x86_64: Optimize ffsll function code size.

Ffsll function randomly regress by ~20%, depending on how code gets
aligned in memory.  Ffsll function code size is 17 bytes.  Since default
function alignment is 16 bytes, it can load on 16, 32, 48 or 64 bytes
aligned memory.  When ffsll function load at 16, 32 or 64 bytes aligned
memory, entire code fits in single 64 bytes cache line.  When ffsll
function load at 48 bytes aligned memory, it splits in two cache line,
hence random regression.

Ffsll function size reduction from 17 bytes to 12 bytes ensures that it
will always fit in single 64 bytes cache line.

This patch fixes ffsll function random performance regression.

Reviewed-by: Carlos O'Donell <carlos@redhat.com>

diff --git a/sysdeps/x86_64/ffsll.c b/sysdeps/x86_64/ffsll.c
index 73cfc6d90ef9ef85eca6ee8c0a6a30d4a8014bcd..28444284e6b507a461b77d3f1b55910659c7d860 100644 (file)
--- a/sysdeps/x86_64/ffsll.c
+++ b/sysdeps/x86_64/ffsll.c
@@ -26,13 +26,13 @@ int
 ffsll (long long int x)
 {
   long long int cnt;
-  long long int tmp;
 
-  asm ("bsfq %2,%0\n"          /* Count low bits in X and store in %1.  */
-       "cmoveq %1,%0\n"                /* If number was zero, use -1 as result.  */
-       : "=&r" (cnt), "=r" (tmp) : "rm" (x), "1" (-1));
+  asm ("mov $-1,%k0\n" /* Initialize cnt to -1.  */
+       "bsf %1,%0\n"   /* Count low bits in x and store in cnt.  */
+       "inc %k0\n"     /* Increment cnt by 1.  */
+       : "=&r" (cnt) : "r" (x));
 
-  return cnt + 1;
+  return cnt;
 }
 
 #ifndef __ILP32__