projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 1211af7) | patch
[AMDGPU] Remove permlane discard vdst_in optimization from isel
authorJay Foad <jay.foad@amd.com>
Thu, 22 Dec 2022 12:02:11 +0000 (12:02 +0000)
committerJay Foad <jay.foad@amd.com>
Thu, 22 Dec 2022 15:49:26 +0000 (15:49 +0000)
commit7e1e99381650cbea8b86b163f3186f3ddf8b9e36
treed3881b3869bd2faf94c2c7468f0eeb0e4eefae75tree | snapshot
parent1211af761fb949372c200bb98fa7075ceeead7a1commit | diff
[AMDGPU] Remove permlane discard vdst_in optimization from isel

D72845 implemented the equivalent IR optimization in InstCombine so it
seems that there's no advantage to doing it during isel too.

This partially reverts D72844.

Differential Revision: https://reviews.llvm.org/D140546
llvm/lib/Target/AMDGPU/VOP3Instructions.td diff | blob | history
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.permlane.ll diff | blob | history
Domain: System / Toolchain;