[clang] [llvm] [AMDGPU] Change CF intrinsics lowering to reconverge on predecessors. (PR #92809)

Gang Chen via cfe-commits cfe-commits at lists.llvm.org
Mon Jun 24 20:24:42 PDT 2024


================
@@ -305,43 +304,43 @@ bool SIAnnotateControlFlow::handleLoop(BranchInst *Term) {
 }
 
 /// Close the last opened control flow
-bool SIAnnotateControlFlow::closeControlFlow(BasicBlock *BB) {
-  llvm::Loop *L = LI->getLoopFor(BB);
+bool SIAnnotateControlFlow::tryWaveReconverge(BasicBlock *BB) {
----------------
cmc-rep wrote:

This function is one core part of this change. It would be nice to have more comment with examples before the function header showing when and where wave_converge is inserted.

https://github.com/llvm/llvm-project/pull/92809


More information about the cfe-commits mailing list