From 1527bc8b928dd1399c3d3467dd47d9ede210978a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 1 Feb 2010 15:03:07 +0100 Subject: bitops: Optimize hweight() by making use of compile-time evaluation 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 LKML-Reference: <20100318111929.GB11152@aftab> Acked-by: H. Peter Anvin LKML-Reference: <1265028224.24455.154.camel@laptop> Signed-off-by: H. Peter Anvin --- include/linux/bitops.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux/bitops.h') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index b79389879238..c55d5bc4ee58 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -47,31 +47,6 @@ static inline unsigned long hweight_long(unsigned long w) 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 -- cgit From 4677d4a53e0d565742277e8913e91c821453e63e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 3 May 2010 14:57:11 +0200 Subject: arch, hweight: Fix compilation errors Fix function prototype visibility issues when compiling for non-x86 architectures. Tested with crosstool (ftp://ftp.kernel.org/pub/tools/crosstool/) with alpha, ia64 and sparc targets. Signed-off-by: Borislav Petkov LKML-Reference: <20100503130736.GD26107@aftab> Signed-off-by: H. Peter Anvin --- include/linux/bitops.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/bitops.h') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index c55d5bc4ee58..26caa608ccd9 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -10,6 +10,11 @@ #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #endif +extern unsigned int __sw_hweight8(unsigned int w); +extern unsigned int __sw_hweight16(unsigned int w); +extern unsigned int __sw_hweight32(unsigned int w); +extern unsigned long __sw_hweight64(__u64 w); + /* * Include this here because some architectures need generic_ffs/fls in * scope -- cgit