[llvm] [AMDGPU][SIInsertWaitCnts] Use RegUnits-based tracking (PR #162077)

[Jay Foad via llvm-commits]

================
@@ -617,35 +618,29 @@ class WaitcntBrackets {
     return getScoreUB(T) - getScoreLB(T);
   }
 
-  unsigned getRegScore(int GprNo, InstCounterType T) const {
-    if (GprNo < NUM_ALL_VGPRS)
-      return VgprScores[T][GprNo];
-
-    if (GprNo < NUM_ALL_ALLOCATABLE)
-      return SgprScores[getSgprScoresIdx(T)][GprNo - NUM_ALL_VGPRS];
+  unsigned getSGPRScore(MCRegUnit RU, InstCounterType T) const {
+    auto It = SGPRs.find(RU);
+    return It != SGPRs.end() ? It->second.Scores[getSgprScoresIdx(T)] : 0;
+  }
 
-    assert(GprNo == SCC);
-    return SCCScore;
+  unsigned getVMemScore(VMEMID TID, InstCounterType T) const {
+    auto It = VMem.find(TID);
+    return It != VMem.end() ? It->second.Scores[T] : 0;
   }
 
   bool merge(const WaitcntBrackets &Other);
 
-  RegInterval getRegInterval(const MachineInstr *MI,
-                             const MachineOperand &Op) const;
-
   bool counterOutOfOrder(InstCounterType T) const;
   void simplifyWaitcnt(AMDGPU::Waitcnt &Wait);
   void simplifyWaitcnt(InstCounterType T, unsigned &Count) const;
   bool hasRedundantXCntWithKmCnt(const AMDGPU::Waitcnt &Wait);
   bool canOptimizeXCntWithLoadCnt(const AMDGPU::Waitcnt &Wait);
   void simplifyXcnt(AMDGPU::Waitcnt &CheckWait, AMDGPU::Waitcnt &UpdateWait);
 
-  void determineWait(InstCounterType T, RegInterval Interval,
-                     AMDGPU::Waitcnt &Wait) const;
-  void determineWait(InstCounterType T, int RegNo,
-                     AMDGPU::Waitcnt &Wait) const {
-    determineWait(T, {RegNo, RegNo + 1}, Wait);
-  }
+  void determineWaitForPhysReg(InstCounterType T, MCPhysReg Reg,
+                               AMDGPU::Waitcnt &Wait) const;
+  void determineWaitForLDSDMA(InstCounterType T, VMEMID TID,
+                              AMDGPU::Waitcnt &Wait) const;
----------------
jayfoad wrote:

Could these be two overloads of `determineWait`, or does that cause problems because `MCPhysReg` and `VMEMID` have more or less the same underlying type?

https://github.com/llvm/llvm-project/pull/162077