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>

1 files changed, 10 insertions, 9 deletions

diff --git a/lib/hweight.c b/lib/hweight.c
index 63ee4eb1228d..a6927e76840f 100644
--- a/lib/hweight.c
+++ b/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);