Index: llvm/trunk/include/llvm/CodeGen/MachineInstr.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/MachineInstr.h
+++ llvm/trunk/include/llvm/CodeGen/MachineInstr.h
@@ -427,6 +427,22 @@
     return getNumExplicitDefs() + MCID->getNumImplicitDefs();
   }
 
+  /// Returns true if the instruction has implicit definition.
+  bool hasImplicitDef() const {
+    for (unsigned I = getNumExplicitOperands(), E = getNumOperands();
+      I != E; ++I) {
+      const MachineOperand &MO = getOperand(I);
+      if (MO.isDef() && MO.isImplicit())
+        return true;
+    }
+    return false;
+  }
+
+  /// Returns the implicit operands number.
+  unsigned getNumImplicitOperands() const {
+    return getNumOperands() - getNumExplicitOperands();
+  }
+
   /// Return true if operand \p OpIdx is a subregister index.
   bool isOperandSubregIdx(unsigned OpIdx) const {
     assert(getOperand(OpIdx).getType() == MachineOperand::MO_Immediate &&
Index: llvm/trunk/lib/CodeGen/PeepholeOptimizer.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/PeepholeOptimizer.cpp
+++ llvm/trunk/lib/CodeGen/PeepholeOptimizer.cpp
@@ -1808,7 +1808,11 @@
   assert(Def->isCopy() && "Invalid definition");
   // Copy instruction are supposed to be: Def = Src.
   // If someone breaks this assumption, bad things will happen everywhere.
-  assert(Def->getNumOperands() == 2 && "Invalid number of operands");
+  // There may be implicit uses preventing the copy to be moved across
+  // some target specific register definitions
+  assert(Def->getNumOperands() - Def->getNumImplicitOperands() == 2 &&
+         "Invalid number of operands");
+  assert(!Def->hasImplicitDef() && "Only implicit uses are allowed");
 
   if (Def->getOperand(DefIdx).getSubReg() != DefSubReg)
     // If we look for a different subreg, it means we want a subreg of src.
Index: llvm/trunk/lib/Target/AMDGPU/SIFoldOperands.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ llvm/trunk/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -612,6 +612,13 @@
       return;
 
     UseMI->setDesc(TII->get(MovOp));
+    MachineInstr::mop_iterator ImpOpI = UseMI->implicit_operands().begin();
+    MachineInstr::mop_iterator ImpOpE = UseMI->implicit_operands().end();
+    while (ImpOpI != ImpOpE) {
+      MachineInstr::mop_iterator Tmp = ImpOpI;
+      ImpOpI++;
+      UseMI->RemoveOperand(UseMI->getOperandNo(Tmp));
+    }
     CopiesToReplace.push_back(UseMI);
   } else {
     if (UseMI->isCopy() && OpToFold.isReg() &&
Index: llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -4200,6 +4200,15 @@
   // Try to eliminate the copy if it is copying an immediate value.
   if (Def->isMoveImmediate())
     FoldImmediate(*Copy, *Def, OpReg, &MRI);
+
+  bool ImpDef = Def->isImplicitDef();
+  while (!ImpDef && Def && Def->isCopy()) {
+    Def = MRI.getUniqueVRegDef(Def->getOperand(1).getReg());
+    ImpDef = Def && Def->isImplicitDef();
+  }
+  if (!RI.isSGPRClass(DstRC) && !Copy->readsRegister(AMDGPU::EXEC, &RI) &&
+      !ImpDef)
+    Copy->addOperand(MachineOperand::CreateReg(AMDGPU::EXEC, false, true));
 }
 
 // Emit the actual waterfall loop, executing the wrapped instruction for each
Index: llvm/trunk/test/CodeGen/AMDGPU/constant-fold-imm-immreg.mir
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/constant-fold-imm-immreg.mir
+++ llvm/trunk/test/CodeGen/AMDGPU/constant-fold-imm-immreg.mir
@@ -882,7 +882,7 @@
 ---
 
 # GCN-LABEL: name: constant_fold_lshl_or_reg0_immreg_immreg{{$}}
-# GCN: %3:vgpr_32 = V_MOV_B32_e32 12345, implicit $exec, implicit $exec
+# GCN: %3:vgpr_32 = V_MOV_B32_e32 12345, implicit $exec
 # GCN-NEXT: S_ENDPGM 0, implicit %3
 
 name: constant_fold_lshl_or_reg0_immreg_immreg