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 <hpa@zytor.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100318111929.GB11152@aftab>
Acked-by: H. Peter Anvin <hpa@zytor.com>
LKML-Reference: <1265028224.24455.154.camel@laptop>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
This commit is contained in:
Peter Zijlstra
2010-02-01 15:03:07 +01:00
committed by H. Peter Anvin
parent 0fdf86754f
commit 1527bc8b92
8 changed files with 87 additions and 58 deletions

View File

@@ -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