projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 587c7ff) | patch
[AMDGPU] Split fp min/max atomics test. NFC.
authorJay Foad <jay.foad@amd.com>
Wed, 23 Feb 2022 13:35:34 +0000 (13:35 +0000)
committerJay Foad <jay.foad@amd.com>
Wed, 23 Feb 2022 15:00:49 +0000 (15:00 +0000)
commite66b1b73854e43f7e822fbb3be9e9875e6780761
tree0075b15fac27c230f923e7e95f428efe6486c24ftree | snapshot
parent587c7ff15c26d3a751fb6a10b2af60d4a25640c9commit | diff
[AMDGPU] Split fp min/max atomics test. NFC.

Split out f32 buffer, f64 buffer and image atomics. This just makes
it easier to test subtargets that only have some of these
instructions.

Differential Revision: https://reviews.llvm.org/D120407
llvm/test/CodeGen/AMDGPU/fp-min-max-atomics.ll [deleted file] blob | history
llvm/test/CodeGen/AMDGPU/fp-min-max-buffer-atomics.ll [new file with mode: 0644] blob
llvm/test/CodeGen/AMDGPU/fp-min-max-image-atomics.ll [new file with mode: 0644] blob
llvm/test/CodeGen/AMDGPU/fp64-min-max-buffer-atomics.ll [new file with mode: 0644] blob
Domain: System / Toolchain;