diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -7093,7 +7093,6 @@
 
   return false;
 }
-
 bool llvm::execMayBeModifiedBeforeAnyUse(const MachineRegisterInfo &MRI,
                                          Register VReg,
                                          const MachineInstr &DefMI) {
@@ -7102,16 +7101,17 @@
   auto *TRI = MRI.getTargetRegisterInfo();
   auto *DefBB = DefMI.getParent();
 
-  const int MaxUseInstScan = 10;
-  int NumUseInst = 0;
+  const int MaxUseScan = 10;
+  int NumUse = 0;
 
-  for (auto &UseInst : MRI.use_nodbg_instructions(VReg)) {
+  for (auto &Use : MRI.use_nodbg_operands(VReg)) {
+    auto &UseInst = *Use.getParent();
     // Don't bother searching between blocks, although it is possible this block
     // doesn't modify exec.
     if (UseInst.getParent() != DefBB)
       return true;
 
-    if (++NumUseInst > MaxUseInstScan)
+    if (++NumUse > MaxUseScan)
       return true;
   }
 
@@ -7120,18 +7120,31 @@
 
   // Stop scan when we have seen all the uses.
   for (auto I = std::next(DefMI.getIterator()); ; ++I) {
+    assert(I != DefBB->end());
+
     if (I->isDebugInstr())
       continue;
 
     if (++NumInst > MaxInstScan)
       return true;
 
-    if (I->readsRegister(VReg))
-      if (--NumUseInst == 0)
-        return false;
+    for (unsigned OpI = 0, E = I->getNumOperands(); OpI != E; ++OpI) {
+      const auto &Op = I->getOperand(OpI);
 
-    if (I->modifiesRegister(AMDGPU::EXEC, TRI))
-      return true;
+      if (Op.isRegMask() && Op.clobbersPhysReg(AMDGPU::EXEC))
+        return true;
+
+      if (!Op.isReg())
+        continue;
+
+      Register Reg = Op.getReg();
+      if (Op.isUse()) {
+        if (Reg == VReg && --NumUse == 0)
+          return false;
+      } else // Reg is a def
+          if (TRI->regsOverlap(Reg, AMDGPU::EXEC))
+        return true;
+    }
   }
 }