[all-commits] [llvm/llvm-project] e2eee9: [AMDGPU] Fix an assertion failure when folding int...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e2eee902a41671c6dc67128e20af6c8f1dec55aa
      https://github.com/llvm/llvm-project/commit/e2eee902a41671c6dc67128e20af6c8f1dec55aa
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2023-02-22 (Wed, 22 Feb 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
    M llvm/test/CodeGen/AMDGPU/fma.f16.ll

  Log Message:
  -----------
  [AMDGPU] Fix an assertion failure when folding into src2 of V_FMAC_F16

D139469 "[AMDGPU] Enable OMod on more VOP3 instructions" caused an
assertion failure when trying to fold into src2 of V_FMAC_F16. It would
temporarily convert the instruction to V_FMA_F16_gfx9 and add an opsel
operand, but if the fold still failed then it would forget to remove the
opsel operand.

Differential Revision: https://reviews.llvm.org/D144558