[all-commits] [llvm/llvm-project] 6d3d88: AMDGPU: Use SmallSet for VOPD scalar reg tracking ...

[Petar Avramovic via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6d3d88f74c405db660a20103905787fc67087287
      https://github.com/llvm/llvm-project/commit/6d3d88f74c405db660a20103905787fc67087287
  Author: Petar Avramovic <Petar.Avramovic at amd.com>
  Date:   2026-04-07 (Tue, 07 Apr 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNVOPDUtils.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/combine-short-clamp.ll
    M llvm/test/CodeGen/AMDGPU/fcopysign.f16.ll
    M llvm/test/CodeGen/AMDGPU/fmed3.bf16.ll
    M llvm/test/CodeGen/AMDGPU/fmed3.ll
    M llvm/test/CodeGen/AMDGPU/fold-int-pow2-with-fmul-or-fdiv.ll
    M llvm/test/CodeGen/AMDGPU/frem.ll
    M llvm/test/CodeGen/AMDGPU/llvm.maximum.f16.ll
    M llvm/test/CodeGen/AMDGPU/llvm.maximum.f32.ll
    M llvm/test/CodeGen/AMDGPU/llvm.minimum.f16.ll
    M llvm/test/CodeGen/AMDGPU/llvm.minimum.f32.ll
    M llvm/test/CodeGen/AMDGPU/uniform-vgpr-to-sgpr-return.ll
    M llvm/test/CodeGen/AMDGPU/vector-reduce-fmaximum.ll
    M llvm/test/CodeGen/AMDGPU/vector-reduce-fminimum.ll

  Log Message:
  -----------
  AMDGPU: Use SmallSet for VOPD scalar reg tracking (#190650)

Use SmallSet instead of SmallVector for UniqueScalarRegs.
VCC_LO was pushed without uniqueness check, so when both
components used VCC implicitly it was counted twice,
rejecting valid VOPD pairings.

Co-Authored-By: Claude Opus 4.6 <noreply at anthropic.com>



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications