[PATCH] D153537: [AMDGPU] Do not wait for vscnt on function entry and return

Jay Foad via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Jun 22 05:33:04 PDT 2023


foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp:1231
       !ST->hasAutoWaitcntBeforeBarrier() && !ST->supportsBackOffBarrier()) {
-    Wait = Wait.combined(allZeroWaitcnt());
+    Wait = Wait.combined(AMDGPU::Waitcnt::allZero(ST->hasVscnt()));
   }
----------------
@kerbowa unlike the rest of SIInsertWaitcnts, I assume this part does want to wait for vscnt==0 since it is handling memory dependencies?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153537/new/

https://reviews.llvm.org/D153537



More information about the llvm-commits mailing list