projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 4ab28b6) | patch
AMDGPU: Add additional MIR tests for exec mask optimizations
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Wed, 27 Mar 2019 16:58:30 +0000 (16:58 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Wed, 27 Mar 2019 16:58:30 +0000 (16:58 +0000)
commit4d47ac3b30a0385f7fdbe716284fde1f44685c2e
tree513be4e5eb2cf41cf46479697f02c31e4b138c7ftree | snapshot
parent4ab28b64b4cea1fc7d12a352e706a46eb5e5fe4ccommit | diff
AMDGPU: Add additional MIR tests for exec mask optimizations

Also includes one example of how this transform is unsound. This isn't
verifying the copies are used in the control flow intrinisic patterns.

Also add option to disable exec mask opt pass. Since this pass is
unsound, it may be useful to turn it off until it is fixed.

llvm-svn: 357091
llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/collapse-endcf-broken.mir [new file with mode: 0644] blob
llvm/test/CodeGen/AMDGPU/collapse-endcf.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/collapse-endcf.mir diff | blob | history
Domain: System / Toolchain;