[clang] [AMDGPU][MachineScheduler] Alternative way to control excess RP. (PR #68004)

[Jeffrey Byrnes via cfe-commits]

================
@@ -702,7 +702,7 @@ bool UnclusteredHighRPStage::initGCNSchedStage() {
   if (!GCNSchedStage::initGCNSchedStage())
     return false;
 
-  if (DAG.RegionsWithHighRP.none() && DAG.RegionsWithExcessRP.none())
+  if (DAG.RegionsWithExcessRP.none())
----------------
jrbyrnes wrote:

What about regions that are close to the critical limit?

https://github.com/llvm/llvm-project/pull/68004
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits