387,7 +1390,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
                                 pev->target = build_id_cache__origname(tmp);
                                 free(tmp);
                         } else
-                                pev->target = strdup(ptr + 1);
+                                pev->target = strdup_esc(ptr + 1);
                         if (!pev->target)
                                 return -ENOMEM;
                         *ptr = '\0';
@@ -1421,13 +1424,14 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
          *
          * Otherwise, we consider arg to be a function specification.
          */
-        if (!strpbrk(arg, "+@%") && (ptr = strpbrk(arg, ";:")) != NULL) {
+        if (!strpbrk_esc(arg, "+@%")) {
+                ptr = strpbrk_esc(arg, ";:");
                 /* This is a file spec if it includes a '.' before ; or : */
-                if (memchr(arg, '.', ptr - arg))
+                if (ptr && memchr(arg, '.', ptr - arg))
                         file_spec = true;
         }
 
-        ptr = strpbrk(arg, ";:+@%");
+        ptr = strpbrk_esc(arg, ";:+@%");
         if (ptr) {
                 nc = *ptr;
                 *ptr++ = '\0';
@@ -1436,7 +1440,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
         if (arg[0] == '\0')
                 tmp = NULL;
         else {
-                tmp = strdup(arg);
+                tmp = strdup_esc(arg);
                 if (tmp == NULL)
                         return -ENOMEM;
         }
@@ -1469,12 +1473,12 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
                 arg = ptr;
                 c = nc;
                 if (c == ';') { /* Lazy pattern must be the last part */
-                        pp->lazy_line = strdup(arg);
+                        pp->lazy_line = strdup(arg); /* let leave escapes */
                         if (pp->lazy_line == NULL)
                                 return -ENOMEM;
                         break;
                 }
-                ptr = strpbrk(arg, ";:+@%");
+                ptr = strpbrk_esc(arg, ";:+@%");
                 if (ptr) {
                         nc = *ptr;
                         *ptr++ = '\0';
@@ -1501,7 +1505,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
                                 semantic_error("SRC@SRC is not allowed.\n");
                                 return -EINVAL;
                         }
-                        pp->file = strdup(arg);
+                        pp->file = strdup_esc(arg);
                         if (pp->file == NULL)
                                 return -ENOMEM;
                         break;
@@ -2573,7 +2577,8 @@ int show_perf_probe_events(struct strfilter *filter)
 }
 
 static int get_new_event_name(char *buf, size_t len, const char *base,
-                              struct strlist *namelist, bool allow_suffix)
+                              struct strlist *namelist, bool ret_event,
+                              bool allow_suffix)
 {
         int i, ret;
         char *p, *nbase;
@@ -2584,13 +2589,13 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
         if (!nbase)
                 return -ENOMEM;
 
-        /* Cut off the dot suffixes (e.g. .const, .isra)*/
-        p = strchr(nbase, '.');
+        /* Cut off the dot suffixes (e.g. .const, .isra) and version suffixes */
+        p = strpbrk(nbase, ".@");
         if (p && p != nbase)
                 *p = '\0';
 
         /* Try no suffix number */
-        ret = e_snprintf(buf, len, "%s", nbase);
+        ret = e_snprintf(buf, len, "%s%s", nbase, ret_event ? "__return" : "");
         if (ret < 0) {
                 pr_debug("snprintf() failed: %d\n", ret);
                 goto out;
@@ -2625,6 +2630,14 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 
 out:
         free(nbase);
+
+        /* Final validation */
+        if (ret >= 0 && !is_c_func_name(buf)) {
+                pr_warning("Internal error: \"%s\" is an invalid event name.\n",
+                           buf);
+                ret = -EINVAL;
+        }
+
         return ret;
 }
 
@@ -2681,8 +2694,8 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
                 group = PERFPROBE_GROUP;
 
         /* Get an unused new event name */
-        ret = get_new_event_name(buf, 64, event,
-                                 namelist, allow_suffix);
+        ret = get_new_event_name(buf, 64, event, namelist,
+                                 tev->point.retprobe, allow_suffix);
         if (ret < 0)
                 return ret;
 
@@ -2792,16 +2805,40 @@ static int find_probe_functions(struct map *map, char *name,
         int found = 0;
         struct symbol *sym;
         struct rb_node *tmp;
+        const char *norm, *ver;
+        char *buf = NULL;
+        bool cut_version = true;
 
         if (map__load(map) < 0)
                 return 0;
 
+        /* If user gives a version, don't cut off the version from symbols */
+        if (strchr(name, '@'))
+                cut_version = false;
+
         map__for_each_symbol(map, sym, tmp) {
-                if (strglobmatch(sym->name, name)) {
+                norm = arch__normalize_symbol_name(sym->name);
+                if (!norm)
+                        continue;
+
+                if (cut_version) {
+                        /* We don't care about default symbol or not */
+                        ver = strchr(norm, '@');
+                        if (ver) {
+                                buf = strndup(norm, ver - norm);
+                                if (!buf)
+                                        return -ENOMEM;
+                                norm = buf;
+                        }
+                }
+
+                if (strglobmatch(norm, name)) {
                         found++;
                         if (syms && found < probe_conf.max_probes)
                                 syms[found - 1] = sym;
                 }
+                if (buf)
+                        zfree(&buf);
         }
 
         return found;
@@ -2847,7 +2884,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
          * same name but different addresses, this lists all the symbols.
          */
         num_matched_functions = find_probe_functions(map, pp->function, syms);
-        if (num_matched_functions == 0) {
+        if (num_matched_functions <= 0) {
                 pr_err("Failed to find symbol %s in %s\n", pp->function,
                         pev->target ? : "kernel");
                 ret = -ENOENT;
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index cdf8d83a484c..4ae1123c6794 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -15,6 +15,7 @@
  *
  */
 #include <errno.h>
+#include <fcntl.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/uio.h>
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e66dc495809a..7aa0ea64544e 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,8 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+util/memswap.c
+util/mmap.c
 util/namespaces.c
 ../lib/bitmap.c
 ../lib/find_bit.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 8e49d9cafcfc..b1e999bd21ef 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -864,7 +864,7 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
                                          &pages, &overwrite))
                 return NULL;
 
-        if (perf_evlist__mmap(evlist, pages, overwrite) < 0) {
+        if (perf_evlist__mmap(evlist, pages) < 0) {
                 PyErr_SetFromErrno(PyExc_OSError);
                 return NULL;
         }
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index 7d8972b33f6b..a920f702a74d 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -144,7 +144,8 @@ struct __name##_sorted *__name = __name##_sorted__new
                                   __ilist->rblist.nr_entries)
 
 /* For 'struct machine->threads' */
-#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine)                    \
-        DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads)
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)       \
+        DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries,     \
+                                  __machine->threads[hash_bucket].nr)
 
 #endif /* _PERF_RESORT_RB_H_ */
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
index 0dfe27d99458..0efc3258c648 100644
--- a/tools/perf/util/rblist.c
+++ b/tools/perf/util/rblist.c
@@ -101,16 +101,21 @@ void rblist__init(struct rblist *rblist)
         return;
 }
 
+void rblist__exit(struct rblist *rblist)
+{
+        struct rb_node *pos, *next = rb_first(&rblist->entries);
+
+        while (next) {
+                pos = next;
+                next = rb_next(pos);
+                rblist__remove_node(rblist, pos);
+        }
+}
+
 void rblist__delete(struct rblist *rblist)
 {
         if (rblist != NULL) {
-                struct rb_node *pos, *next = rb_first(&rblist->entries);
-
-                while (next) {
-                        pos = next;
-                        next = rb_next(pos);
-                        rblist__remove_node(rblist, pos);
-                }
+                rblist__exit(rblist);
                 free(rblist);
         }
 }
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
index 4c8638a22571..76df15c27f5f 100644
--- a/tools/perf/util/rblist.h
+++ b/tools/perf/util/rblist.h
@@ -29,6 +29,7 @@ struct rblist {
 };
 
 void rblist__init(struct rblist *rblist);
+void rblist__exit(struct rblist *rblist);
 void rblist__delete(struct rblist *rblist);
 int rblist__add_node(struct rblist *rblist, const void *new_entry);
 void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node);
diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c
new file mode 100644
index 000000000000..5e52e7baa7b6
--- /dev/null
+++ b/tools/perf/util/rwsem.c
@@ -0,0 +1,32 @@
+#include "util.h"
+#include "rwsem.h"
+
+int init_rwsem(struct rw_semaphore *sem)
+{
+        return pthread_rwlock_init(&sem->lock, NULL);
+}
+
+int exit_rwsem(struct rw_semaphore *sem)
+{
+        return pthread_rwlock_destroy(&sem->lock);
+}
+
+int down_read(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_rdlock(&sem->lock);
+}
+
+int up_read(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}
+
+int down_write(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_wrlock(&sem->lock);
+}
+
+int up_write(struct rw_semaphore *sem)
+{
+        return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+}
diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h
new file mode 100644
index 000000000000..94565ad4d494
--- /dev/null
+++ b/tools/perf/util/rwsem.h
@@ -0,0 +1,19 @@
+#ifndef _PERF_RWSEM_H
+#define _PERF_RWSEM_H
+
+#include <pthread.h>
+
+struct rw_semaphore {
+        pthread_rwlock_t lock;
+};
+
+int init_rwsem(struct rw_semaphore *sem);
+int exit_rwsem(struct rw_semaphore *sem);
+
+int down_read(struct rw_semaphore *sem);
+int up_read(struct rw_semaphore *sem);
+
+int down_write(struct rw_semaphore *sem);
+int up_write(struct rw_semaphore *sem);
+
+#endif /* _PERF_RWSEM_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index c7187f067d31..ea070883c593 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -43,7 +43,6 @@
 #include "../db-export.h"
 #include "../thread-stack.h"
 #include "../trace-event.h"
-#include "../machine.h"
 #include "../call-path.h"
 #include "thread_map.h"
 #include "cpumap.h"
@@ -500,6 +499,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
                         PyLong_FromUnsignedLongLong(sample->time));
         pydict_set_item_string_decref(dict_sample, "period",
                         PyLong_FromUnsignedLongLong(sample->period));
+        pydict_set_item_string_decref(dict_sample, "phys_addr",
+                        PyLong_FromUnsignedLongLong(sample->phys_addr));
         set_sample_read_in_dict(dict_sample, sample, evsel);
         pydict_set_item_string_decref(dict, "sample", dict_sample);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index da55081aefc6..c71ced7db152 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -27,20 +27,19 @@
 
 static int perf_session__deliver_event(struct perf_session *session,
                                        union perf_event *event,
-                                       struct perf_sample *sample,
                                        struct perf_tool *tool,
                                        u64 file_offset);
 
 static int perf_session__open(struct perf_session *session)
 {
-        struct perf_data_file *file = session->file;
+        struct perf_data *data = session->data;
 
         if (perf_session__read_header(session) < 0) {
                 pr_err("incompatible file format (rerun with -v to learn more)\n");
                 return -1;
         }
 
-        if (perf_data_file__is_pipe(file))
+        if (perf_data__is_pipe(data))
                 return 0;
 
         if (perf_header__has_feat(&session->header, HEADER_STAT))
@@ -107,21 +106,14 @@ static void perf_session__set_comm_exec(struct perf_session *session)
 static int ordered_events__deliver_event(struct ordered_events *oe,
                                          struct ordered_event *event)
 {
-        struct perf_sample sample;
         struct perf_session *session = container_of(oe, struct perf_session,
                                                     ordered_events);
-        int ret = perf_evlist__parse_sample(session->evlist, event->event, &sample);
-
-        if (ret) {
-                pr_err("Can't parse sample, err = %d\n", ret);
-                return ret;
-        }
 
-        return perf_session__deliver_event(session, event->event, &sample,
+        return perf_session__deliver_event(session, event->event,
                                            session->tool, event->file_offset);
 }
 
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
                                        bool repipe, struct perf_tool *tool)
 {
         struct perf_session *session = zalloc(sizeof(*session));
@@ -135,13 +127,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
         machines__init(&session->machines);
         ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 
-        if (file) {
-                if (perf_data_file__open(file))
+        if (data) {
+                if (perf_data__open(data))
                         goto out_delete;
 
-                session->file = file;
+                session->data = data;
 
-                if (perf_data_file__is_read(file)) {
+                if (perf_data__is_read(data)) {
                         if (perf_session__open(session) < 0)
                                 goto out_close;
 
@@ -149,7 +141,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
                          * set session attributes that are present in perf.data
                          * but not in pipe-mode.
                          */
-                        if (!file->is_pipe) {
+                        if (!data->is_pipe) {
                                 perf_session__set_id_hdr_size(session);
                                 perf_session__set_comm_exec(session);
                         }
@@ -158,7 +150,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
                 session->machines.host.env = &perf_env;
         }
 
-        if (!file || perf_data_file__is_write(file)) {
+        if (!data || perf_data__is_write(data)) {
                 /*
                  * In O_RDONLY mode this will be performed when reading the
                  * kernel MMAP event, in perf_event__process_mmap().
@@ -171,7 +163,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
          * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is
          * processed, so perf_evlist__sample_id_all is not meaningful here.
          */
-        if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps &&
+        if ((!data || !data->is_pipe) && tool && tool->ordering_requires_timestamps &&
             tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
                 dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
                 tool->ordered_events = false;
@@ -180,7 +172,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
         return session;
 
  out_close:
-        perf_data_file__close(file);
+        perf_data__close(data);
  out_delete:
         perf_session__delete(session);
  out:
@@ -202,8 +194,8 @@ void perf_session__delete(struct perf_session *session)
         perf_session__delete_threads(session);
         perf_env__exit(&session->header.env);
         machines__exit(&session->machines);
-        if (session->file)
-                perf_data_file__close(session->file);
+        if (session->data)
+                perf_data__close(session->data);
         free(session);
 }
 
@@ -291,8 +283,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
                                        __maybe_unused)
 {
         dump_printf(": unhandled!\n");
-        if (perf_data_file__is_pipe(session->file))
-                skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+        if (perf_data__is_pipe(session->data))
+                skipn(perf_data__fd(session->data), event->auxtrace.size);
         return event->auxtrace.size;
 }
 
@@ -873,9 +865,9 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 }
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-                              struct perf_sample *sample, u64 file_offset)
+                              u64 timestamp, u64 file_offset)
 {
-        return ordered_events__queue(&s->ordered_events, event, sample, file_offset);
+        return ordered_events__queue(&s->ordered_events, event, timestamp, file_offset);
 }
 
 static void callchain__lbr_callstack_printf(struct perf_sample *sample)
@@ -1328,20 +1320,26 @@ static int machines__deliver_event(struct machines *machines,
 
 static int perf_session__deliver_event(struct perf_session *session,
                                        union perf_event *event,
-                                       struct perf_sample *sample,
                                        struct perf_tool *tool,
                                        u64 file_offset)
 {
+        struct perf_sample sample;
         int ret;
 
-        ret = auxtrace__process_event(session, event, sample, tool);
+        ret = perf_evlist__parse_sample(session->evlist, event, &sample);
+        if (ret) {
+                pr_err("Can't parse sample, err = %d\n", ret);
+                return ret;
+        }
+
+        ret = auxtrace__process_event(session, event, &sample, tool);
         if (ret < 0)
                 return ret;
         if (ret > 0)
                 return 0;
 
         return machines__deliver_event(&session->machines, session->evlist,
-                                       event, sample, tool, file_offset);
+                                       event, &sample, tool, file_offset);
 }
 
 static s64 perf_session__process_user_event(struct perf_session *session,
@@ -1350,10 +1348,11 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 {
         struct ordered_events *oe = &session->ordered_events;
         struct perf_tool *tool = session->tool;
-        int fd = perf_data_file__fd(session->file);
+        struct perf_sample sample = { .time = 0, };
+        int fd = perf_data__fd(session->data);
         int err;
 
-        dump_event(session->evlist, event, file_offset, NULL);
+        dump_event(session->evlist, event, file_offset, &sample);
 
         /* These events are processed right away */
         switch (event->header.type) {
@@ -1450,10 +1449,10 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
                 goto out_parse_sample;
         }
 
-        if (perf_data_file__is_pipe(session->file))
+        if (perf_data__is_pipe(session->data))
                 return -1;
 
-        fd = perf_data_file__fd(session->file);
+        fd = perf_data__fd(session->data);
         hdr_sz = sizeof(struct perf_event_header);
 
         if (buf_sz < hdr_sz)
@@ -1495,7 +1494,6 @@ static s64 perf_session__process_event(struct perf_session *session,
 {
         struct perf_evlist *evlist = session->evlist;
         struct perf_tool *tool = session->tool;
-        struct perf_sample sample;
         int ret;
 
         if (session->header.needs_swap)
@@ -1509,21 +1507,19 @@ static s64 perf_session__process_event(struct perf_session *session,
         if (event->header.type >= PERF_RECORD_USER_TYPE_START)
                 return perf_session__process_user_event(session, event, file_offset);
 
-        /*
-         * For all kernel events we get the sample data
-         */
-        ret = perf_evlist__parse_sample(evlist, event, &sample);
-        if (ret)
-                return ret;
-
         if (tool->ordered_events) {
-                ret = perf_session__queue_event(session, event, &sample, file_offset);
+                u64 timestamp = -1ULL;
+
+                ret = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
+                if (ret && ret != -1)
+                        return ret;
+
+                ret = perf_session__queue_event(session, event, timestamp, file_offset);
                 if (ret != -ETIME)
                         return ret;
         }
 
-        return perf_session__deliver_event(session, event, &sample, tool,
-                                           file_offset);
+        return perf_session__deliver_event(session, event, tool, file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1688,7 +1684,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
 {
         struct ordered_events *oe = &session->ordered_events;
         struct perf_tool *tool = session->tool;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         union perf_event *event;
         uint32_t size, cur_size = 0;
         void *buf = NULL;
@@ -1777,7 +1773,8 @@ done:
         err = perf_session__flush_thread_stacks(session);
 out_err:
         free(buf);
-        perf_session__warn_about_errors(session);
+        if (!tool->no_warn)
+                perf_session__warn_about_errors(session);
         ordered_events__free(&session->ordered_events);
         auxtrace__free_events(session);
         return err;
@@ -1829,7 +1826,7 @@ static int __perf_session__process_events(struct perf_session *session,
 {
         struct ordered_events *oe = &session->ordered_events;
         struct perf_tool *tool = session->tool;
-        int fd = perf_data_file__fd(session->file);
+        int fd = perf_data__fd(session->data);
         u64 head, page_offset, file_offset, file_pos, size;
         int err, mmap_prot, mmap_flags, map_idx = 0;
         size_t  mmap_size;
@@ -1850,7 +1847,7 @@ static int __perf_session__process_events(struct perf_session *session,
         if (data_offset + data_size < file_size)
                 file_size = data_offset + data_size;
 
-        ui_progress__init(&prog, file_size, "Processing events...");
+        ui_progress__init_size(&prog, file_size, "Processing events...");
 
         mmap_size = MMAP_SIZE;
         if (mmap_size > file_size) {
@@ -1933,7 +1930,8 @@ out:
         err = perf_session__flush_thread_stacks(session);
 out_err:
         ui_progress__finish();
-        perf_session__warn_about_errors(session);
+        if (!tool->no_warn)
+                perf_session__warn_about_errors(session);
         /*
          * We may switching perf.data output, make ordered_events
          * reusable.
@@ -1946,13 +1944,13 @@ out_err:
 
 int perf_session__process_events(struct perf_session *session)
 {
-        u64 size = perf_data_file__size(session->file);
+        u64 size = perf_data__size(session->data);
         int err;
 
         if (perf_session__register_idle_thread(session) < 0)
                 return -ENOMEM;
 
-        if (!perf_data_file__is_pipe(session->file))
+        if (!perf_data__is_pipe(session->data))
                 err = __perf_session__process_events(session,
                                                      session->header.data_offset,
                                                      session->header.data_size, size);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 41caa098ed15..da40b4b380ca 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -33,13 +33,13 @@ struct perf_session {
         void                    *one_mmap_addr;
         u64                     one_mmap_offset;
         struct ordered_events   ordered_events;
-        struct perf_data_file   *file;
+        struct perf_data        *data;
         struct perf_tool        *tool;
 };
 
 struct perf_tool;
 
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
                                        bool repipe, struct perf_tool *tool);
 void perf_session__delete(struct perf_session *session);
 
@@ -53,7 +53,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 int perf_session__process_events(struct perf_session *session);
 
 int perf_session__queue_event(struct perf_session *s, union perf_event *event,
-                              struct perf_sample *sample, u64 file_offset);
+                              u64 timestamp, u64 file_offset);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
@@ -114,7 +114,7 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 
 extern volatile int session_done;
 
-#define session_done()  ACCESS_ONCE(session_done)
+#define session_done()  READ_ONCE(session_done)
 
 int perf_session__deliver_synth_event(struct perf_session *session,
                                       union perf_event *event,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 84a33f1e9ec9..2da4d0456a03 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -226,6 +226,9 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
         if (sym_l == sym_r)
                 return 0;
 
+        if (sym_l->inlined || sym_r->inlined)
+                return strcmp(sym_l->name, sym_r->name);
+
         if (sym_l->start != sym_r->start)
                 return (int64_t)(sym_r->start - sym_l->start);
 
@@ -284,6 +287,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
                         ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
                                                width - ret,
                                                sym->name);
+                        if (sym->inlined)
+                                ret += repsep_snprintf(bf + ret, size - ret,
+                                                       " (inlined)");
                 }
         } else {
                 size_t len = BITS_PER_LONG / 4;
@@ -330,7 +336,7 @@ char *hist_entry__get_srcline(struct hist_entry *he)
                 return SRCLINE_UNKNOWN;
 
         return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
-                           he->ms.sym, true, true);
+                           he->ms.sym, true, true, he->ip);
 }
 
 static int64_t
@@ -374,7 +380,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
                                            map__rip_2objdump(map,
                                                              left->branch_info->from.al_addr),
                                                          left->branch_info->from.sym,
-                                                         true, true);
+                                                         true, true,
+                                                         left->branch_info->from.al_addr);
         }
         if (!right->branch_info->srcline_from) {
                 struct map *map = right->branch_info->from.map;
@@ -385,7 +392,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
                                              map__rip_2objdump(map,
                                                                right->branch_info->from.al_addr),
                                                      right->branch_info->from.sym,
-                                                     true, true);
+                                                     true, true,
+                                                     right->branch_info->from.al_addr);
         }
         return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
 }
@@ -417,7 +425,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
                                            map__rip_2objdump(map,
                                                              left->branch_info->to.al_addr),
                                                          left->branch_info->from.sym,
-                                                         true, true);
+                                                         true, true,
+                                                         left->branch_info->to.al_addr);
         }
         if (!right->branch_info->srcline_to) {
                 struct map *map = right->branch_info->to.map;
@@ -428,7 +437,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
                                              map__rip_2objdump(map,
                                                                right->branch_info->to.al_addr),
                                                      right->branch_info->to.sym,
-                                                     true, true);
+                                                     true, true,
+                                                     right->branch_info->to.al_addr);
         }
         return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
 }
@@ -459,7 +469,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e)
                 return no_srcfile;
 
         sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
-                         e->ms.sym, false, true, true);
+                         e->ms.sym, false, true, true, e->ip);
         if (!strcmp(sf, SRCLINE_UNKNOWN))
                 return no_srcfile;
         p = strchr(sf, ':');
@@ -2877,10 +2887,10 @@ static int setup_output_list(struct perf_hpp_list *list, char *str)
                         tok; tok = strtok_r(NULL, ", ", &tmp)) {
                 ret = output_field_add(list, tok);
                 if (ret == -EINVAL) {
-                        pr_err("Invalid --fields key: `%s'", tok);
+                        ui__error("Invalid --fields key: `%s'", tok);
                         break;
                 } else if (ret == -ESRCH) {
-                        pr_err("Unknown --fields key: `%s'", tok);
+                        ui__error("Unknown --fields key: `%s'", tok);
                         break;
                 }
         }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b2b55e5149a7..f5901c10a563 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -130,7 +130,6 @@ struct hist_entry {
         };
         char                    *srcline;
         char                    *srcfile;
-        struct inline_node      *inline_node;
         struct symbol           *parent;
         struct branch_info      *branch_info;
         struct hists            *hists;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 4105682afc7a..3c21fd059b64 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -11,7 +11,7 @@
 #include "util/debug.h"
 #include "util/callchain.h"
 #include "srcline.h"
-
+#include "string2.h"
 #include "symbol.h"
 
 bool srcline_full_filename;
@@ -34,28 +34,17 @@ static const char *dso__name(struct dso *dso)
         return dso_name;
 }
 
-static int inline_list__append(char *filename, char *funcname, int line_nr,
-                               struct inline_node *node, struct dso *dso)
+static int inline_list__append(struct symbol *symbol, char *srcline,
+                               struct inline_node *node)
 {
         struct inline_list *ilist;
-        char *demangled;
 
         ilist = zalloc(sizeof(*ilist));
         if (ilist == NULL)
                 return -1;
 
-        ilist->filename = filename;
-        ilist->line_nr = line_nr;
-
-        if (dso != NULL) {
-                demangled = dso__demangle_sym(dso, 0, funcname);
-                if (demangled == NULL) {
-                        ilist->funcname = funcname;
-                } else {
-                        ilist->funcname = demangled;
-                        free(funcname);
-                }
-        }
+        ilist->symbol = symbol;
+        ilist->srcline = srcline;
 
         if (callchain_param.order == ORDER_CALLEE)
                 list_add_tail(&ilist->list, &node->val);
@@ -65,6 +54,65 @@ static int inline_list__append(char *filename, char *funcname, int line_nr,
         return 0;
 }
 
+/* basename version that takes a const input string */
+static const char *gnu_basename(const char *path)
+{
+        const char *base = strrchr(path, '/');
+
+        return base ? base + 1 : path;
+}
+
+static char *srcline_from_fileline(const char *file, unsigned int line)
+{
+        char *srcline;
+
+        if (!file)
+                return NULL;
+
+        if (!srcline_full_filename)
+                file = gnu_basename(file);
+
+        if (asprintf(&srcline, "%s:%u", file, line) < 0)
+                return NULL;
+
+        return srcline;
+}
+
+static struct symbol *new_inline_sym(struct dso *dso,
+                                     struct symbol *base_sym,
+                                     const char *funcname)
+{
+        struct symbol *inline_sym;
+        char *demangled = NULL;
+
+        if (dso) {
+                demangled = dso__demangle_sym(dso, 0, funcname);
+                if (demangled)
+                        funcname = demangled;
+        }
+
+        if (base_sym && strcmp(funcname, base_sym->name) == 0) {
+                /* reuse the real, existing symbol */
+                inline_sym = base_sym;
+                /* ensure that we don't alias an inlined symbol, which could
+                 * lead to double frees in inline_node__delete
+                 */
+                assert(!base_sym->inlined);
+        } else {
+                /* create a fake symbol for the inline frame */
+                inline_sym = symbol__new(base_sym ? base_sym->start : 0,
+                                         base_sym ? base_sym->end : 0,
+                                         base_sym ? base_sym->binding : 0,
+                                         funcname);
+                if (inline_sym)
+                        inline_sym->inlined = 1;
+        }
+
+        free(demangled);
+
+        return inline_sym;
+}
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -208,18 +256,23 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 #define MAX_INLINE_NEST 1024
 
 static int inline_list__append_dso_a2l(struct dso *dso,
-                                       struct inline_node *node)
+                                       struct inline_node *node,
+                                       struct symbol *sym)
 {
         struct a2l_data *a2l = dso->a2l;
-        char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL;
-        char *filename = a2l->filename ? strdup(a2l->filename) : NULL;
+        struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname);
+        char *srcline = NULL;
 
-        return inline_list__append(filename, funcname, a2l->line, node, dso);
+        if (a2l->filename)
+                srcline = srcline_from_fileline(a2l->filename, a2l->line);
+
+        return inline_list__append(inline_sym, srcline, node);
 }
 
 static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line, struct dso *dso,
-                     bool unwind_inlines, struct inline_node *node)
+                     bool unwind_inlines, struct inline_node *node,
+                     struct symbol *sym)
 {
         int ret = 0;
         struct a2l_data *a2l = dso->a2l;
@@ -245,7 +298,7 @@ static int addr2line(const char *dso_name, u64 addr,
         if (unwind_inlines) {
                 int cnt = 0;
 
-                if (node && inline_list__append_dso_a2l(dso, node))
+                if (node && inline_list__append_dso_a2l(dso, node, sym))
                         return 0;
 
                 while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
@@ -256,7 +309,7 @@ static int addr2line(const char *dso_name, u64 addr,
                                 a2l->filename = NULL;
 
                         if (node != NULL) {
-                                if (inline_list__append_dso_a2l(dso, node))
+                                if (inline_list__append_dso_a2l(dso, node, sym))
                                         return 0;
                                 // found at least one inline frame
                                 ret = 1;
@@ -288,7 +341,7 @@ void dso__free_a2l(struct dso *dso)
 }
 
 static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
-        struct dso *dso)
+                                        struct dso *dso, struct symbol *sym)
 {
         struct inline_node *node;
 
@@ -301,17 +354,8 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
         INIT_LIST_HEAD(&node->val);
         node->addr = addr;
 
-        if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node))
-                goto out_free_inline_node;
-
-        if (list_empty(&node->val))
-                goto out_free_inline_node;
-
+        addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym);
         return node;
-
-out_free_inline_node:
-        inline_node__delete(node);
-        return NULL;
 }
 
 #else /* HAVE_LIBBFD_SUPPORT */
@@ -341,7 +385,8 @@ static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line_nr,
                      struct dso *dso __maybe_unused,
                      bool unwind_inlines __maybe_unused,
-                     struct inline_node *node __maybe_unused)
+                     struct inline_node *node __maybe_unused,
+                     struct symbol *sym __maybe_unused)
 {
         FILE *fp;
         char cmd[PATH_MAX];
@@ -381,16 +426,18 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 }
 
 static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
-        struct dso *dso __maybe_unused)
+                                        struct dso *dso __maybe_unused,
+                                        struct symbol *sym)
 {
         FILE *fp;
         char cmd[PATH_MAX];
         struct inline_node *node;
         char *filename = NULL;
-        size_t len;
+        char *funcname = NULL;
+        size_t filelen, funclen;
         unsigned int line_nr = 0;
 
-        scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
+        scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i -f %016"PRIx64,
                   dso_name, addr);
 
         fp = popen(cmd, "r");
@@ -408,26 +455,34 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
         INIT_LIST_HEAD(&node->val);
         node->addr = addr;
 
-        while (getline(&filename, &len, fp) != -1) {
-                if (filename_split(filename, &line_nr) != 1) {
-                        free(filename);
+        /* addr2line -f generates two lines for each inlined functions */
+        while (getline(&funcname, &funclen, fp) != -1) {
+                char *srcline;
+                struct symbol *inline_sym;
+
+                rtrim(funcname);
+
+                if (getline(&filename, &filelen, fp) == -1)
                         goto out;
-                }
 
-                if (inline_list__append(filename, NULL, line_nr, node,
-                                        NULL) != 0)
+                if (filename_split(filename, &line_nr) != 1)
                         goto out;
 
-                filename = NULL;
+                srcline = srcline_from_fileline(filename, line_nr);
+                inline_sym = new_inline_sym(dso, sym, funcname);
+
+                if (inline_list__append(inline_sym, srcline, node) != 0) {
+                        free(srcline);
+                        if (inline_sym && inline_sym->inlined)
+                                symbol__delete(inline_sym);
+                        goto out;
+                }
         }
 
 out:
         pclose(fp);
-
-        if (list_empty(&node->val)) {
-                inline_node__delete(node);
-                return NULL;
-        }
+        free(filename);
+        free(funcname);
 
         return node;
 }
@@ -441,7 +496,8 @@ out:
 #define A2L_FAIL_LIMIT 123
 
 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym, bool show_addr, bool unwind_inlines)
+                  bool show_sym, bool show_addr, bool unwind_inlines,
+                  u64 ip)
 {
         char *file = NULL;
         unsigned line = 0;
@@ -455,19 +511,18 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
         if (dso_name == NULL)
                 goto out;
 
-        if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL))
+        if (!addr2line(dso_name, addr, &file, &line, dso,
+                       unwind_inlines, NULL, sym))
                 goto out;
 
-        if (asprintf(&srcline, "%s:%u",
-                                srcline_full_filename ? file : basename(file),
-                                line) < 0) {
-                free(file);
+        srcline = srcline_from_fileline(file, line);
+        free(file);
+
+        if (!srcline)
                 goto out;
-        }
 
         dso->a2l_fails = 0;
 
-        free(file);
         return srcline;
 
 out:
@@ -482,7 +537,7 @@ out:
 
         if (sym) {
                 if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
-                                        addr - sym->start) < 0)
+                                        ip - sym->start) < 0)
                         return SRCLINE_UNKNOWN;
         } else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0)
                 return SRCLINE_UNKNOWN;
@@ -496,12 +551,79 @@ void free_srcline(char *srcline)
 }
 
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym, bool show_addr)
+                  bool show_sym, bool show_addr, u64 ip)
+{
+        return __get_srcline(dso, addr, sym, show_sym, show_addr, false, ip);
+}
+
+struct srcline_node {
+        u64                     addr;
+        char                    *srcline;
+        struct rb_node          rb_node;
+};
+
+void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline)
+{
+        struct rb_node **p = &tree->rb_node;
+        struct rb_node *parent = NULL;
+        struct srcline_node *i, *node;
+
+        node = zalloc(sizeof(struct srcline_node));
+        if (!node) {
+                perror("not enough memory for the srcline node");
+                return;
+        }
+
+        node->addr = addr;
+        node->srcline = srcline;
+
+        while (*p != NULL) {
+                parent = *p;
+                i = rb_entry(parent, struct srcline_node, rb_node);
+                if (addr < i->addr)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+        rb_link_node(&node->rb_node, parent, p);
+        rb_insert_color(&node->rb_node, tree);
+}
+
+char *srcline__tree_find(struct rb_root *tree, u64 addr)
 {
-        return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
+        struct rb_node *n = tree->rb_node;
+
+        while (n) {
+                struct srcline_node *i = rb_entry(n, struct srcline_node,
+                                                  rb_node);
+
+                if (addr < i->addr)
+                        n = n->rb_left;
+                else if (addr > i->addr)
+                        n = n->rb_right;
+                else
+                        return i->srcline;
+        }
+
+        return NULL;
 }
 
-struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
+void srcline__tree_delete(struct rb_root *tree)
+{
+        struct srcline_node *pos;
+        struct rb_node *next = rb_first(tree);
+
+        while (next) {
+                pos = rb_entry(next, struct srcline_node, rb_node);
+                next = rb_next(&pos->rb_node);
+                rb_erase(&pos->rb_node, tree);
+                free_srcline(pos->srcline);
+                zfree(&pos);
+        }
+}
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
+                                            struct symbol *sym)
 {
         const char *dso_name;
 
@@ -509,7 +631,7 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
         if (dso_name == NULL)
                 return NULL;
 
-        return addr2inlines(dso_name, addr, dso);
+        return addr2inlines(dso_name, addr, dso, sym);
 }
 
 void inline_node__delete(struct inline_node *node)
@@ -518,10 +640,63 @@ void inline_node__delete(struct inline_node *node)
 
         list_for_each_entry_safe(ilist, tmp, &node->val, list) {
                 list_del_init(&ilist->list);
-                zfree(&ilist->filename);
-                zfree(&ilist->funcname);
+                free_srcline(ilist->srcline);
+                /* only the inlined symbols are owned by the list */
+                if (ilist->symbol && ilist->symbol->inlined)
+                        symbol__delete(ilist->symbol);
                 free(ilist);
         }
 
         free(node);
 }
+
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines)
+{
+        struct rb_node **p = &tree->rb_node;
+        struct rb_node *parent = NULL;
+        const u64 addr = inlines->addr;
+        struct inline_node *i;
+
+        while (*p != NULL) {
+                parent = *p;
+                i = rb_entry(parent, struct inline_node, rb_node);
+                if (addr < i->addr)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+        rb_link_node(&inlines->rb_node, parent, p);
+        rb_insert_color(&inlines->rb_node, tree);
+}
+
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
+{
+        struct rb_node *n = tree->rb_node;
+
+        while (n) {
+                struct inline_node *i = rb_entry(n, struct inline_node,
+                                                 rb_node);
+
+                if (addr < i->addr)
+                        n = n->rb_left;
+                else if (addr > i->addr)
+                        n = n->rb_right;
+                else
+                        return i;
+        }
+
+        return NULL;
+}
+
+void inlines__tree_delete(struct rb_root *tree)
+{
+        struct inline_node *pos;
+        struct rb_node *next = rb_first(tree);
+
+        while (next) {
+                pos = rb_entry(next, struct inline_node, rb_node);
+                next = rb_next(&pos->rb_node);
+                rb_erase(&pos->rb_node, tree);
+                inline_node__delete(pos);
+        }
+}
diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h
index 8e73f607dfa3..b2bb5502fd62 100644
--- a/tools/perf/util/srcline.h
+++ b/tools/perf/util/srcline.h
@@ -3,6 +3,7 @@
 #define PERF_SRCLINE_H
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/types.h>
 
 struct dso;
@@ -10,26 +11,44 @@ struct symbol;
 
 extern bool srcline_full_filename;
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym, bool show_addr);
+                  bool show_sym, bool show_addr, u64 ip);
 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym, bool show_addr, bool unwind_inlines);
+                  bool show_sym, bool show_addr, bool unwind_inlines,
+                  u64 ip);
 void free_srcline(char *srcline);
 
+/* insert the srcline into the DSO, which will take ownership */
+void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline);
+/* find previously inserted srcline */
+char *srcline__tree_find(struct rb_root *tree, u64 addr);
+/* delete all srclines within the tree */
+void srcline__tree_delete(struct rb_root *tree);
+
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
 struct inline_list {
-        char                    *filename;
-        char                    *funcname;
-        unsigned int            line_nr;
+        struct symbol           *symbol;
+        char                    *srcline;
         struct list_head        list;
 };
 
 struct inline_node {
         u64                     addr;
         struct list_head        val;
+        struct rb_node          rb_node;
 };
 
-struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+/* parse inlined frames for the given address */
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
+                                            struct symbol *sym);
+/* free resources associated to the inline node list */
 void inline_node__delete(struct inline_node *node);
 
+/* insert the inline node list into the DSO, which will take ownership */
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines);
+/* find previously inserted inline node list */
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr);
+/* delete all nodes within the tree of inline_node s */
+void inlines__tree_delete(struct rb_root *tree);
+
 #endif /* PERF_SRCLINE_H */
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 37363869c9a1..594d14a02b67 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -7,17 +7,7 @@
 #include "rblist.h"
 #include "evlist.h"
 #include "expr.h"
-
-enum {
-        CTX_BIT_USER    = 1 << 0,
-        CTX_BIT_KERNEL  = 1 << 1,
-        CTX_BIT_HV      = 1 << 2,
-        CTX_BIT_HOST    = 1 << 3,
-        CTX_BIT_IDLE    = 1 << 4,
-        CTX_BIT_MAX     = 1 << 5,
-};
-
-#define NUM_CTX CTX_BIT_MAX
+#include "metricgroup.h"
 
 /*
  * AGGR_GLOBAL: Use CPU 0
@@ -26,37 +16,18 @@ enum {
  * AGGR_NONE: Use matching CPU
  * AGGR_THREAD: Not supported?
  */
-static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_total_slots[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_smi_num_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS];
-static struct rblist runtime_saved_values;
 static bool have_frontend_stalled;
 
+struct runtime_stat rt_stat;
 struct stats walltime_nsecs_stats;
 
 struct saved_value {
         struct rb_node rb_node;
         struct perf_evsel *evsel;
-        int cpu;
+        enum stat_type type;
         int ctx;
+        int cpu;
+        struct runtime_stat *stat;
         struct stats stats;
 };
 
@@ -67,10 +38,32 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
                                              rb_node);
         const struct saved_value *b = entry;
 
-        if (a->ctx != b->ctx)
-                return a->ctx - b->ctx;
         if (a->cpu != b->cpu)
                 return a->cpu - b->cpu;
+
+        /*
+         * Previously the rbtree was used to link generic metrics.
+         * The keys were evsel/cpu. Now the rbtree is extended to support
+         * per-thread shadow stats. For shadow stats case, the keys
+         * are cpu/type/ctx/stat (evsel is NULL). For generic metrics
+         * case, the keys are still evsel/cpu (type/ctx/stat are 0 or NULL).
+         */
+        if (a->type != b->type)
+                return a->type - b->type;
+
+        if (a->ctx != b->ctx)
+                return a->ctx - b->ctx;
+
+        if (a->evsel == NULL && b->evsel == NULL) {
+                if (a->stat == b->stat)
+                        return 0;
+
+                if ((char *)a->stat < (char *)b->stat)
+                        return -1;
+
+                return 1;
+        }
+
         if (a->evsel == b->evsel)
                 return 0;
         if ((char *)a->evsel < (char *)b->evsel)
@@ -89,35 +82,66 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
         return &nd->rb_node;
 }
 
+static void saved_value_delete(struct rblist *rblist __maybe_unused,
+                               struct rb_node *rb_node)
+{
+        struct saved_value *v;
+
+        BUG_ON(!rb_node);
+        v = container_of(rb_node, struct saved_value, rb_node);
+        free(v);
+}
+
 static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
-                                              int cpu, int ctx,
-                                              bool create)
+                                              int cpu,
+                                              bool create,
+                                              enum stat_type type,
+                                              int ctx,
+                                              struct runtime_stat *st)
 {
+        struct rblist *rblist;
         struct rb_node *nd;
         struct saved_value dm = {
                 .cpu = cpu,
-                .ctx = ctx,
                 .evsel = evsel,
+                .type = type,
+                .ctx = ctx,
+                .stat = st,
         };
-        nd = rblist__find(&runtime_saved_values, &dm);
+
+        rblist = &st->value_list;
+
+        nd = rblist__find(rblist, &dm);
         if (nd)
                 return container_of(nd, struct saved_value, rb_node);
         if (create) {
-                rblist__add_node(&runtime_saved_values, &dm);
-                nd = rblist__find(&runtime_saved_values, &dm);
+                rblist__add_node(rblist, &dm);
+                nd = rblist__find(rblist, &dm);
                 if (nd)
                         return container_of(nd, struct saved_value, rb_node);
         }
         return NULL;
 }
 
+void runtime_stat__init(struct runtime_stat *st)
+{
+        struct rblist *rblist = &st->value_list;
+
+        rblist__init(rblist);
+        rblist->node_cmp = saved_value_cmp;
+        rblist->node_new = saved_value_new;
+        rblist->node_delete = saved_value_delete;
+}
+
+void runtime_stat__exit(struct runtime_stat *st)
+{
+        rblist__exit(&st->value_list);
+}
+
 void perf_stat__init_shadow_stats(void)
 {
         have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
-        rblist__init(&runtime_saved_values);
-        runtime_saved_values.node_cmp = saved_value_cmp;
-        runtime_saved_values.node_new = saved_value_new;
-        /* No delete for now */
+        runtime_stat__init(&rt_stat);
 }
 
 static int evsel_context(struct perf_evsel *evsel)
@@ -138,36 +162,13 @@ static int evsel_context(struct perf_evsel *evsel)
         return ctx;
 }
 
-void perf_stat__reset_shadow_stats(void)
+static void reset_stat(struct runtime_stat *st)
 {
+        struct rblist *rblist;
         struct rb_node *pos, *next;
 
-        memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
-        memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
-        memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
-        memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
-        memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
-        memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
-        memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
-        memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
-        memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
-        memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
-        memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
-        memset(runtime_cycles_in_tx_stats, 0,
-                        sizeof(runtime_cycles_in_tx_stats));
-        memset(runtime_transaction_stats, 0,
-                sizeof(runtime_transaction_stats));
-        memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
-        memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
-        memset(runtime_topdown_total_slots, 0, sizeof(runtime_topdown_total_slots));
-        memset(runtime_topdown_slots_retired, 0, sizeof(runtime_topdown_slots_retired));
-        memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
-        memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
-        memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
-        memset(runtime_smi_num_stats, 0, sizeof(runtime_smi_num_stats));
-        memset(runtime_aperf_stats, 0, sizeof(runtime_aperf_stats));
-
-        next = rb_first(&runtime_saved_values.entries);
+        rblist = &st->value_list;
+        next = rb_first(&rblist->entries);
         while (next) {
                 pos = next;
                 next = rb_next(pos);
@@ -177,64 +178,95 @@ void perf_stat__reset_shadow_stats(void)
         }
 }
 
+void perf_stat__reset_shadow_stats(void)
+{
+        reset_stat(&rt_stat);
+        memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
+void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
+{
+        reset_stat(st);
+}
+
+static void update_runtime_stat(struct runtime_stat *st,
+                                enum stat_type type,
+                                int ctx, int cpu, u64 count)
+{
+        struct saved_value *v = saved_value_lookup(NULL, cpu, true,
+                                                   type, ctx, st);
+
+        if (v)
+                update_stats(&v->stats, count);
+}
+
 /*
  * Update various tracking values we maintain to print
  * more semantic information such as miss/hit ratios,
  * instruction rates, etc:
  */
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
-                                    int cpu)
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
+                                    int cpu, struct runtime_stat *st)
 {
         int ctx = evsel_context(counter);
 
+        count *= counter->scale;
+
         if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
             perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
-                update_stats(&runtime_nsecs_stats[cpu], count[0]);
+                update_runtime_stat(st, STAT_NSECS, 0, cpu, count);
         else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-                update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-                update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, TRANSACTION_START))
-                update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, ELISION_START))
-                update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_ELISION, ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
-                update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
+                                    ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
-                update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
+                                    ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
-                update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
+                                    ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
-                update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+                update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
+                                    ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
-                update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
+                                    ctx, cpu, count);
         else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-                update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
+                                    ctx, cpu, count);
         else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
-                update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
+                                    ctx, cpu, count);
         else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-                update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
         else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-                update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-                update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-                update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-                update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-                update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
         else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-                update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, SMI_NUM))
-                update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
         else if (perf_stat_evsel__is(counter, APERF))
-                update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
+                update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
 
         if (counter->collect_stat) {
-                struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
-                                                           true);
-                update_stats(&v->stats, count[0]);
+                struct saved_value *v = saved_value_lookup(counter, cpu, true,
+                                                           STAT_NONE, 0, st);
+                update_stats(&v->stats, count);
         }
 }
 
@@ -354,15 +386,40 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
         }
 }
 
+static double runtime_stat_avg(struct runtime_stat *st,
+                               enum stat_type type, int ctx, int cpu)
+{
+        struct saved_value *v;
+
+        v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+        if (!v)
+                return 0.0;
+
+        return avg_stats(&v->stats);
+}
+
+static double runtime_stat_n(struct runtime_stat *st,
+                             enum stat_type type, int ctx, int cpu)
+{
+        struct saved_value *v;
+
+        v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+        if (!v)
+                return 0.0;
+
+        return v->stats.n;
+}
+
 static void print_stalled_cycles_frontend(int cpu,
                                           struct perf_evsel *evsel, double avg,
-                                          struct perf_stat_output_ctx *out)
+                                          struct perf_stat_output_ctx *out,
+                                          struct runtime_stat *st)
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -378,13 +435,14 @@ static void print_stalled_cycles_frontend(int cpu,
 
 static void print_stalled_cycles_backend(int cpu,
                                          struct perf_evsel *evsel, double avg,
-                                         struct perf_stat_output_ctx *out)
+                                         struct perf_stat_output_ctx *out,
+                                         struct runtime_stat *st)
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -397,13 +455,14 @@ static void print_stalled_cycles_backend(int cpu,
 static void print_branch_misses(int cpu,
                                 struct perf_evsel *evsel,
                                 double avg,
-                                struct perf_stat_output_ctx *out)
+                                struct perf_stat_output_ctx *out,
+                                struct runtime_stat *st)
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_branches_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -416,13 +475,15 @@ static void print_branch_misses(int cpu,
 static void print_l1_dcache_misses(int cpu,
                                    struct perf_evsel *evsel,
                                    double avg,
-                                   struct perf_stat_output_ctx *out)
+                                   struct perf_stat_output_ctx *out,
+                                   struct runtime_stat *st)
+
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -435,13 +496,15 @@ static void print_l1_dcache_misses(int cpu,
 static void print_l1_icache_misses(int cpu,
                                    struct perf_evsel *evsel,
                                    double avg,
-                                   struct perf_stat_output_ctx *out)
+                                   struct perf_stat_output_ctx *out,
+                                   struct runtime_stat *st)
+
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -453,13 +516,14 @@ static void print_l1_icache_misses(int cpu,
 static void print_dtlb_cache_misses(int cpu,
                                     struct perf_evsel *evsel,
                                     double avg,
-                                    struct perf_stat_output_ctx *out)
+                                    struct perf_stat_output_ctx *out,
+                                    struct runtime_stat *st)
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -471,13 +535,14 @@ static void print_dtlb_cache_misses(int cpu,
 static void print_itlb_cache_misses(int cpu,
                                     struct perf_evsel *evsel,
                                     double avg,
-                                    struct perf_stat_output_ctx *out)
+                                    struct perf_stat_output_ctx *out,
+                                    struct runtime_stat *st)
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -489,13 +554,14 @@ static void print_itlb_cache_misses(int cpu,
 static void print_ll_cache_misses(int cpu,
                                   struct perf_evsel *evsel,
                                   double avg,
-                                  struct perf_stat_output_ctx *out)
+                                  struct perf_stat_output_ctx *out,
+                                  struct runtime_stat *st)
 {
         double total, ratio = 0.0;
         const char *color;
         int ctx = evsel_context(evsel);
 
-        total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
+        total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu);
 
         if (total)
                 ratio = avg / total * 100.0;
@@ -553,68 +619,72 @@ static double sanitize_val(double x)
         return x;
 }
 
-static double td_total_slots(int ctx, int cpu)
+static double td_total_slots(int ctx, int cpu, struct runtime_stat *st)
 {
-        return avg_stats(&runtime_topdown_total_slots[ctx][cpu]);
+        return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
 }
 
-static double td_bad_spec(int ctx, int cpu)
+static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st)
 {
         double bad_spec = 0;
         double total_slots;
         double total;
 
-        total = avg_stats(&runtime_topdown_slots_issued[ctx][cpu]) -
-                avg_stats(&runtime_topdown_slots_retired[ctx][cpu]) +
-                avg_stats(&runtime_topdown_recovery_bubbles[ctx][cpu]);
-        total_slots = td_total_slots(ctx, cpu);
+        total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
+                runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
+                runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+
+        total_slots = td_total_slots(ctx, cpu, st);
         if (total_slots)
                 bad_spec = total / total_slots;
         return sanitize_val(bad_spec);
 }
 
-static double td_retiring(int ctx, int cpu)
+static double td_retiring(int ctx, int cpu, struct runtime_stat *st)
 {
         double retiring = 0;
-        double total_slots = td_total_slots(ctx, cpu);
-        double ret_slots = avg_stats(&runtime_topdown_slots_retired[ctx][cpu]);
+        double total_slots = td_total_slots(ctx, cpu, st);
+        double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
+                                            ctx, cpu);
 
         if (total_slots)
                 retiring = ret_slots / total_slots;
         return retiring;
 }
 
-static double td_fe_bound(int ctx, int cpu)
+static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st)
 {
         double fe_bound = 0;
-        double total_slots = td_total_slots(ctx, cpu);
-        double fetch_bub = avg_stats(&runtime_topdown_fetch_bubbles[ctx][cpu]);
+        double total_slots = td_total_slots(ctx, cpu, st);
+        double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
+                                            ctx, cpu);
 
         if (total_slots)
                 fe_bound = fetch_bub / total_slots;
         return fe_bound;
 }
 
-static double td_be_bound(int ctx, int cpu)
+static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
 {
-        double sum = (td_fe_bound(ctx, cpu) +
-                      td_bad_spec(ctx, cpu) +
-                      td_retiring(ctx, cpu));
+        double sum = (td_fe_bound(ctx, cpu, st) +
+                      td_bad_spec(ctx, cpu, st) +
+                      td_retiring(ctx, cpu, st));
         if (sum == 0)
                 return 0;
         return sanitize_val(1.0 - sum);
 }
 
 static void print_smi_cost(int cpu, struct perf_evsel *evsel,
-                           struct perf_stat_output_ctx *out)
+                           struct perf_stat_output_ctx *out,
+                           struct runtime_stat *st)
 {
         double smi_num, aperf, cycles, cost = 0.0;
         int ctx = evsel_context(evsel);
         const char *color = NULL;
 
-        smi_num = avg_stats(&runtime_smi_num_stats[ctx][cpu]);
-        aperf = avg_stats(&runtime_aperf_stats[ctx][cpu]);
-        cycles = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+        smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu);
+        aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
+        cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
         if ((cycles == 0) || (aperf == 0))
                 return;
@@ -628,18 +698,75 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
         out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
+static void generic_metric(const char *metric_expr,
+                           struct perf_evsel **metric_events,
+                           char *name,
+                           const char *metric_name,
+                           double avg,
+                           int cpu,
+                           struct perf_stat_output_ctx *out,
+                           struct runtime_stat *st)
+{
+        print_metric_t print_metric = out->print_metric;
+        struct parse_ctx pctx;
+        double ratio;
+        int i;
+        void *ctxp = out->ctx;
+
+        expr__ctx_init(&pctx);
+        expr__add_id(&pctx, name, avg);
+        for (i = 0; metric_events[i]; i++) {
+                struct saved_value *v;
+                struct stats *stats;
+                double scale;
+
+                if (!strcmp(metric_events[i]->name, "duration_time")) {
+                        stats = &walltime_nsecs_stats;
+                        scale = 1e-9;
+                } else {
+                        v = saved_value_lookup(metric_events[i], cpu, false,
+                                               STAT_NONE, 0, st);
+                        if (!v)
+                                break;
+                        stats = &v->stats;
+                        scale = 1.0;
+                }
+                expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
+        }
+        if (!metric_events[i]) {
+                const char *p = metric_expr;
+
+                if (expr__parse(&ratio, &pctx, &p) == 0)
+                        print_metric(ctxp, NULL, "%8.1f",
+                                metric_name ?
+                                metric_name :
+                                out->force_header ?  name : "",
+                                ratio);
+                else
+                        print_metric(ctxp, NULL, NULL,
+                                     out->force_header ?
+                                     (metric_name ? metric_name : name) : "", 0);
+        } else
+                print_metric(ctxp, NULL, NULL, "", 0);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                                    double avg, int cpu,
-                                   struct perf_stat_output_ctx *out)
+                                   struct perf_stat_output_ctx *out,
+                                   struct rblist *metric_events,
+                                   struct runtime_stat *st)
 {
         void *ctxp = out->ctx;
         print_metric_t print_metric = out->print_metric;
         double total, ratio = 0.0, total2;
         const char *color = NULL;
         int ctx = evsel_context(evsel);
+        struct metric_event *me;
+        int num = 1;
 
         if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
-                total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+                total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+
                 if (total) {
                         ratio = avg / total;
                         print_metric(ctxp, NULL, "%7.2f ",
@@ -647,8 +774,13 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 } else {
                         print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
                 }
-                total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
-                total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
+
+                total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
+                                         ctx, cpu);
+
+                total = max(total, runtime_stat_avg(st,
+                                                    STAT_STALLED_CYCLES_BACK,
+                                                    ctx, cpu));
 
                 if (total && avg) {
                         out->new_line(ctxp);
@@ -661,8 +793,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                                      "stalled cycles per insn", 0);
                 }
         } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
-                if (runtime_branches_stats[ctx][cpu].n != 0)
-                        print_branch_misses(cpu, evsel, avg, out);
+                if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
+                        print_branch_misses(cpu, evsel, avg, out, st);
                 else
                         print_metric(ctxp, NULL, NULL, "of all branches", 0);
         } else if (
@@ -670,8 +802,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
                                          ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
-                if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
-                        print_l1_dcache_misses(cpu, evsel, avg, out);
+
+                if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
+                        print_l1_dcache_misses(cpu, evsel, avg, out, st);
                 else
                         print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
         } else if (
@@ -679,8 +812,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
                                          ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
-                if (runtime_l1_icache_stats[ctx][cpu].n != 0)
-                        print_l1_icache_misses(cpu, evsel, avg, out);
+
+                if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
+                        print_l1_icache_misses(cpu, evsel, avg, out, st);
                 else
                         print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
         } else if (
@@ -688,8 +822,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
                                          ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
-                if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
-                        print_dtlb_cache_misses(cpu, evsel, avg, out);
+
+                if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
+                        print_dtlb_cache_misses(cpu, evsel, avg, out, st);
                 else
                         print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
         } else if (
@@ -697,8 +832,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
                                          ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
-                if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
-                        print_itlb_cache_misses(cpu, evsel, avg, out);
+
+                if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
+                        print_itlb_cache_misses(cpu, evsel, avg, out, st);
                 else
                         print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
         } else if (
@@ -706,27 +842,28 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
                                          ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
-                if (runtime_ll_cache_stats[ctx][cpu].n != 0)
-                        print_ll_cache_misses(cpu, evsel, avg, out);
+
+                if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
+                        print_ll_cache_misses(cpu, evsel, avg, out, st);
                 else
                         print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
-                total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
+                total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
                 if (total)
                         ratio = avg * 100 / total;
 
-                if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+                if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
                         print_metric(ctxp, NULL, "%8.3f %%",
                                      "of all cache refs", ratio);
                 else
                         print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-                print_stalled_cycles_frontend(cpu, evsel, avg, out);
+                print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-                print_stalled_cycles_backend(cpu, evsel, avg, out);
+                print_stalled_cycles_backend(cpu, evsel, avg, out, st);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
-                total = avg_stats(&runtime_nsecs_stats[cpu]);
+                total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
                 if (total) {
                         ratio = avg / total;
@@ -735,7 +872,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                         print_metric(ctxp, NULL, NULL, "Ghz", 0);
                 }
         } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
-                total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+                total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+
                 if (total)
                         print_metric(ctxp, NULL,
                                         "%7.2f%%", "transactional cycles",
@@ -744,8 +882,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                         print_metric(ctxp, NULL, NULL, "transactional cycles",
                                      0);
         } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
-                total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
-                total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+                total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+                total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);
+
                 if (total2 < avg)
                         total2 = avg;
                 if (total)
@@ -754,19 +893,21 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 else
                         print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
         } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
-                total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+                total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
+                                         ctx, cpu);
 
                 if (avg)
                         ratio = total / avg;
 
-                if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+                if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
                         print_metric(ctxp, NULL, "%8.0f",
                                      "cycles / transaction", ratio);
                 else
                         print_metric(ctxp, NULL, NULL, "cycles / transaction",
-                                     0);
+                                      0);
         } else if (perf_stat_evsel__is(evsel, ELISION_START)) {
-                total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+                total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
+                                         ctx, cpu);
 
                 if (avg)
                         ratio = total / avg;
@@ -780,28 +921,28 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 else
                         print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
         } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
-                double fe_bound = td_fe_bound(ctx, cpu);
+                double fe_bound = td_fe_bound(ctx, cpu, st);
 
                 if (fe_bound > 0.2)
                         color = PERF_COLOR_RED;
                 print_metric(ctxp, color, "%8.1f%%", "frontend bound",
                                 fe_bound * 100.);
         } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
-                double retiring = td_retiring(ctx, cpu);
+                double retiring = td_retiring(ctx, cpu, st);
 
                 if (retiring > 0.7)
                         color = PERF_COLOR_GREEN;
                 print_metric(ctxp, color, "%8.1f%%", "retiring",
                                 retiring * 100.);
         } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
-                double bad_spec = td_bad_spec(ctx, cpu);
+                double bad_spec = td_bad_spec(ctx, cpu, st);
 
                 if (bad_spec > 0.1)
                         color = PERF_COLOR_RED;
                 print_metric(ctxp, color, "%8.1f%%", "bad speculation",
                                 bad_spec * 100.);
         } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
-                double be_bound = td_be_bound(ctx, cpu);
+                double be_bound = td_be_bound(ctx, cpu, st);
                 const char *name = "backend bound";
                 static int have_recovery_bubbles = -1;
 
@@ -814,44 +955,19 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
                 if (be_bound > 0.2)
                         color = PERF_COLOR_RED;
-                if (td_total_slots(ctx, cpu) > 0)
+                if (td_total_slots(ctx, cpu, st) > 0)
                         print_metric(ctxp, color, "%8.1f%%", name,
                                         be_bound * 100.);
                 else
                         print_metric(ctxp, NULL, NULL, name, 0);
         } else if (evsel->metric_expr) {
-                struct parse_ctx pctx;
-                int i;
-
-                expr__ctx_init(&pctx);
-                expr__add_id(&pctx, evsel->name, avg);
-                for (i = 0; evsel->metric_events[i]; i++) {
-                        struct saved_value *v;
-
-                        v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
-                        if (!v)
-                                break;
-                        expr__add_id(&pctx, evsel->metric_events[i]->name,
-                                             avg_stats(&v->stats));
-                }
-                if (!evsel->metric_events[i]) {
-                        const char *p = evsel->metric_expr;
-
-                        if (expr__parse(&ratio, &pctx, &p) == 0)
-                                print_metric(ctxp, NULL, "%8.1f",
-                                        evsel->metric_name ?
-                                        evsel->metric_name :
-                                        out->force_header ?  evsel->name : "",
-                                        ratio);
-                        else
-                                print_metric(ctxp, NULL, NULL, "", 0);
-                } else
-                        print_metric(ctxp, NULL, NULL, "", 0);
-        } else if (runtime_nsecs_stats[cpu].n != 0) {
+                generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+                                evsel->metric_name, avg, cpu, out, st);
+        } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
                 char unit = 'M';
                 char unit_buf[10];
 
-                total = avg_stats(&runtime_nsecs_stats[cpu]);
+                total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
                 if (total)
                         ratio = 1000.0 * avg / total;
@@ -862,8 +978,22 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                 snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
                 print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
         } else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-                print_smi_cost(cpu, evsel, out);
+                print_smi_cost(cpu, evsel, out, st);
         } else {
-                print_metric(ctxp, NULL, NULL, NULL, 0);
+                num = 0;
+        }
+
+        if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
+                struct metric_expr *mexp;
+
+                list_for_each_entry (mexp, &me->head, nd) {
+                        if (num++ > 0)
+                                out->new_line(ctxp);
+                        generic_metric(mexp->metric_expr, mexp->metric_events,
+                                        evsel->name, mexp->metric_name,
+                                        avg, cpu, out, st);
+                }
         }
+        if (num == 0)
+                print_metric(ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index c9bae5fb8b47..32235657c1ac 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -70,7 +70,7 @@ double rel_stddev_stats(double stddev, double avg)
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
                            enum perf_stat_evsel_id id)
 {
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
 
         return ps->id == id;
 }
@@ -94,7 +94,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 
 void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 {
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
         int i;
 
         /* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
@@ -110,7 +110,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
         int i;
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
 
         for (i = 0; i < 3; i++)
                 init_stats(&ps->res_stats[i]);
@@ -120,8 +120,8 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
-        evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
-        if (evsel->priv == NULL)
+        evsel->stats = zalloc(sizeof(struct perf_stat_evsel));
+        if (evsel->stats == NULL)
                 return -ENOMEM;
         perf_evsel__reset_stat_priv(evsel);
         return 0;
@@ -129,11 +129,11 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
-        struct perf_stat_evsel *ps = evsel->priv;
+        struct perf_stat_evsel *ps = evsel->stats;
 
         if (ps)
                 free(ps->group_data);
-        zfree(&evsel->priv);
+        zfree(&evsel->stats);
 }
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
@@ -278,7 +278,16 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
                         perf_evsel__compute_deltas(evsel, cpu, thread, count);
                 perf_counts_values__scale(count, config->scale, NULL);
                 if (config->aggr_mode == AGGR_NONE)
-                        perf_stat__update_shadow_stats(evsel, count->values, cpu);
+                        perf_stat__update_shadow_stats(evsel, count->val, cpu,
+                                                       &rt_stat);
+                if (config->aggr_mode == AGGR_THREAD) {
+                        if (config->stats)
+                                perf_stat__update_shadow_stats(evsel,
+                                        count->val, 0, &config->stats[thread]);
+                        else
+                                perf_stat__update_shadow_stats(evsel,
+                                        count->val, 0, &rt_stat);
+                }
                 break;
         case AGGR_GLOBAL:
                 aggr->val += count->val;
@@ -319,9 +328,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
                               struct perf_evsel *counter)
 {
         struct perf_counts_values *aggr = &counter->counts->aggr;
-        struct perf_stat_evsel *ps = counter->priv;
+        struct perf_stat_evsel *ps = counter->stats;
         u64 *count = counter->counts->aggr.values;
-        u64 val;
         int i, ret;
 
         aggr->val = aggr->ena = aggr->run = 0;
@@ -361,8 +369,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
         /*
          * Save the full runtime - to allow normalization during printout:
          */
-        val = counter->scale * *count;
-        perf_stat__update_shadow_stats(counter, &val, 0);
+        perf_stat__update_shadow_stats(counter, *count, 0, &rt_stat);
 
         return 0;
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 96326b1f9443..dbc6f7134f61 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <stdio.h>
 #include "xyarray.h"
+#include "rblist.h"
 
 struct stats
 {
@@ -43,11 +44,54 @@ enum aggr_mode {
         AGGR_UNSET,
 };
 
+enum {
+        CTX_BIT_USER    = 1 << 0,
+        CTX_BIT_KERNEL  = 1 << 1,
+        CTX_BIT_HV      = 1 << 2,
+        CTX_BIT_HOST    = 1 << 3,
+        CTX_BIT_IDLE    = 1 << 4,
+        CTX_BIT_MAX     = 1 << 5,
+};
+
+#define NUM_CTX CTX_BIT_MAX
+
+enum stat_type {
+        STAT_NONE = 0,
+        STAT_NSECS,
+        STAT_CYCLES,
+        STAT_STALLED_CYCLES_FRONT,
+        STAT_STALLED_CYCLES_BACK,
+        STAT_BRANCHES,
+        STAT_CACHEREFS,
+        STAT_L1_DCACHE,
+        STAT_L1_ICACHE,
+        STAT_LL_CACHE,
+        STAT_ITLB_CACHE,
+        STAT_DTLB_CACHE,
+        STAT_CYCLES_IN_TX,
+        STAT_TRANSACTION,
+        STAT_ELISION,
+        STAT_TOPDOWN_TOTAL_SLOTS,
+        STAT_TOPDOWN_SLOTS_ISSUED,
+        STAT_TOPDOWN_SLOTS_RETIRED,
+        STAT_TOPDOWN_FETCH_BUBBLES,
+        STAT_TOPDOWN_RECOVERY_BUBBLES,
+        STAT_SMI_NUM,
+        STAT_APERF,
+        STAT_MAX
+};
+
+struct runtime_stat {
+        struct rblist value_list;
+};
+
 struct perf_stat_config {
         enum aggr_mode  aggr_mode;
         bool            scale;
         FILE            *output;
         unsigned int    interval;
+        struct runtime_stat *stats;
+        int             stats_num;
 };
 
 void update_stats(struct stats *stats, u64 val);
@@ -67,6 +111,15 @@ static inline void init_stats(struct stats *stats)
 struct perf_evsel;
 struct perf_evlist;
 
+struct perf_aggr_thread_value {
+        struct perf_evsel *counter;
+        int id;
+        double uval;
+        u64 val;
+        u64 run;
+        u64 ena;
+};
+
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
                            enum perf_stat_evsel_id id);
 
@@ -75,16 +128,20 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 
 void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
+extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
 typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
                                const char *fmt, double val);
 typedef void (*new_line_t )(void *ctx);
 
+void runtime_stat__init(struct runtime_stat *st);
+void runtime_stat__exit(struct runtime_stat *st);
 void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
-                                    int cpu);
+void perf_stat__reset_shadow_per_stat(struct runtime_stat *st);
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
+                                    int cpu, struct runtime_stat *st);
 struct perf_stat_output_ctx {
         void *ctx;
         print_metric_t print_metric;
@@ -94,7 +151,9 @@ struct perf_stat_output_ctx {
 
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                                    double avg, int cpu,
-                                   struct perf_stat_output_ctx *out);
+                                   struct perf_stat_output_ctx *out,
+                                   struct rblist *metric_events,
+                                   struct runtime_stat *st);
 void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index aaa08ee8c717..d8bfd0c4d2cb 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -396,3 +396,49 @@ out_err_overflow:
         free(expr);
         return NULL;
 }
+
+/* Like strpbrk(), but not break if it is right after a backslash (escaped) */
+char *strpbrk_esc(char *str, const char *stopset)
+{
+        char *ptr;
+
+        do {
+                ptr = strpbrk(str, stopset);
+                if (ptr == str ||
+                    (ptr == str + 1 && *(ptr - 1) != '\\'))
+                        break;
+                str = ptr + 1;
+        } while (ptr && *(ptr - 1) == '\\' && *(ptr - 2) != '\\');
+
+        return ptr;
+}
+
+/* Like strdup, but do not copy a single backslash */
+char *strdup_esc(const char *str)
+{
+        char *s, *d, *p, *ret = strdup(str);
+
+        if (!ret)
+                return NULL;
+
+        d = strchr(ret, '\\');
+        if (!d)
+                return ret;
+
+        s = d + 1;
+        do {
+                if (*s == '\0') {
+                        *d = '\0';
+                        break;
+                }
+                p = strchr(s + 1, '\\');
+                if (p) {
+                        memmove(d, s, p - s);
+                        d += p - s;
+                        s = p + 1;
+                } else
+                        memmove(d, s, strlen(s) + 1);
+        } while (p);
+
+        return ret;
+}
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index ee14ca5451ab..4c68a09b97e8 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -39,5 +39,7 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
         return asprintf_expr_inout_ints(var, false, nints, ints);
 }
 
+char *strpbrk_esc(char *str, const char *stopset);
+char *strdup_esc(const char *str);
 
 #endif /* PERF_STRING_H */
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6492ef38b090..cc065d4bfafc 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -46,6 +46,7 @@ struct symbol_conf symbol_conf = {
         .show_hist_headers      = true,
         .symfs                  = "",
         .event_group            = true,
+        .inline_name            = true,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -93,6 +94,11 @@ static int prefix_underscores_count(const char *str)
         return tail - str;
 }
 
+const char * __weak arch__normalize_symbol_name(const char *name)
+{
+        return name;
+}
+
 int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
 {
         return strcmp(namea, nameb);
@@ -227,7 +233,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
         struct maps *maps = &mg->maps[type];
         struct map *next, *curr;
 
-        pthread_rwlock_wrlock(&maps->lock);
+        down_write(&maps->lock);
 
         curr = maps__first(maps);
         if (curr == NULL)
@@ -247,7 +253,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
                 curr->end = ~0ULL;
 
 out_unlock:
-        pthread_rwlock_unlock(&maps->lock);
+        up_write(&maps->lock);
 }
 
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
@@ -1672,7 +1678,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
         struct maps *maps = &mg->maps[type];
         struct map *map;
 
-        pthread_rwlock_rdlock(&maps->lock);
+        down_read(&maps->lock);
 
         for (map = maps__first(maps); map; map = map__next(map)) {
                 if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1682,7 +1688,7 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
         map = NULL;
 
 out_unlock:
-        pthread_rwlock_unlock(&maps->lock);
+        up_read(&maps->lock);
         return map;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 6352022593c6..0563f33c1eb3 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -60,6 +60,7 @@ struct symbol {
         u8              binding;
         u8              idle:1;
         u8              ignore:1;
+        u8              inlined:1;
         u8              arch_sym;
         char            name[0];
 };
@@ -209,6 +210,7 @@ struct addr_location {
         struct thread *thread;
         struct map    *map;
         struct symbol *sym;
+        const char    *srcline;
         u64           addr;
         char          level;
         u8            filtered;
@@ -347,6 +349,7 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
 void arch__sym_update(struct symbol *s, GElf_Sym *sym);
 #endif
 
+const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 6eea7cff3d4e..303bdb84ab5a 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -26,6 +26,10 @@
 #include <asm/syscalls_64.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_x86_64;
+#elif defined(__s390x__)
+#include <asm/syscalls_64.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_s390_64;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 446aa7a56f25..6ef01a83b24e 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -64,6 +64,11 @@ static inline bool target__none(struct target *target)
         return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__has_per_thread(struct target *target)
+{
+        return target->system_wide && target->per_thread;
+}
+
 static inline bool target__uses_dummy_map(struct target *target)
 {
         bool use_dummy = false;
@@ -73,6 +78,8 @@ static inline bool target__uses_dummy_map(struct target *target)
         else if (target__has_task(target) ||
                  (!target__has_cpu(target) && !target->uses_mmap))
                 use_dummy = true;
+        else if (target__has_per_thread(target))
+                use_dummy = true;
 
         return use_dummy;
 }
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1dbcd3c8dee0..68b65b10579b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -46,6 +46,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
                 thread->cpu = -1;
                 INIT_LIST_HEAD(&thread->namespaces_list);
                 INIT_LIST_HEAD(&thread->comm_list);
+                init_rwsem(&thread->namespaces_lock);
+                init_rwsem(&thread->comm_lock);
 
                 comm_str = malloc(32);
                 if (!comm_str)
@@ -84,18 +86,26 @@ void thread__delete(struct thread *thread)
                 map_groups__put(thread->mg);
                 thread->mg = NULL;
         }
+        down_write(&thread->namespaces_lock);
         list_for_each_entry_safe(namespaces, tmp_namespaces,
                                  &thread->namespaces_list, list) {
                 list_del(&namespaces->list);
                 namespaces__free(namespaces);
         }
+        up_write(&thread->namespaces_lock);
+
+        down_write(&thread->comm_lock);
         list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
                 list_del(&comm->list);
                 comm__free(comm);
         }
+        up_write(&thread->comm_lock);
+
         unwind__finish_access(thread);
         nsinfo__zput(thread->nsinfo);
 
+        exit_rwsem(&thread->namespaces_lock);
+        exit_rwsem(&thread->comm_lock);
         free(thread);
 }
 
@@ -126,8 +136,8 @@ struct namespaces *thread__namespaces(const struct thread *thread)
         return list_first_entry(&thread->namespaces_list, struct namespaces, list);
 }
 
-int thread__set_namespaces(struct thread *thread, u64 timestamp,
-                           struct namespaces_event *event)
+static int __thread__set_namespaces(struct thread *thread, u64 timestamp,
+                                    struct namespaces_event *event)
 {
         struct namespaces *new, *curr = thread__namespaces(thread);
 
@@ -150,6 +160,17 @@ int thread__set_namespaces(struct thread *thread, u64 timestamp,
         return 0;
 }
 
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+                           struct namespaces_event *event)
+{
+        int ret;
+
+        down_write(&thread->namespaces_lock);
+        ret = __thread__set_namespaces(thread, timestamp, event);
+        up_write(&thread->namespaces_lock);
+        return ret;
+}
+
 struct comm *thread__comm(const struct thread *thread)
 {
         if (list_empty(&thread->comm_list))
@@ -171,8 +192,8 @@ struct comm *thread__exec_comm(const struct thread *thread)
         return last;
 }
 
-int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
-                       bool exec)
+static int ____thread__set_comm(struct thread *thread, const char *str,
+                                u64 timestamp, bool exec)
 {
         struct comm *new, *curr = thread__comm(thread);
 
@@ -196,6 +217,17 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
         return 0;
 }
 
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+                       bool exec)
+{
+        int ret;
+
+        down_write(&thread->comm_lock);
+        ret = ____thread__set_comm(thread, str, timestamp, exec);
+        up_write(&thread->comm_lock);
+        return ret;
+}
+
 int thread__set_comm_from_proc(struct thread *thread)
 {
         char path[64];
@@ -213,7 +245,7 @@ int thread__set_comm_from_proc(struct thread *thread)
         return err;
 }
 
-const char *thread__comm_str(const struct thread *thread)
+static const char *__thread__comm_str(const struct thread *thread)
 {
         const struct comm *comm = thread__comm(thread);
 
@@ -223,6 +255,17 @@ const char *thread__comm_str(const struct thread *thread)
         return comm__str(comm);
 }
 
+const char *thread__comm_str(const struct thread *thread)
+{
+        const char *str;
+
+        down_read((struct rw_semaphore *)&thread->comm_lock);
+        str = __thread__comm_str(thread);
+        up_read((struct rw_semaphore *)&thread->comm_lock);
+
+        return str;
+}
+
 /* CHECKME: it should probably better return the max comm len from its comm list */
 int thread__comm_len(struct thread *thread)
 {
@@ -265,7 +308,7 @@ static int __thread__prepare_access(struct thread *thread)
                 struct maps *maps = &thread->mg->maps[i];
                 struct map *map;
 
-                pthread_rwlock_rdlock(&maps->lock);
+                down_read(&maps->lock);
 
                 for (map = maps__first(maps); map; map = map__next(map)) {
                         err = unwind__prepare_access(thread, map, &initialized);
@@ -273,7 +316,7 @@ static int __thread__prepare_access(struct thread *thread)
                                 break;
                 }
 
-                pthread_rwlock_unlock(&maps->lock);
+                up_read(&maps->lock);
         }
 
         return err;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index fdcea7c0cac1..40cfa36c022a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
+#include "rwsem.h"
 
 struct thread_stack;
 struct unwind_libunwind_ops;
@@ -30,7 +31,9 @@ struct thread {
         int                     comm_len;
         bool                    dead; /* if set thread has exited */
         struct list_head        namespaces_list;
+        struct rw_semaphore     namespaces_lock;
         struct list_head        comm_list;
+        struct rw_semaphore     comm_lock;
         u64                     db_id;
 
         void                    *priv;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index be0d5a736dea..3e1038f6491c 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -92,7 +92,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
         return threads;
 }
 
-struct thread_map *thread_map__new_by_uid(uid_t uid)
+static struct thread_map *__thread_map__new_all_cpus(uid_t uid)
 {
         DIR *proc;
         int max_threads = 32, items, i;
@@ -113,7 +113,6 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
         while ((dirent = readdir(proc)) != NULL) {
                 char *end;
                 bool grow = false;
-                struct stat st;
                 pid_t pid = strtol(dirent->d_name, &end, 10);
 
                 if (*end) /* only interested in proper numerical dirents */
@@ -121,11 +120,12 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 
                 snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
-                if (stat(path, &st) != 0)
-                        continue;
+                if (uid != UINT_MAX) {
+                        struct stat st;
 
-                if (st.st_uid != uid)
-                        continue;
+                        if (stat(path, &st) != 0 || st.st_uid != uid)
+                                continue;
+                }
 
                 snprintf(path, sizeof(path), "/proc/%d/task", pid);
                 items = scandir(path, &namelist, filter, NULL);
@@ -178,6 +178,16 @@ out_free_closedir:
         goto out_closedir;
 }
 
+struct thread_map *thread_map__new_all_cpus(void)
+{
+        return __thread_map__new_all_cpus(UINT_MAX);
+}
+
+struct thread_map *thread_map__new_by_uid(uid_t uid)
+{
+        return __thread_map__new_all_cpus(uid);
+}
+
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid)
 {
         if (pid != -1)
@@ -313,7 +323,7 @@ out_free_threads:
 }
 
 struct thread_map *thread_map__new_str(const char *pid, const char *tid,
-                                       uid_t uid)
+                                       uid_t uid, bool per_thread)
 {
         if (pid)
                 return thread_map__new_by_pid_str(pid);
@@ -321,6 +331,9 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
         if (!tid && uid != UINT_MAX)
                 return thread_map__new_by_uid(uid);
 
+        if (per_thread)
+                return thread_map__new_all_cpus();
+
         return thread_map__new_by_tid_str(tid);
 }
 
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index f15803985435..0a806b99e73c 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -23,6 +23,7 @@ struct thread_map *thread_map__new_dummy(void);
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
+struct thread_map *thread_map__new_all_cpus(void);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 struct thread_map *thread_map__new_event(struct thread_map_event *event);
 
@@ -30,7 +31,7 @@ struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
 
 struct thread_map *thread_map__new_str(const char *pid,
-                const char *tid, uid_t uid);
+                const char *tid, uid_t uid, bool per_thread);
 
 struct thread_map *thread_map__new_by_tid_str(const char *tid_str);
 
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 81927d027417..6193b46050a5 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -6,6 +6,7 @@
 #include <time.h>
 #include <errno.h>
 #include <inttypes.h>
+#include <math.h>
 
 #include "perf.h"
 #include "debug.h"
@@ -60,11 +61,10 @@ static int parse_timestr_sec_nsec(struct perf_time_interval *ptime,
         return 0;
 }
 
-int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr)
+static int split_start_end(char **start, char **end, const char *ostr, char ch)
 {
         char *start_str, *end_str;
         char *d, *str;
-        int rc = 0;
 
         if (ostr == NULL || *ostr == '\0')
                 return 0;
@@ -74,25 +74,35 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr)
         if (str == NULL)
                 return -ENOMEM;
 
-        ptime->start = 0;
-        ptime->end = 0;
-
-        /* str has the format: <start>,<stop>
-         * variations: <start>,
-         *             ,<stop>
-         *             ,
-         */
         start_str = str;
-        d = strchr(start_str, ',');
+        d = strchr(start_str, ch);
         if (d) {
                 *d = '\0';
                 ++d;
         }
         end_str = d;
 
+        *start = start_str;
+        *end = end_str;
+
+        return 0;
+}
+
+int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr)
+{
+        char *start_str = NULL, *end_str;
+        int rc;
+
+        rc = split_start_end(&start_str, &end_str, ostr, ',');
+        if (rc || !start_str)
+                return rc;
+
+        ptime->start = 0;
+        ptime->end = 0;
+
         rc = parse_timestr_sec_nsec(ptime, start_str, end_str);
 
-        free(str);
+        free(start_str);
 
         /* make sure end time is after start time if it was given */
         if (rc == 0 && ptime->end && ptime->end < ptime->start)
@@ -104,6 +114,245 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr)
         return rc;
 }
 
+static int parse_percent(double *pcnt, char *str)
+{
+        char *c, *endptr;
+        double d;
+
+        c = strchr(str, '%');
+        if (c)
+                *c = '\0';
+        else
+                return -1;
+
+        d = strtod(str, &endptr);
+        if (endptr != str + strlen(str))
+                return -1;
+
+        *pcnt = d / 100.0;
+        return 0;
+}
+
+static int percent_slash_split(char *str, struct perf_time_interval *ptime,
+                               u64 start, u64 end)
+{
+        char *p, *end_str;
+        double pcnt, start_pcnt, end_pcnt;
+        u64 total = end - start;
+        int i;
+
+        /*
+         * Example:
+         * 10%/2: select the second 10% slice and the third 10% slice
+         */
+
+        /* We can modify this string since the original one is copied */
+        p = strchr(str, '/');
+        if (!p)
+                return -1;
+
+        *p = '\0';
+        if (parse_percent(&pcnt, str) < 0)
+                return -1;
+
+        p++;
+        i = (int)strtol(p, &end_str, 10);
+        if (*end_str)
+                return -1;
+
+        if (pcnt <= 0.0)
+                return -1;
+
+        start_pcnt = pcnt * (i - 1);
+        end_pcnt = pcnt * i;
+
+        if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
+            end_pcnt < 0.0 || end_pcnt > 1.0) {
+                return -1;
+        }
+
+        ptime->start = start + round(start_pcnt * total);
+        ptime->end = start + round(end_pcnt * total);
+
+        return 0;
+}
+
+static int percent_dash_split(char *str, struct perf_time_interval *ptime,
+                              u64 start, u64 end)
+{
+        char *start_str = NULL, *end_str;
+        double start_pcnt, end_pcnt;
+        u64 total = end - start;
+        int ret;
+
+        /*
+         * Example: 0%-10%
+         */
+
+        ret = split_start_end(&start_str, &end_str, str, '-');
+        if (ret || !start_str)
+                return ret;
+
+        if ((parse_percent(&start_pcnt, start_str) != 0) ||
+            (parse_percent(&end_pcnt, end_str) != 0)) {
+                free(start_str);
+                return -1;
+        }
+
+        free(start_str);
+
+        if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
+            end_pcnt < 0.0 || end_pcnt > 1.0 ||
+            start_pcnt > end_pcnt) {
+                return -1;
+        }
+
+        ptime->start = start + round(start_pcnt * total);
+        ptime->end = start + round(end_pcnt * total);
+
+        return 0;
+}
+
+typedef int (*time_pecent_split)(char *, struct perf_time_interval *,
+                                 u64 start, u64 end);
+
+static int percent_comma_split(struct perf_time_interval *ptime_buf, int num,
+                               const char *ostr, u64 start, u64 end,
+                               time_pecent_split func)
+{
+        char *str, *p1, *p2;
+        int len, ret, i = 0;
+
+        str = strdup(ostr);
+        if (str == NULL)
+                return -ENOMEM;
+
+        len = strlen(str);
+        p1 = str;
+
+        while (p1 < str + len) {
+                if (i >= num) {
+                        free(str);
+                        return -1;
+                }
+
+                p2 = strchr(p1, ',');
+                if (p2)
+                        *p2 = '\0';
+
+                ret = (func)(p1, &ptime_buf[i], start, end);
+                if (ret < 0) {
+                        free(str);
+                        return -1;
+                }
+
+                pr_debug("start time %d: %" PRIu64 ", ", i, ptime_buf[i].start);
+                pr_debug("end time %d: %" PRIu64 "\n", i, ptime_buf[i].end);
+
+                i++;
+
+                if (p2)
+                        p1 = p2 + 1;
+                else
+                        break;
+        }
+
+        free(str);
+        return i;
+}
+
+static int one_percent_convert(struct perf_time_interval *ptime_buf,
+                               const char *ostr, u64 start, u64 end, char *c)
+{
+        char *str;
+        int len = strlen(ostr), ret;
+
+        /*
+         * c points to '%'.
+         * '%' should be the last character
+         */
+        if (ostr + len - 1 != c)
+                return -1;
+
+        /*
+         * Construct a string like "xx%/1"
+         */
+        str = malloc(len + 3);
+        if (str == NULL)
+                return -ENOMEM;
+
+        memcpy(str, ostr, len);
+        strcpy(str + len, "/1");
+
+        ret = percent_slash_split(str, ptime_buf, start, end);
+        if (ret == 0)
+                ret = 1;
+
+        free(str);
+        return ret;
+}
+
+int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num,
+                                 const char *ostr, u64 start, u64 end)
+{
+        char *c;
+
+        /*
+         * ostr example:
+         * 10%/2,10%/3: select the second 10% slice and the third 10% slice
+         * 0%-10%,30%-40%: multiple time range
+         * 50%: just one percent
+         */
+
+        memset(ptime_buf, 0, sizeof(*ptime_buf) * num);
+
+        c = strchr(ostr, '/');
+        if (c) {
+                return percent_comma_split(ptime_buf, num, ostr, start,
+                                           end, percent_slash_split);
+        }
+
+        c = strchr(ostr, '-');
+        if (c) {
+                return percent_comma_split(ptime_buf, num, ostr, start,
+                                           end, percent_dash_split);
+        }
+
+        c = strchr(ostr, '%');
+        if (c)
+                return one_percent_convert(ptime_buf, ostr, start, end, c);
+
+        return -1;
+}
+
+struct perf_time_interval *perf_time__range_alloc(const char *ostr, int *size)
+{
+        const char *p1, *p2;
+        int i = 1;
+        struct perf_time_interval *ptime;
+
+        /*
+         * At least allocate one time range.
+         */
+        if (!ostr)
+                goto alloc;
+
+        p1 = ostr;
+        while (p1 < ostr + strlen(ostr)) {
+                p2 = strchr(p1, ',');
+                if (!p2)
+                        break;
+
+                p1 = p2 + 1;
+                i++;
+        }
+
+alloc:
+        *size = i;
+        ptime = calloc(i, sizeof(*ptime));
+        return ptime;
+}
+
 bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp)
 {
         /* if time is not set don't drop sample */
@@ -119,6 +368,34 @@ bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp)
         return false;
 }
 
+bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
+                                   int num, u64 timestamp)
+{
+        struct perf_time_interval *ptime;
+        int i;
+
+        if ((timestamp == 0) || (num == 0))
+                return false;
+
+        if (num == 1)
+                return perf_time__skip_sample(&ptime_buf[0], timestamp);
+
+        /*
+         * start/end of multiple time ranges must be valid.
+         */
+        for (i = 0; i < num; i++) {
+                ptime = &ptime_buf[i];
+
+                if (timestamp >= ptime->start &&
+                    ((timestamp < ptime->end && i < num - 1) ||
+                     (timestamp <= ptime->end && i == num - 1))) {
+                        break;
+                }
+        }
+
+        return (i == num) ? true : false;
+}
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
 {
         u64  sec = timestamp / NSEC_PER_SEC;
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 15b475c50ccf..70b177d2b98c 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -13,8 +13,16 @@ int parse_nsec_time(const char *str, u64 *ptime);
 
 int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr);
 
+int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num,
+                                 const char *ostr, u64 start, u64 end);
+
+struct perf_time_interval *perf_time__range_alloc(const char *ostr, int *size);
+
 bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp);
 
+bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
+                                   int num, u64 timestamp);
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
 
 int fetch_current_timestamp(char *buf, size_t sz);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 2532b558099b..183c91453522 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -76,6 +76,7 @@ struct perf_tool {
         bool            ordered_events;
         bool            ordering_requires_timestamps;
         bool            namespace_events;
+        bool            no_warn;
         enum show_feature_header show_feat_hdr;
 };
 
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 506150a75bd0..9892323cdd7c 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -38,6 +38,7 @@ struct perf_top {
         int                sym_pcnt_filter;
         const char         *sym_filter;
         float              min_percent;
+        unsigned int       nr_threads_synthesize;
 };
 
 #define CONSOLE_CLEAR ""
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index e7d60d05596d..d7f2113462fb 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -28,7 +28,6 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 8a9a677f7576..40b425949aa3 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -27,7 +27,6 @@
 #include <sys/stat.h>
 #include <sys/wait.h>
 #include <sys/mman.h>
-#include <pthread.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 7a42f703e858..af873044d33a 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -631,9 +631,8 @@ static unw_accessors_t accessors = {
 
 static int _unwind__prepare_access(struct thread *thread)
 {
-        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+        if (!dwarf_callchain_users)
                 return 0;
-
         thread->addr_space = unw_create_addr_space(&accessors, 0);
         if (!thread->addr_space) {
                 pr_err("unwind: Can't create unwind address space.\n");
@@ -646,17 +645,15 @@ static int _unwind__prepare_access(struct thread *thread)
 
 static void _unwind__flush_access(struct thread *thread)
 {
-        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+        if (!dwarf_callchain_users)
                 return;
-
         unw_flush_cache(thread->addr_space, 0, 0);
 }
 
 static void _unwind__finish_access(struct thread *thread)
 {
-        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+        if (!dwarf_callchain_users)
                 return;
-
         unw_destroy_addr_space(thread->addr_space);
 }
 
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 647a1e6b4c7b..b029a5e9ae49 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -3,7 +3,7 @@
 #include "thread.h"
 #include "session.h"
 #include "debug.h"
-#include "arch/common.h"
+#include "env.h"
 
 struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;
@@ -39,7 +39,7 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
         if (dso_type == DSO__TYPE_UNKNOWN)
                 return 0;
 
-        arch = normalize_arch(thread->mg->machine->env->arch);
+        arch = perf_env__arch(thread->mg->machine->env);
 
         if (!strcmp(arch, "x86")) {
                 if (dso_type != DSO__TYPE_64BIT)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 3687b720327a..1019bbc5dbd8 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -7,6 +7,7 @@
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <dirent.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <signal.h>
 #include <stdio.h>
@@ -23,6 +24,19 @@
 /*
  * XXX We need to find a better place for these things...
  */
+
+bool perf_singlethreaded = true;
+
+void perf_set_singlethreaded(void)
+{
+        perf_singlethreaded = true;
+}
+
+void perf_set_multithreaded(void)
+{
+        perf_singlethreaded = false;
+}
+
 unsigned int page_size;
 int cacheline_size;
 
@@ -175,7 +189,7 @@ out:
         return err;
 }
 
-int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
         void *ptr;
         loff_t pgoff;
@@ -196,7 +210,7 @@ int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 
                 size -= ret;
                 off_in += ret;
-                off_out -= ret;
+                off_out += ret;
         }
         munmap(ptr, off_in + size);
 
@@ -326,35 +340,15 @@ size_t hex_width(u64 v)
         return n;
 }
 
-static int hex(char ch)
-{
-        if ((ch >= '0') && (ch <= '9'))
-                return ch - '0';
-        if ((ch >= 'a') && (ch <= 'f'))
-                return ch - 'a' + 10;
-        if ((ch >= 'A') && (ch <= 'F'))
-                return ch - 'A' + 10;
-        return -1;
-}
-
 /*
  * While we find nice hex chars, build a long_val.
  * Return number of chars processed.
  */
 int hex2u64(const char *ptr, u64 *long_val)
 {
-        const char *p = ptr;
-        *long_val = 0;
-
-        while (*p) {
-                const int hex_val = hex(*p);
+        char *p;
 
-                if (hex_val < 0)
-                        break;
-
-                *long_val = (*long_val << 4) | hex_val;
-                p++;
-        }
+        *long_val = strtoull(ptr, &p, 16);
 
         return p - ptr;
 }
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b52765e6d7b4..9496365da3d7 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,7 +6,6 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
-#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -36,7 +35,6 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
-int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);
@@ -65,4 +63,19 @@ int sched_getcpu(void);
 int setns(int fd, int nstype);
 #endif
 
+extern bool perf_singlethreaded;
+
+void perf_set_singlethreaded(void);
+void perf_set_multithreaded(void);
+
+#ifndef O_CLOEXEC
+#ifdef __sparc__
+#define O_CLOEXEC      0x400000
+#elif defined(__alpha__) || defined(__hppa__)
+#define O_CLOEXEC      010000000
+#else
+#define O_CLOEXEC      02000000
+#endif
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index cffcda448c28..0acb1ec0e2f0 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -320,7 +320,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
         struct vdso_info *vdso_info;
         struct dso *dso = NULL;
 
-        pthread_rwlock_wrlock(&machine->dsos.lock);
+        down_write(&machine->dsos.lock);
         if (!machine->vdso_info)
                 machine->vdso_info = vdso_info__new();
 
@@ -348,7 +348,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 
 out_unlock:
         dso__get(dso);
-        pthread_rwlock_unlock(&machine->dsos.lock);
+        up_write(&machine->dsos.lock);
         return dso;
 }
 
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 008fe68d7b76..a725b958cf31 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/stat.h>