1 files changed, 7 insertions, 2 deletions
diff --git a/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp b/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp
index 3168bcd53eda..e1018bdfde46 100644
--- a/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp
+++ b/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp
@@ -56,6 +56,7 @@
 #include "llvm/CodeGen/LiveVariables.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
 
@@ -90,6 +91,8 @@ private:
   unsigned OrSaveExecOpc;
   unsigned Exec;
 
+  bool EnableOptimizeEndCf = false;
+
   bool hasKill(const MachineBasicBlock *Begin, const MachineBasicBlock *End);
 
   void emitIf(MachineInstr &MI);
@@ -579,10 +582,10 @@ void SILowerControlFlow::combineMasks(MachineInstr &MI) {
 void SILowerControlFlow::optimizeEndCf() {
   // If the only instruction immediately following this END_CF is an another
   // END_CF in the only successor we can avoid emitting exec mask restore here.
-  if (!RemoveRedundantEndcf)
+  if (!EnableOptimizeEndCf)
     return;
 
-  for (MachineInstr *MI : LoweredEndCf) {
+  for (MachineInstr *MI : reverse(LoweredEndCf)) {
     MachineBasicBlock &MBB = *MI->getParent();
     auto Next =
       skipIgnoreExecInstsTrivialSucc(MBB, std::next(MI->getIterator()));
@@ -807,6 +810,8 @@ bool SILowerControlFlow::runOnMachineFunction(MachineFunction &MF) {
   const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
   TII = ST.getInstrInfo();
   TRI = &TII->getRegisterInfo();
+  EnableOptimizeEndCf =
+      RemoveRedundantEndcf && MF.getTarget().getOptLevel() > CodeGenOpt::None;
 
   // This doesn't actually need LiveIntervals, but we can preserve them.
   LIS = getAnalysisIfAvailable<LiveIntervals>();