diff options
| author | Chris Metcalf <cmetcalf@tilera.com> | 2014-09-25 16:49:38 -0400 |
|---|---|---|
| committer | Chris Metcalf <cmetcalf@tilera.com> | 2014-10-06 11:20:59 -0400 |
| commit | d9cd52e64d7b6b0fd56566de87c826cb6fe3677d (patch) | |
| tree | 2e79c9dae8aaf921b08bd73c3af19d65879545cd /COPYING.LIB | |
| parent | 4b68ea1162f39f62590e49eb5d4371871e071f32 (diff) | |
| download | glibc-d9cd52e64d7b6b0fd56566de87c826cb6fe3677d.tar glibc-d9cd52e64d7b6b0fd56566de87c826cb6fe3677d.tar.gz glibc-d9cd52e64d7b6b0fd56566de87c826cb6fe3677d.tar.bz2 glibc-d9cd52e64d7b6b0fd56566de87c826cb6fe3677d.zip | |
tile: optimize memcmp
Customize memcmp.c for tile, using similar tricks from memcpy:
- replace MERGE macro with dblalign.
- replace memcmp_bytes function with revbytes.
- use __glibc_likely.
- use post-increment addressing.
The schedule is still not perfect: the compiler is not hoisting
code above the comparison branch, which could save a bundle or two.
memcmp speeds up by 30-40% on shorter aligned tests in benchtest,
with some tests with unaligned lengths taking a small performance hit.
Diffstat (limited to 'COPYING.LIB')
0 files changed, 0 insertions, 0 deletions