diff options
| author | Jack Lloyd <[email protected]> | 2017-10-09 23:40:44 -0400 |
|---|---|---|
| committer | Jack Lloyd <[email protected]> | 2017-10-11 17:08:55 -0400 |
| commit | 40b3f979723b2b3dfb5c44047d7f786a73fd7f6f (patch) | |
| tree | bb2ad6b1df281aab32de7bec3e17a806ae95922c /src/tests/test_simd.cpp | |
| parent | f60b816469ebc3b46aa64dcba0dcdcdb92e87301 (diff) | |
Use rol/ror x86 instructions on GCC/Clang
Neither is very good at recognizing rotate sequences. For cases where
the rotation value is a constant they do fine, but for variable rotations
they do horribly. Using inline asm here improved performance of both
CAST-128 and CAST-256 by ~20% on my system with both GCC and Clang.
Diffstat (limited to 'src/tests/test_simd.cpp')
0 files changed, 0 insertions, 0 deletions