[all-commits] [llvm/llvm-project] be2388: [AMDGPU] Prefer v_madak_f32 over v_madmk_f32 to re...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: be2388c0d9923ed02fa4723fe9a06f07a0491fe5
      https://github.com/llvm/llvm-project/commit/be2388c0d9923ed02fa4723fe9a06f07a0491fe5
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2023-11-16 (Thu, 16 Nov 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/test/CodeGen/AMDGPU/dagcombine-fma-fmad.ll

  Log Message:
  -----------
  [AMDGPU] Prefer v_madak_f32 over v_madmk_f32 to reduce vgpr pressure (#72506)

As explained in the comment in SIInstrInfo::FoldImmediate, if we have a
choice between v_madak_f32 and v_madmk_f32 we should choose the former
so that the literal that is not folded into the instruction can be
materialized in an sgpr instead of a vgpr.