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

[via libc-commits]

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

This change was intended to be the preliminary for the balanced scheduling model.
Maybe it is better to join it with the large change or revert the line in question.
Nevertheless, I would like to see if this affects the performance.

https://github.com/llvm/llvm-project/pull/68004