powerpc: Add support for popcnt instructions

POWER5 added popcntb, and POWER7 added popcntw and popcntd. As a first step
this patch does all the work out of line, but it would be nice to implement
them as inlines with an out of line fallback.

The performance issue with hweight was noticed when disabling SMT on a large
(192 thread) POWER7 box. The patch improves that testcase by about 8%.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This commit is contained in:
Anton Blanchard
2010-08-12 16:28:09 +00:00
committed by Benjamin Herrenschmidt
parent 7208364652
commit 64ff312876
5 changed files with 133 additions and 4 deletions

View File

@@ -267,7 +267,16 @@ static __inline__ int fls64(__u64 x)
#include <asm-generic/bitops/fls64.h>
#endif /* __powerpc64__ */
#ifdef CONFIG_PPC64
unsigned int __arch_hweight8(unsigned int w);
unsigned int __arch_hweight16(unsigned int w);
unsigned int __arch_hweight32(unsigned int w);
unsigned long __arch_hweight64(__u64 w);
#include <asm-generic/bitops/const_hweight.h>
#else
#include <asm-generic/bitops/hweight.h>
#endif
#include <asm-generic/bitops/find.h>
/* Little-endian versions */