projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 55ed09d) | patch
AMDGPU/GlobalISel: Start handling _L to _LZ optimization
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Sat, 8 Feb 2020 14:28:27 +0000 (09:28 -0500)
committerMatt Arsenault <arsenm2@gmail.com>
Mon, 30 Mar 2020 21:02:30 +0000 (17:02 -0400)
commit42d5609809836aceff41f78ab652a882d4982260
tree5fcb501813bde8d636f0031e33e7ff08d2f564ebtree | snapshot
parent55ed09d32e2602eba1dbb8aba1985246739c3909commit | diff
AMDGPU/GlobalISel: Start handling _L to _LZ optimization

We currently don't have a way to map to the equivalent intrinsic
opcode, so track immediate 0s in place of the address for the
selection to know to change the final opcode.
llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/GlobalISel/image_ls_mipmap_zero.a16.ll [new file with mode: 0644] blob
llvm/test/CodeGen/AMDGPU/GlobalISel/image_ls_mipmap_zero.ll [new file with mode: 0644] blob
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.sample.ltolz.a16.ll [new file with mode: 0644] blob
llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.image.sample.ltolz.ll [new file with mode: 0644] blob
Domain: System / Toolchain;