1 files changed, 15 insertions, 30 deletions
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index 27621906e4c5..bb499c5c8c57 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -708,9 +708,6 @@ public:
                                  WaitcntBrackets &ScoreBrackets,
                                  MachineInstr *OldWaitcntInstr,
                                  bool FlushVmCnt);
-  bool generateWaitcntBlockEnd(MachineBasicBlock &Block,
-                               WaitcntBrackets &ScoreBrackets,
-                               MachineInstr *OldWaitcntInstr);
   bool generateWaitcnt(AMDGPU::Waitcnt Wait,
                        MachineBasicBlock::instr_iterator It,
                        MachineBasicBlock &Block, WaitcntBrackets &ScoreBrackets,
@@ -1902,31 +1899,6 @@ bool SIInsertWaitcnts::generateWaitcntInstBefore(MachineInstr &MI,
                          OldWaitcntInstr);
 }
 
-// Add a waitcnt to flush the LOADcnt, SAMPLEcnt and BVHcnt counters at the
-// end of the given block if needed.
-bool SIInsertWaitcnts::generateWaitcntBlockEnd(MachineBasicBlock &Block,
-                                               WaitcntBrackets &ScoreBrackets,
-                                               MachineInstr *OldWaitcntInstr) {
-  AMDGPU::Waitcnt Wait;
-
-  unsigned LoadCntPending = ScoreBrackets.hasPendingEvent(LOAD_CNT);
-  unsigned SampleCntPending = ScoreBrackets.hasPendingEvent(SAMPLE_CNT);
-  unsigned BvhCntPending = ScoreBrackets.hasPendingEvent(BVH_CNT);
-
-  if (LoadCntPending == 0 && SampleCntPending == 0 && BvhCntPending == 0)
-    return false;
-
-  if (LoadCntPending != 0)
-    Wait.LoadCnt = 0;
-  if (SampleCntPending != 0)
-    Wait.SampleCnt = 0;
-  if (BvhCntPending != 0)
-    Wait.BvhCnt = 0;
-
-  return generateWaitcnt(Wait, Block.instr_end(), Block, ScoreBrackets,
-                         OldWaitcntInstr);
-}
-
 bool SIInsertWaitcnts::generateWaitcnt(AMDGPU::Waitcnt Wait,
                                        MachineBasicBlock::instr_iterator It,
                                        MachineBasicBlock &Block,
@@ -2355,9 +2327,22 @@ bool SIInsertWaitcnts::insertWaitcntInBlock(MachineFunction &MF,
     ++Iter;
   }
 
+  // Flush the LOADcnt, SAMPLEcnt and BVHcnt counters at the end of the block if
+  // needed.
+  AMDGPU::Waitcnt Wait;
   if (Block.getFirstTerminator() == Block.end() &&
-      isPreheaderToFlush(Block, ScoreBrackets))
-    Modified |= generateWaitcntBlockEnd(Block, ScoreBrackets, OldWaitcntInstr);
+      isPreheaderToFlush(Block, ScoreBrackets)) {
+    if (ScoreBrackets.hasPendingEvent(LOAD_CNT))
+      Wait.LoadCnt = 0;
+    if (ScoreBrackets.hasPendingEvent(SAMPLE_CNT))
+      Wait.SampleCnt = 0;
+    if (ScoreBrackets.hasPendingEvent(BVH_CNT))
+      Wait.BvhCnt = 0;
+  }
+
+  // Combine or remove any redundant waitcnts at the end of the block.
+  Modified |= generateWaitcnt(Wait, Block.instr_end(), Block, ScoreBrackets,
+                              OldWaitcntInstr);
 
   return Modified;
 }