| commit | 837e225ba1992f9745e5bbbd5e8443243a7f475f | [log] [tgz] |
|---|---|---|
| author | Jan Beulich <jbeulich@suse.com> | Thu Oct 20 10:01:12 2022 +0200 |
| committer | Jan Beulich <jbeulich@suse.com> | Thu Oct 20 10:01:12 2022 +0200 |
| tree | a540ffd72839917cfbc5b8580c1dfc85904bcd2b | |
| parent | 15ede33bfa86fd2dfd2d088e01ac2d20cdba46c9 [diff] |
x86: re-work AVX-VNNI support
By putting the templates after their AVX512 counterparts, the AVX512
flavors will be picked by default. That way the need to always use {vex}
ceases to exist once respective CPU features (AVX512-VNNI or AVX512VL as
a whole) have been disabled. This way the need for the PseudoVexPrefix
attribute also disappears.