[PATCH] D77228: [AMDGPU] Disable 'Skip Uniform Regions' optimization by default; add support for -opt-bisect-limit; update tests.
Sameer Sahasrabuddhe via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Apr 1 19:37:15 PDT 2020
sameerds added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp:869
}
- addPass(createStructurizeCFGPass(true)); // true -> SkipUniformRegions
+ addPass(createStructurizeCFGPass(false)); // true -> SkipUniformRegions
}
----------------
This only changes the invocation in AMDGPU, but does not change the structurizer default itself. If that is the intention, then commit message needs to reflect that correctly, and should start with the flag [AMDGPU].
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D77228/new/
https://reviews.llvm.org/D77228
More information about the llvm-commits
mailing list