From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755702Ab0BDK10 (ORCPT ); Thu, 4 Feb 2010 05:27:26 -0500 Received: from casper.infradead.org ([85.118.1.10]:49183 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751606Ab0BDK1X (ORCPT ); Thu, 4 Feb 2010 05:27:23 -0500 Subject: [PATCH] bitops: Optimize hweight() by making use of compile-time evaluation From: Peter Zijlstra To: mingo@redhat.com, hpa@zytor.com, linux-kernel@vger.kernel.org, akpm@linux-foundation.org, torvalds@linux-foundation.org, tglx@linutronix.de, mingo@elte.hu Cc: linux-tip-commits@vger.kernel.org In-Reply-To: References:

Content-Type: text/plain; charset="UTF-8" Date: Thu, 04 Feb 2010 11:27:08 +0100 Message-ID: <1265279228.24455.1816.camel@laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.28.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Andrew, Ingo suggested you take this patch through -mm since it touches !x86 arch bits. It should apply nicely once fce877e3a429940a986e085a41e8b57f2d922e36 makes in into -next. --- Subject: bitops: Optimize hweight() by making use of compile-time evaluation From: Peter Zijlstra Date: Mon Feb 01 15:03:07 CET 2010 Rename the extisting runtime hweight() implementations to __arch_hweight(), rename the compile-time versions to __const_hweight() and then have hweight() pick between them. Suggested-by: H. Peter Anvin Signed-off-by: Peter Zijlstra Acked-by: H. Peter Anvin LKML-Reference: <1265028224.24455.154.camel@laptop> --- arch/alpha/include/asm/bitops.h | 18 ++++++------ arch/ia64/include/asm/bitops.h | 11 ++++--- arch/sparc/include/asm/bitops_64.h | 11 ++++--- include/asm-generic/bitops/arch_hweight.h | 11 +++++++ include/asm-generic/bitops/const_hweight.h | 42 +++++++++++++++++++++++++++++ include/asm-generic/bitops/hweight.h | 8 +---- include/linux/bitops.h | 25 ----------------- lib/hweight.c | 19 ++++++------- 8 files changed, 87 insertions(+), 58 deletions(-) Index: linux-2.6/arch/alpha/include/asm/bitops.h =================================================================== --- linux-2.6.orig/arch/alpha/include/asm/bitops.h +++ linux-2.6/arch/alpha/include/asm/bitops.h @@ -405,29 +405,31 @@ static inline int fls(int x) #if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) /* Whee. EV67 can calculate it directly. */ -static inline unsigned long hweight64(unsigned long w) +static inline unsigned long __arch_hweight64(unsigned long w) { return __kernel_ctpop(w); } -static inline unsigned int hweight32(unsigned int w) +static inline unsigned int __arch_weight32(unsigned int w) { - return hweight64(w); + return __arch_hweight64(w); } -static inline unsigned int hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { - return hweight64(w & 0xffff); + return __arch_hweight64(w & 0xffff); } -static inline unsigned int hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { - return hweight64(w & 0xff); + return __arch_hweight64(w & 0xff); } #else -#include +#include #endif +#include + #endif /* __KERNEL__ */ #include Index: linux-2.6/arch/ia64/include/asm/bitops.h =================================================================== --- linux-2.6.orig/arch/ia64/include/asm/bitops.h +++ linux-2.6/arch/ia64/include/asm/bitops.h @@ -437,17 +437,18 @@ __fls (unsigned long x) * hweightN: returns the hamming weight (i.e. the number * of bits set) of a N-bit word */ -static __inline__ unsigned long -hweight64 (unsigned long x) +static __inline__ unsigned long __arch_hweight64(unsigned long x) { unsigned long result; result = ia64_popcnt(x); return result; } -#define hweight32(x) (unsigned int) hweight64((x) & 0xfffffffful) -#define hweight16(x) (unsigned int) hweight64((x) & 0xfffful) -#define hweight8(x) (unsigned int) hweight64((x) & 0xfful) +#define __arch_hweight32(x) ((unsigned int) __arch_hweight64((x) & 0xfffffffful)) +#define __arch_hweight16(x) ((unsigned int) __arch_hweight64((x) & 0xfffful)) +#define __arch_hweight8(x) ((unsigned int) __arch_hweight64((x) & 0xfful)) + +#include #endif /* __KERNEL__ */ Index: linux-2.6/arch/sparc/include/asm/bitops_64.h =================================================================== --- linux-2.6.orig/arch/sparc/include/asm/bitops_64.h +++ linux-2.6/arch/sparc/include/asm/bitops_64.h @@ -44,7 +44,7 @@ extern void change_bit(unsigned long nr, #ifdef ULTRA_HAS_POPULATION_COUNT -static inline unsigned int hweight64(unsigned long w) +static inline unsigned int __arch_hweight64(unsigned long w) { unsigned int res; @@ -52,7 +52,7 @@ static inline unsigned int hweight64(uns return res; } -static inline unsigned int hweight32(unsigned int w) +static inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res; @@ -60,7 +60,7 @@ static inline unsigned int hweight32(uns return res; } -static inline unsigned int hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { unsigned int res; @@ -68,7 +68,7 @@ static inline unsigned int hweight16(uns return res; } -static inline unsigned int hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { unsigned int res; @@ -78,9 +78,10 @@ static inline unsigned int hweight8(unsi #else -#include +#include #endif +#include #include #endif /* __KERNEL__ */ Index: linux-2.6/include/asm-generic/bitops/arch_hweight.h =================================================================== --- /dev/null +++ linux-2.6/include/asm-generic/bitops/arch_hweight.h @@ -0,0 +1,11 @@ +#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ + +#include + +extern unsigned int __arch_hweight32(unsigned int w); +extern unsigned int __arch_hweight16(unsigned int w); +extern unsigned int __arch_hweight8(unsigned int w); +extern unsigned long __arch_hweight64(__u64 w); + +#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ Index: linux-2.6/include/asm-generic/bitops/const_hweight.h =================================================================== --- /dev/null +++ linux-2.6/include/asm-generic/bitops/const_hweight.h @@ -0,0 +1,42 @@ +#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ + +/* + * Compile time versions of __arch_hweightN() + */ +#define __const_hweight8(w) \ + ( (!!((w) & (1ULL << 0))) + \ + (!!((w) & (1ULL << 1))) + \ + (!!((w) & (1ULL << 2))) + \ + (!!((w) & (1ULL << 3))) + \ + (!!((w) & (1ULL << 4))) + \ + (!!((w) & (1ULL << 5))) + \ + (!!((w) & (1ULL << 6))) + \ + (!!((w) & (1ULL << 7))) ) + +#define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) +#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) +#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) + +/* + * Generic interface. + */ +#define hweight8(w) (__builtin_constant_p(w) ? __const_hweight8(w) : __arch_hweight8(w)) +#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w)) +#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w)) +#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) + +/* + * Interface for known constant arguments + */ +#define HWEIGHT8(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w)) +#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w)) +#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w)) +#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w)) + +/* + * Type invariant interface to the compile time constant hweight functions. + */ +#define HWEIGHT(w) HWEIGHT64((u64)w) + +#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */ Index: linux-2.6/include/asm-generic/bitops/hweight.h =================================================================== --- linux-2.6.orig/include/asm-generic/bitops/hweight.h +++ linux-2.6/include/asm-generic/bitops/hweight.h @@ -1,11 +1,7 @@ #ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_ #define _ASM_GENERIC_BITOPS_HWEIGHT_H_ -#include - -extern unsigned int hweight32(unsigned int w); -extern unsigned int hweight16(unsigned int w); -extern unsigned int hweight8(unsigned int w); -extern unsigned long hweight64(__u64 w); +#include +#include #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ Index: linux-2.6/include/linux/bitops.h =================================================================== --- linux-2.6.orig/include/linux/bitops.h +++ linux-2.6/include/linux/bitops.h @@ -45,31 +45,6 @@ static inline unsigned long hweight_long return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } -/* - * Clearly slow versions of the hweightN() functions, their benefit is - * of course compile time evaluation of constant arguments. - */ -#define HWEIGHT8(w) \ - ( BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + \ - (!!((w) & (1ULL << 0))) + \ - (!!((w) & (1ULL << 1))) + \ - (!!((w) & (1ULL << 2))) + \ - (!!((w) & (1ULL << 3))) + \ - (!!((w) & (1ULL << 4))) + \ - (!!((w) & (1ULL << 5))) + \ - (!!((w) & (1ULL << 6))) + \ - (!!((w) & (1ULL << 7))) ) - -#define HWEIGHT16(w) (HWEIGHT8(w) + HWEIGHT8((w) >> 8)) -#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16)) -#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32)) - -/* - * Type invariant version that simply casts things to the - * largest type. - */ -#define HWEIGHT(w) HWEIGHT64((u64)(w)) - /** * rol32 - rotate a 32-bit value left * @word: value to rotate Index: linux-2.6/lib/hweight.c =================================================================== --- linux-2.6.orig/lib/hweight.c +++ linux-2.6/lib/hweight.c @@ -9,7 +9,7 @@ * The Hamming Weight of a number is the total number of bits set in it. */ -unsigned int hweight32(unsigned int w) +unsigned int __arch_hweight32(unsigned int w) { #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; @@ -24,29 +24,30 @@ unsigned int hweight32(unsigned int w) return (res + (res >> 16)) & 0x000000FF; #endif } -EXPORT_SYMBOL(hweight32); +EXPORT_SYMBOL(__arch_hweight32); -unsigned int hweight16(unsigned int w) +unsigned int __arch_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(hweight16); +EXPORT_SYMBOL(__arch_hweight16); -unsigned int hweight8(unsigned int w) +unsigned int __arch_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } -EXPORT_SYMBOL(hweight8); +EXPORT_SYMBOL(__arch_hweight8); -unsigned long hweight64(__u64 w) +unsigned long __arch_hweight64(__u64 w) { #if BITS_PER_LONG == 32 - return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w); + return __arch_hweight32((unsigned int)(w >> 32)) + + __arch_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; @@ -63,4 +64,4 @@ unsigned long hweight64(__u64 w) #endif #endif } -EXPORT_SYMBOL(hweight64); +EXPORT_SYMBOL(__arch_hweight64);