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 /arch/x86/include/asm | |
| 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 'arch/x86/include/asm')
| -rw-r--r-- | arch/x86/include/asm/alternative.h | 9 | ||||
| -rw-r--r-- | arch/x86/include/asm/arch_hweight.h | 59 | ||||
| -rw-r--r-- | arch/x86/include/asm/bitops.h | 4 |
3 files changed, 68 insertions, 4 deletions
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index b09ec55650b..67dae51e7fd 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -39,9 +39,6 @@ #define LOCK_PREFIX "" #endif -/* This must be included *after* the definition of LOCK_PREFIX */ -#include <asm/cpufeature.h> - struct alt_instr { u8 *instr; /* original instruction */ u8 *replacement; @@ -96,6 +93,12 @@ static inline int alternatives_text_reserved(void *start, void *end) ".previous" /* + * This must be included *after* the definition of ALTERNATIVE due to + * <asm/arch_hweight.h> + */ +#include <asm/cpufeature.h> + +/* * Alternative instructions for different CPU types or capabilities. * * This allows to use optimized instructions even on generic binary diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h new file mode 100644 index 00000000000..d1fc3c219ae --- /dev/null +++ b/arch/x86/include/asm/arch_hweight.h @@ -0,0 +1,59 @@ +#ifndef _ASM_X86_HWEIGHT_H +#define _ASM_X86_HWEIGHT_H + +#ifdef CONFIG_64BIT +/* popcnt %rdi, %rax */ +#define POPCNT ".byte 0xf3,0x48,0x0f,0xb8,0xc7" +#define REG_IN "D" +#define REG_OUT "a" +#else +/* popcnt %eax, %eax */ +#define POPCNT ".byte 0xf3,0x0f,0xb8,0xc0" +#define REG_IN "a" +#define REG_OUT "a" +#endif + +/* + * __sw_hweightXX are called from within the alternatives below + * and callee-clobbered registers need to be taken care of. See + * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective + * compiler switches. + */ +static inline unsigned int __arch_hweight32(unsigned int w) +{ + unsigned int res = 0; + + asm (ALTERNATIVE("call __sw_hweight32", POPCNT, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); + + return res; +} + +static inline unsigned int __arch_hweight16(unsigned int w) +{ + return __arch_hweight32(w & 0xffff); +} + +static inline unsigned int __arch_hweight8(unsigned int w) +{ + return __arch_hweight32(w & 0xff); +} + +static inline unsigned long __arch_hweight64(__u64 w) +{ + unsigned long res = 0; + +#ifdef CONFIG_X86_32 + return __arch_hweight32((u32)w) + + __arch_hweight32((u32)(w >> 32)); +#else + asm (ALTERNATIVE("call __sw_hweight64", POPCNT, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); +#endif /* CONFIG_X86_32 */ + + return res; +} + +#endif diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 02b47a603fc..545776efeb1 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -444,7 +444,9 @@ static inline int fls(int x) #define ARCH_HAS_FAST_MULTIPLIER 1 -#include <asm-generic/bitops/hweight.h> +#include <asm/arch_hweight.h> + +#include <asm-generic/bitops/const_hweight.h> #endif /* __KERNEL__ */ |