Index: llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -417,7 +417,23 @@
                             const MachineInstr &MI,
                             const MachineOperand &UseMO) {
   return !UseMO.isUndef() && !TII->isSDWA(MI);
-  //return !MI.hasRegisterImplicitUseOperand(UseMO.getReg());
+}
+
+static bool isFoldingRegisterAcrossExecDef(const MachineInstr &MI,
+                                          const MachineOperand &UseMO) {
+  const MachineInstr *Def = UseMO.getParent();
+  const MachineBasicBlock *MBB = MI.getParent();
+  const MachineBasicBlock *DefBB = Def->getParent();
+  bool CrossDefExec = false;
+  if (!const_cast<MachineBasicBlock *>(DefBB)->canFallThrough() &&
+      (DefBB != MBB)) {
+    MachineBasicBlock::const_iterator IT =
+        Def->getParent()->getFirstTerminator();
+    const MachineInstr *Term = &*IT;
+    CrossDefExec = Def->hasRegisterImplicitUseOperand(AMDGPU::EXEC) &&
+                   Term->definesRegister(AMDGPU::EXEC);
+  }
+  return CrossDefExec;
 }
 
 static bool tryToFoldACImm(const SIInstrInfo *TII,
@@ -1086,6 +1102,9 @@
     Copy->addImplicitDefUseOperands(*MF);
 
   for (FoldCandidate &Fold : FoldList) {
+    if (Fold.isReg() &&
+        isFoldingRegisterAcrossExecDef(*Fold.UseMI, *Fold.OpToFold))
+      continue;
     if (updateOperand(Fold, *TII, *TRI, *ST)) {
       // Clear kill flags.
       if (Fold.isReg()) {