diff options
| author | Noah Goldstein <goldstein.w.n@gmail.com> | 2021-12-24 18:54:53 -0600 |
|---|---|---|
| committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2021-12-27 03:18:58 -0600 |
| commit | cca457f9c51a90cf82cae75432ed3de20942519c (patch) | |
| tree | 84222287827e96165605200016965b48ef0d5928 /sysdeps/x86_64/multiarch/wmemchr.c | |
| parent | abddd61de090ae84e380aff68a98bd94ef704667 (diff) | |
| download | glibc-cca457f9c51a90cf82cae75432ed3de20942519c.tar.gz glibc-cca457f9c51a90cf82cae75432ed3de20942519c.tar.xz glibc-cca457f9c51a90cf82cae75432ed3de20942519c.zip | |
x86: Optimize L(less_vec) case in memcmpeq-evex.S
No bug. Optimizations are twofold. 1) Replace page cross and 0/1 checks with masked load instructions in L(less_vec). In applications this reduces branch-misses in the hot [0, 32] case. 2) Change controlflow so that L(less_vec) case gets the fall through. Change 2) helps copies in the [0, 32] size range but comes at the cost of copies in the [33, 64] size range. From profiles of GCC and Python3, 94%+ and 99%+ of calls are in the [0, 32] range so this appears to the the right tradeoff. Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com> Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Diffstat (limited to 'sysdeps/x86_64/multiarch/wmemchr.c')
0 files changed, 0 insertions, 0 deletions