x86: Add optimized popcnt variants

Add support for the hardware version of the Hamming weight function,
popcnt, present in CPUs which advertize it under CPUID, Function
0x0000_0001_ECX[23]. On CPUs which don't support it, we fallback to the
default lib/hweight.c sw versions.

A synthetic benchmark comparing popcnt with __sw_hweight64 showed almost
a 3x speedup on a F10h machine.

Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <20100318112015.GC11152@aftab>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

1 files changed, 5 insertions, 0 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0eacb1ffb421..89d8c54cdd37 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -238,6 +238,11 @@ config X86_32_LAZY_GS
         def_bool y
         depends on X86_32 && !CC_STACKPROTECTOR
 
+config ARCH_HWEIGHT_CFLAGS
+        string
+        default "-fcall-saved-ecx -fcall-saved-edx" if X86_32
+        default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64
+
 config KTIME_SCALAR
         def_bool X86_32
 source "init/Kconfig"