3 files changed, 233 insertions, 145 deletions

diff --git a/smt_analysis/computeLCslowdown.py b/smt_analysis/computeLCslowdown.py
new file mode 100755
index 0000000..bcd22da
--- /dev/null
+++ b/smt_analysis/computeLCslowdown.py
@@ -0,0 +1,73 @@
+#!/usr/bin/python3
+import numpy as np
+import sys
+import plotille.plotille as plt
+from libSMT import *
+TIMING_ERROR = 1000 #ns
+ASYNC_FORMAT = False
+
+def print_usage():
+    print("This program takes in the all-pairs and baseline SMT data and computes the worst-case slowdown against any other task when SMT is enabled.", file=sys.stderr)
+    print("Level-A/B usage: {} <file -A> <file -B> <baseline file>".format(sys.argv[0]), file=sys.stderr)
+    print("Level-C usage: {} <continuous pairs> <baseline file>".format(sys.argv[0]), file=sys.stderr)
+
+# Check that we got the right number of parameters
+if len(sys.argv) < 3:
+    print_usage()
+    exit()
+
+if len(sys.argv) > 3:
+    print("Reading file using synchronous pair format...")
+    print("Are you sure you want to do this? For the RTAS'21 paper, L-A/-B pairs should use the other script.")
+    input("Press enter to continue, Ctrl+C to exit...")
+else:
+    print("Reading file using asynchronous pair format...")
+    ASYNC_FORMAT = True
+
+assert_valid_input_files(sys.argv[1:-1], print_usage)
+
+# Pull in the data
+if not ASYNC_FORMAT:
+    baseline_times, baseline_sample_cnt, baseline_max_times = load_baseline(sys.argv[3])
+    paired_times, paired_offsets, name_to_idx, idx_to_name = load_paired(sys.argv[1], sys.argv[2], len(list(baseline_times.keys())))
+    for key in baseline_times:
+        print(key,max(baseline_times[key]))
+else:
+    baseline_times, baseline_sample_cnt, baseline_max_times = load_baseline(sys.argv[2])
+    paired_times, name_to_idx, idx_to_name = load_fake_paired(sys.argv[1])
+
+# We work iff the baseline was run for the same set of benchmarks as the pairs were
+assert_base_and_pair_keys_match(baseline_times, name_to_idx)
+
+# Only consider benchmarks that are at least an order of magnitude longer than the timing error
+reliableNames = []
+for i in range(0, len(name_to_idx)):
+    benchmark = idx_to_name[i]
+    if min(baseline_times[benchmark]) > TIMING_ERROR * 10:
+        reliableNames.append(benchmark)
+
+# Compute worst-case SMT slowdown for each benchmark
+print("Bench           Mi")
+# Print rows
+sample_f = np.mean # Change this to np.mean to use mean values in Mi generation
+M_vals = []
+for b1 in reliableNames:
+    print("{:<14.14}:".format(b1), end=" ")
+    max_mi = 0
+    # Scan through everyone we ran against and find our maximum slowdown
+    for b2 in reliableNames:
+        time_with_smt = sample_f(paired_times[name_to_idx[b1]][name_to_idx[b2]])
+        time_wout_smt = sample_f(baseline_times[b1])
+        M = time_with_smt / time_wout_smt
+        max_mi = max(max_mi, M)
+    print("{:>10.3}".format(max_mi), end=" ")
+    M_vals.append(max_mi)
+    print("")
+# Print some statistics about the distribution
+print("Average: {:>5.3} with standard deviation {:>5.3} using `{}`".format(np.mean(M_vals), np.std(M_vals), sample_f.__name__))
+Ms = np.asarray(M_vals, dtype=np.float32)
+print(np.sum(Ms <= 1), "of", len(M_vals), "M_i values are at most one -", 100*np.sum(Ms <= 1)/len(M_vals), "percent")
+print(np.sum(Ms > 2), "of", len(M_vals), "M_i values are greater than two -", 100*np.sum(Ms > 2)/len(M_vals), "percent")
+M_vals_to_plot = Ms
+
+print(plt.hist(M_vals_to_plot, bins=10))
diff --git a/smt_analysis/computeSMTslowdown.py b/smt_analysis/computeSMTslowdown.py
index aa7aa21..805def1 100755
--- a/smt_analysis/computeSMTslowdown.py
+++ b/smt_analysis/computeSMTslowdown.py
@@ -3,19 +3,19 @@ from typing import List, Any
 import numpy as np
 from scipy import stats
 import sys
-import os
 import plotille.plotille as plt
 TIMING_ERROR = 1000 #ns
 LEVEL_C_ANALYSIS = False
+from libSMT import *
 
-def print_usage(argv):
+def print_usage():
     print("This program takes in the all-pairs and baseline SMT data and computes how much each program is slowed when SMT in enabled.", file=sys.stderr)
-    print("Level-A/B usage: {} <file -A> <file -B> <baseline file> --cij".format(argv[0]), file=sys.stderr)
-    print("Level-C usage: {} <continuous pairs> <baseline file>".format(argv[0]), file=sys.stderr)
+    print("Level-A/B usage: {} <file -A> <file -B> <baseline file> --cij".format(sys.argv[0]), file=sys.stderr)
+    print("Level-C usage: {} <continuous pairs> <baseline file>".format(sys.argv[0]), file=sys.stderr)
 
 # Check that we got the right number of parameters
 if len(sys.argv) < 3:
-    print_usage(sys.argv)
+    print_usage()
     exit()
 
 if len(sys.argv) > 3:
@@ -24,127 +24,12 @@ else:
     print("Analyzing results using Level-C methodology...")
     LEVEL_C_ANALYSIS = True
 
-# Check that all input files are valid
-for f in sys.argv[1:-1]:
-    if not os.path.exists(f) or os.path.getsize(f) == 0:
-        print("ERROR: File '{}' does not exist or is empty".format(f), file=sys.stderr);
-        print_usage(sys.argv)
-        exit()
+assert_valid_input_files(sys.argv[1:-1], print_usage);
 
 # Print Cij values rather than Mij
 TIMES_ONLY = len(sys.argv) > 4 and "--cij" in sys.argv[4]
 OK_PAIRS_ONLY = len(sys.argv) > 4 and "--cij-ok" in sys.argv[4]
 
-# This parses the result data from unthreaded timing experiments
-# @param f File name to load
-# @returns res Map of benchmark name to sample count
-# @returns samples Map of benchmark name to list of execution time samples
-# @returns max_res May of benchmark to maximum execution time among all samples for that benchmark
-def load_baseline(f):
-    # constants for columns of baseline data files
-    TOTAL_NS = 5
-    BENCH_NAME = 0
-    SAMPLES = 4
-
-    # Load baseline data. This logic is based off the summarize programs
-    res = {} # Map of benchmark to list of all execution time samples
-    samples = {} # Map of benchmark name to sample count
-    max_res = {} # Map of benchmark name to maximum execution time
-
-    with open(f) as fp:
-        for line in fp:
-            s = line.split()
-            if s[BENCH_NAME] not in res:
-                res[s[BENCH_NAME]] = list([int(s[TOTAL_NS])])
-                samples[s[BENCH_NAME]] = int(s[SAMPLES])
-                max_res[s[BENCH_NAME]] = int(s[TOTAL_NS])
-            else:
-                res[s[BENCH_NAME]].append(int(s[TOTAL_NS]))
-                max_res[s[BENCH_NAME]] = max(int(s[TOTAL_NS]), max_res[s[BENCH_NAME]])
-    return res, samples, max_res
-
-# This parses the result data from paired, threaded timing experiements
-# @param file1 The -A file name
-# @param file2 The -B file name
-# @returns time 2D array of benchmark IDs to list of total container execution times
-# @returns offset 2D array of benchmark IDs to list of differences between the start
-#                 of the first and the start of the second benchmark
-# @returns name_to_idx Map of benchmark names to benchmark IDs
-# @returns idx_to_name List which when indexed with benchmark ID will yield the benchmark name
-def load_paired(file1, file2, benchmarkCount):
-    # constants for columns of paired data files
-    FIRST_PROG = 0
-    SECOND_PROG = 1
-    FIRST_CORE = 2
-    SECOND_CORE = 3
-    TRIALS = 4
-    START_S = 5 # Start seconds
-    START_N = 6 # Start nanoseconds
-    END_S = 7   # End seconds
-    END_N = 8   # End nanoseconds
-    RUN_ID = 9
-    JOB_NUM = 10
-
-    with open(file1) as f1:
-        numJobs = int(f1.readline().split()[TRIALS])
-    assert numJobs > 0
-    assert benchmarkCount > 0
-
-    # Total times of each container
-    time=[[[0 for x in range(numJobs)]for y in range(benchmarkCount)]for z in range(benchmarkCount)]
-    # Difference in time between when the first and the second task start in the container
-    offset=[[[0 for x in range(numJobs)]for y in range(benchmarkCount)]for z in range(benchmarkCount)]
-
-    # Some aggregate counters that we update as we go along
-    avg_off = 0
-    avg_off_samp = 0
-
-    # Load paired data
-    bench1 = 0 # Index to what's the current first benchmark being examined
-    bench2 = 0 # Index to what's the current second benchmark being examined
-
-    name_to_idx = {}