[PATCH] x86_64: Optimize ffsll function code size.

[Sunil K Pandey]

Ffsll function size is 17 byte, this patch optimizes size to 16 byte.
Currently ffsll function randomly regress by ~20%, depending on how
code get aligned.

This patch fixes ffsll function random performance regression.
---
 sysdeps/x86_64/ffsll.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sysdeps/x86_64/ffsll.c b/sysdeps/x86_64/ffsll.c
index a1c13d4906..dbded6f0a1 100644
--- a/sysdeps/x86_64/ffsll.c
+++ b/sysdeps/x86_64/ffsll.c
@@ -29,7 +29,7 @@ ffsll (long long int x)
   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.  */
+       "cmove %k1,%k0\n"	/* If number was zero, use -1 as result.  */
        : "=&r" (cnt), "=r" (tmp) : "rm" (x), "1" (-1));
 
   return cnt + 1;
-- 
2.41.0