[all-commits] [llvm/llvm-project] 89226e: [AMDGPU] Do not widen scalar loads on GFX12 (#78724)

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 89226ecbb9975eea1c8dee4744f719555fc39036
      https://github.com/llvm/llvm-project/commit/89226ecbb9975eea1c8dee4744f719555fc39036
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2024-01-19 (Fri, 19 Jan 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp
    M llvm/test/CodeGen/AMDGPU/amdgpu-late-codegenprepare.ll
    M llvm/test/CodeGen/AMDGPU/indirect-call-known-callees.ll

  Log Message:
  -----------
  [AMDGPU] Do not widen scalar loads on GFX12 (#78724)

GFX12 has subword scalar loads so there is no need to do this.