diff options
| author | Borislav Petkov <borislav.petkov@amd.com> | 2010-03-05 17:34:46 +0100 |
|---|---|---|
| committer | H. Peter Anvin <hpa@zytor.com> | 2010-04-06 15:52:11 -0700 |
| commit | d61931d89be506372d01a90d1755f6d0a9fafe2d (patch) | |
| tree | 652c34238edcb6c558163abc3cd9d6ce7c5f91a5 /lib | |
| parent | 1527bc8b928dd1399c3d3467dd47d9ede210978a (diff) | |
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>
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Makefile | 3 | ||||
| -rw-r--r-- | lib/hweight.c | 20 |
2 files changed, 13 insertions, 10 deletions
diff --git a/lib/Makefile b/lib/Makefile index 2e152aed7198..abe63a8ad143 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -39,7 +39,10 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o obj-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o + +CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS)) obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o + obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o obj-$(CONFIG_BTREE) += btree.o obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o diff --git a/lib/hweight.c b/lib/hweight.c index a6927e76840f..3c79d50814cf 100644 --- a/lib/hweight.c +++ b/lib/hweight.c @@ -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); |