linux/arch/x86/include/asm/arch_hweight.h
Borislav Petkov d61931d89b 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>
2010-04-06 15:52:11 -07:00

60 lines
1.3 KiB
C

#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