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>

1 files changed, 18 insertions, 4 deletions

diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h
index 3a7be842cdce..9a81c1e9436c 100644
--- a/include/asm-generic/bitops/arch_hweight.h
+++ b/include/asm-generic/bitops/arch_hweight.h
@@ -3,9 +3,23 @@
 
 #include <asm/types.h>
 
-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);
+inline unsigned int __arch_hweight32(unsigned int w)
+{
+        return __sw_hweight32(w);
+}
 
+inline unsigned int __arch_hweight16(unsigned int w)
+{
+        return __sw_hweight16(w);
+}
+
+inline unsigned int __arch_hweight8(unsigned int w)
+{
+        return __sw_hweight8(w);
+}
+
+inline unsigned long __arch_hweight64(__u64 w)
+{
+        return __sw_hweight64(w);
+}
 #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */