[all-commits] [llvm/llvm-project] 952584: [AMDGPU] Use AMDGPU::isIntrinsicAlwaysUniform in i...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 95258419f6fe2e0922c2c0916fd176b9f7361555
      https://github.com/llvm/llvm-project/commit/95258419f6fe2e0922c2c0916fd176b9f7361555
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2024-03-30 (Sat, 30 Mar 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/wave32.ll

  Log Message:
  -----------
  [AMDGPU] Use AMDGPU::isIntrinsicAlwaysUniform in isSDNodeAlwaysUniform (#87085)

This is mostly just a simplification, but tests show a slight codegen
improvement in code using the deprecated amdgcn.icmp/fcmp intrinsics.



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