diff options
| author | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-06-06 21:11:33 -0700 |
|---|---|---|
| committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-06-07 13:10:31 -0700 |
| commit | 6dcbb7d95dded20153b12d76d2f4e0ef0cda4f35 (patch) | |
| tree | 6ff9f0fea9ac9a67aac6b708bb20faf01d3fae1f /sysdeps/x86_64/multiarch/memchr-avx2-rtm.S | |
| parent | af5306a735eb0966fdc2f8ccdafa8888e2df0c87 (diff) | |
| download | glibc-6dcbb7d95dded20153b12d76d2f4e0ef0cda4f35.tar glibc-6dcbb7d95dded20153b12d76d2f4e0ef0cda4f35.tar.gz glibc-6dcbb7d95dded20153b12d76d2f4e0ef0cda4f35.tar.bz2 glibc-6dcbb7d95dded20153b12d76d2f4e0ef0cda4f35.zip | |
x86: Shrink code size of memchr-avx2.S
This is not meant as a performance optimization. The previous code was
far to liberal in aligning targets and wasted code size unnecissarily.
The total code size saving is: 59 bytes
There are no major changes in the benchmarks.
Geometric Mean of all benchmarks New / Old: 0.967
Full xcheck passes on x86_64.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Diffstat (limited to 'sysdeps/x86_64/multiarch/memchr-avx2-rtm.S')
| -rw-r--r-- | sysdeps/x86_64/multiarch/memchr-avx2-rtm.S | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/memchr-avx2-rtm.S b/sysdeps/x86_64/multiarch/memchr-avx2-rtm.S index 87b076c7c4..c4d71938c5 100644 --- a/sysdeps/x86_64/multiarch/memchr-avx2-rtm.S +++ b/sysdeps/x86_64/multiarch/memchr-avx2-rtm.S @@ -2,6 +2,7 @@ # define MEMCHR __memchr_avx2_rtm #endif +#define COND_VZEROUPPER COND_VZEROUPPER_XTEST #define ZERO_UPPER_VEC_REGISTERS_RETURN \ ZERO_UPPER_VEC_REGISTERS_RETURN_XTEST |