ich777/linux_media
1
0
Fork 0
mirror of https://github.com/tbsdtv/linux_media.git synced 2025-07-23 12:43:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

x86: Add optimized popcnt variants

Browse Source 
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>
This commit is contained in:
Borislav Petkov
2010-03-05 17:34:46 +01:00
committed by H. Peter Anvin
parent 1527bc8b92
commit d61931d89b
8 changed files with 108 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
lib/hweight.c
View File

@@ -9,7 +9,7 @@
* The Hamming Weight of a number is the total number of bits set in it.
*/
unsigned int __arch_hweight32(unsigned int w)
unsigned int __sw_hweight32(unsigned int w)
{
#ifdef ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x55555555;
@@ -24,30 +24,30 @@ unsigned int __arch_hweight32(unsigned int w)
return (res + (res >> 16)) & 0x000000FF;
#endif
}
EXPORT_SYMBOL(__arch_hweight32);
EXPORT_SYMBOL(__sw_hweight32);
unsigned int __arch_hweight16(unsigned int w)
unsigned int __sw_hweight16(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x5555);
res = (res & 0x3333) + ((res >> 2) & 0x3333);
res = (res + (res >> 4)) & 0x0F0F;
return (res + (res >> 8)) & 0x00FF;
}
EXPORT_SYMBOL(__arch_hweight16);
EXPORT_SYMBOL(__sw_hweight16);
unsigned int __arch_hweight8(unsigned int w)
unsigned int __sw_hweight8(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x55);
res = (res & 0x33) + ((res >> 2) & 0x33);
return (res + (res >> 4)) & 0x0F;
}
EXPORT_SYMBOL(__arch_hweight8);
EXPORT_SYMBOL(__sw_hweight8);
unsigned long __arch_hweight64(__u64 w)
unsigned long __sw_hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
return __arch_hweight32((unsigned int)(w >> 32)) +
__arch_hweight32((unsigned int)w);
return __sw_hweight32((unsigned int)(w >> 32)) +
__sw_hweight32((unsigned int)w);
#elif BITS_PER_LONG == 64
#ifdef ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x5555555555555555ul;
@@ -64,4 +64,4 @@ unsigned long __arch_hweight64(__u64 w)
#endif
#endif
}
EXPORT_SYMBOL(__arch_hweight64);
EXPORT_SYMBOL(__sw_hweight64);