[PATCH] D115747: [AMDGPU] Hoist waitcnt out of loops when they unecessarily wait for stores

Jay Foad via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Dec 15 02:35:35 PST 2021


foad added a comment.

In the commit message:

- "before using a loaded value" -> "before using a value that was loaded outside the loop"?
- typo "GFX0"
- "If" should be "if" in middle of sentence
- maybe briefly mention why this particular problem doesn't happen on GFX10?

Please run "git clang-format @^".

I'm still reading the patch.



================
Comment at: llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp:827
                                                AMDGPU::Waitcnt &Wait,
                                                const MachineInstr *MI) {
   bool Modified = false;
----------------
Might be cleaner to change this function to take a BasicBlock::iterator instead of a MachineInstr*, so you could naturally pass in MBB->end() without treating it as a special case?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D115747/new/

https://reviews.llvm.org/D115747



More information about the llvm-commits mailing list