1 files changed, 8 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp
index d3b41797871..94e614750d2 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaits.cpp
@@ -494,6 +494,14 @@ bool SIInsertWaits::runOnMachineFunction(MachineFunction &MF) {
 
     // Wait for everything at the end of the MBB
     Changes |= insertWait(MBB, MBB.getFirstTerminator(), LastIssued);
+
+    // Functions returning something shouldn't contain S_ENDPGM, because other
+    // bytecode will be appended after it.
+    if (!ReturnsVoid) {
+      MachineBasicBlock::iterator I = MBB.getFirstTerminator();
+      if (I != MBB.end() && I->getOpcode() == AMDGPU::S_ENDPGM)
+        I->eraseFromParent();
+    }
   }
 
   return Changes;