[AMDGPU] Do not widen scalar loads on GFX12 (#78724)
commit89226ecbb9975eea1c8dee4744f719555fc39036
authorJay Foad <jay.foad@amd.com>
Fri, 19 Jan 2024 15:30:07 +0000 (19 15:30 +0000)
committerGitHub <noreply@github.com>
Fri, 19 Jan 2024 15:30:07 +0000 (19 15:30 +0000)
tree0d55ee3a91ae1b44f71fbdbdda37045d6e1dc7d0
parentaac1d9710b5123e2d4fca0b5e0e2b66cbb6b0fb3
[AMDGPU] Do not widen scalar loads on GFX12 (#78724)

GFX12 has subword scalar loads so there is no need to do this.
llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp
llvm/test/CodeGen/AMDGPU/amdgpu-late-codegenprepare.ll
llvm/test/CodeGen/AMDGPU/indirect-call-known-callees.ll