[PATCH] D133305: [AMDGPU] Simplify mad/mac patterns. NFC.
Jay Foad via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 9 07:56:44 PDT 2022
foad added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/SIInstructions.td:987
// better to select mad instead of mac.
-class FMADPat <ValueType vt, Instruction inst, SDPatternOperator node>
- : GCNPat <(vt (node (vt (VOP3NoMods vt:$src0)),
----------------
arsenm wrote:
> If we keep the node parameter, can we reuse this for v_fmac_*?
Not sure - it looks like V_FMAC_* lack the clamp and omod operands.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D133305/new/
https://reviews.llvm.org/D133305
More information about the llvm-commits
mailing list