diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2024-05-07 10:28:55 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-07 10:28:55 +0100 |
| commit | abd314938dda1b117f289be5e630e43e68533929 (patch) | |
| tree | d90e13ee8da8aa037379edd25ff437ba4938954b /llvm/lib/Transforms/Utils/CloneFunction.cpp | |
| parent | 6ce04747cff524b4c5c8738e25144659a5cf6691 (diff) | |
| download | llvm-abd314938dda1b117f289be5e630e43e68533929.zip llvm-abd314938dda1b117f289be5e630e43e68533929.tar.gz llvm-abd314938dda1b117f289be5e630e43e68533929.tar.bz2 | |
[X86] Use GFNI for vXi8 shifts/rotates (#89115)
As detailed here: https://github.com/InstLatx64/InstLatX64_Demo/blob/master/GFNI_Demo.h
We can use the gf2p8affine instruction to lower byte shifts/rotates as well as the existing bitreverse case.
Based off the original patch here: https://reviews.llvm.org/D137026
Diffstat (limited to 'llvm/lib/Transforms/Utils/CloneFunction.cpp')
0 files changed, 0 insertions, 0 deletions