[all-commits] [llvm/llvm-project] afa0ed: [AMDGPU] Fix shrinking of F16 FMA on newer subtargets

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: afa0ed33df0717e73232f72ff8acee279f285140
      https://github.com/llvm/llvm-project/commit/afa0ed33df0717e73232f72ff8acee279f285140
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2022-09-08 (Thu, 08 Sep 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
    M llvm/test/CodeGen/AMDGPU/fma.f16.ll
    M llvm/test/CodeGen/AMDGPU/gfx10-shrink-mad-fma.mir

  Log Message:
  -----------
  [AMDGPU] Fix shrinking of F16 FMA on newer subtargets

D125803 introduced shrinking of F16 FMA to FMAAK/FMAMK in
SIShrinkInstructions (useful on GFX10+ where VOP3 instructions may have
a literal operand) but failed to handle the V_FMA_F16_gfx9_e64 form of
the opcode which is used on GFX9+.

Differential Revision: https://reviews.llvm.org/D133489