[AMDGPU][GlobalISel] Transform (fadd (fmul x, y), z) -> (fma x, y, z)
authorMirko Brkusanin <Mirko.Brkusanin@amd.com>
Fri, 26 Nov 2021 16:01:32 +0000 (17:01 +0100)
committerMirko Brkusanin <Mirko.Brkusanin@amd.com>
Mon, 29 Nov 2021 15:27:21 +0000 (16:27 +0100)
commit881840fc268e6523b71b40e717c647ed45682816
treed4dec30e8d78cf8945cc37c3c2802169b1879d6d
parent65d9dc7f1f4ac5b4d76502d36bd81d9857538148
[AMDGPU][GlobalISel] Transform (fadd (fmul x, y), z) -> (fma x, y, z)

Patch by: Mateja Marjanovic

Differential Revision: https://reviews.llvm.org/D93305
llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
llvm/include/llvm/CodeGen/TargetLowering.h
llvm/include/llvm/Target/GlobalISel/Combine.td
llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
llvm/lib/Target/AMDGPU/SIISelLowering.h
llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-mul-post-legalize.mir [new file with mode: 0644]
llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-mul-pre-legalize.mir [new file with mode: 0644]
llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-mul.ll [new file with mode: 0644]