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

[Lucas Ramirez via llvm-commits]

================
@@ -1883,65 +2118,79 @@ void PreRARematStage::rematerialize() {
             assert((SR.LaneMask & UncoveredLanes).none());
         }
       }
+    }
 #endif
 
-      // The register is no longer a live-in in all regions but the one that
-      // contains the single use. In live-through regions, maximum register
-      // pressure decreases predictably so we can directly update it. In the
-      // using region, maximum RP may or may not decrease, so we will mark it
-      // for re-computation after all materializations have taken place.
-      LaneBitmask PrevMask = RegionLiveIns[Reg];
-      RegionLiveIns.erase(Reg);
-      RegMasks.insert({{I, Remat.RematMI->getOperand(0).getReg()}, PrevMask});
-      if (Remat.UseMI->getParent() != DAG.Regions[I].first->getParent())
-        DAG.Pressure[I].inc(Reg, PrevMask, LaneBitmask::getNone(), DAG.MRI);
-      else
-        RecomputeRP.insert(I);
+    // This save is exact in beneficial regions but optimistic in all other
+    // regions where the register is live.
+    RPTargets[I].saveReg(Reg, Remat.Mask, DAG.MRI);
+    DAG.LiveIns[I].erase(Reg);
----------------
lucas-rami wrote:

I think this isn't needed because of the one-def check indeed.

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