| commit | 22c3694052384bc207bdf36d8c05c560bd91d291 | [log] [tgz] |
|---|---|---|
| author | Jan Beulich <jbeulich@suse.com> | Fri Mar 18 10:54:53 2022 +0100 |
| committer | Jan Beulich <jbeulich@suse.com> | Fri Mar 18 10:54:53 2022 +0100 |
| tree | f5b31c934a04b4dbb644b3625a4c2c3a1fe2dbd3 | |
| parent | 41d6ac5da655a2e78109848f2db47e53552fd61a [diff] |
x86: fold certain AVX2 templates into their AVX counterparts Like for AVX512VL we can make the handling of operand sizes a little more flexible to allow reducing the number of templates we have.