x86: Shrink memcmp-sse4.S code size

Browse Source

No bug.

This implementation refactors memcmp-sse4.S primarily with minimizing
code size in mind. It does this by removing the lookup table logic and
removing the unrolled check from (256, 512] bytes.

memcmp-sse4 code size reduction : -3487 bytes
wmemcmp-sse4 code size reduction: -1472 bytes

The current memcmp-sse4.S implementation has a large code size
cost. This has serious adverse affects on the ICache / ITLB. While
in micro-benchmarks the implementations appears fast, traces of
real-world code have shown that the speed in micro benchmarks does not
translate when the ICache/ITLB are not primed, and that the cost
of the code size has measurable negative affects on overall
application performance.

See https://research.google/pubs/pub48320/ for more details.

Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
(cherry picked from commit 2f9062d717)

...

This commit is contained in:

Noah Goldstein 2021-11-10 16:18:56 -06:00 committed by Sunil K Pandey

parent cecbac5212

commit 7cb126e7e7

1 changed files with 629 additions and 1604 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2233

sysdeps/x86_64/multiarch/memcmp-sse4.S

View File

File diff suppressed because it is too large Load Diff