[llvm] [AMDGPU][Scheduler] Scoring system for rematerialization candidates (PR #153092)

[Lucas Ramirez via llvm-commits]

================
@@ -1151,15 +1352,19 @@ void UnclusteredHighRPStage::finalizeGCNSchedStage() {
 }
 
 bool GCNSchedStage::initGCNRegion() {
+  // Skip empty scheduling region.
+  if (DAG.begin() == DAG.end())
+    return false;
+
   // Check whether this new region is also a new block.
   if (DAG.RegionBegin->getParent() != CurrentMBB)
     setupNewBlock();
 
   unsigned NumRegionInstrs = std::distance(DAG.begin(), DAG.end());
   DAG.enterRegion(CurrentMBB, DAG.begin(), DAG.end(), NumRegionInstrs);
 
-  // Skip empty scheduling regions (0 or 1 schedulable instructions).
-  if (DAG.begin() == DAG.end() || DAG.begin() == std::prev(DAG.end()))
+  // Skip regions with 1 schedulable instruction.
+  if (DAG.begin() == std::prev(DAG.end()))
     return false;
----------------
lucas-rami wrote:

Unfortunately no, `ScheduleDAGMILive::enterRegion` expects to be called even for single-instruction regions to maintain some internal state.

https://github.com/llvm/llvm-project/pull/153092