diff options
| author | Noah Goldstein <goldstein.w.n@gmail.com> | 2021-05-03 03:03:19 -0400 |
|---|---|---|
| committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2021-05-03 21:18:03 -0400 |
| commit | 2a76821c3081d2c0231ecd2618f52662cb48fccd (patch) | |
| tree | 053a73e993b4eb15341f53039a3b98dade784c28 /elf/reldepmod5.c | |
| parent | acfd088a1963ba51cd83c78f95c0ab25ead79e04 (diff) | |
| download | glibc-2a76821c3081d2c0231ecd2618f52662cb48fccd.tar glibc-2a76821c3081d2c0231ecd2618f52662cb48fccd.tar.gz glibc-2a76821c3081d2c0231ecd2618f52662cb48fccd.tar.bz2 glibc-2a76821c3081d2c0231ecd2618f52662cb48fccd.zip | |
x86: Optimize memchr-evex.S
No bug. This commit optimizes memchr-evex.S. The optimizations include
replacing some branches with cmovcc, avoiding some branches entirely
in the less_4x_vec case, making the page cross logic less strict,
saving some ALU in the alignment process, and most importantly
increasing ILP in the 4x loop. test-memchr, test-rawmemchr, and
test-wmemchr are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Diffstat (limited to 'elf/reldepmod5.c')
0 files changed, 0 insertions, 0 deletions