Index: llvm/trunk/include/llvm/Analysis/DivergenceAnalysis.h
===================================================================
--- llvm/trunk/include/llvm/Analysis/DivergenceAnalysis.h
+++ llvm/trunk/include/llvm/Analysis/DivergenceAnalysis.h
@@ -13,6 +13,8 @@
 // better decisions.
 //
 //===----------------------------------------------------------------------===//
+#ifndef LLVM_ANALYSIS_DIVERGENCE_ANALYSIS_H
+#define LLVM_ANALYSIS_DIVERGENCE_ANALYSIS_H
 
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/IR/Function.h"
@@ -46,3 +48,5 @@
   DenseSet<const Value *> DivergentValues;
 };
 } // End llvm namespace
+
+#endif //LLVM_ANALYSIS_DIVERGENCE_ANALYSIS_H
\ No newline at end of file
Index: llvm/trunk/include/llvm/CodeGen/FunctionLoweringInfo.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/FunctionLoweringInfo.h
+++ llvm/trunk/include/llvm/CodeGen/FunctionLoweringInfo.h
@@ -118,6 +118,17 @@
   /// cross-basic-block values.
   DenseMap<const Value *, unsigned> ValueMap;
 
+  /// VirtReg2Value map is needed by the Divergence Analysis driven
+  /// instruction selection. It is reverted ValueMap. It is computed
+  /// in lazy style - on demand. It is used to get the Value corresponding
+  /// to the live in virtual register and is called from the
+  /// TargetLowerinInfo::isSDNodeSourceOfDivergence.
+  DenseMap<unsigned, const Value*> VirtReg2Value;
+
+  /// This method is called from TargetLowerinInfo::isSDNodeSourceOfDivergence
+  /// to get the Value corresponding to the live-in virtual register.
+  const Value * getValueFromVirtualReg(unsigned Vreg);
+
   /// Track virtual registers created for exception pointers.
   DenseMap<const Value *, unsigned> CatchPadExceptionPointers;
 
Index: llvm/trunk/include/llvm/CodeGen/SelectionDAG.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/SelectionDAG.h
+++ llvm/trunk/include/llvm/CodeGen/SelectionDAG.h
@@ -28,8 +28,10 @@
 #include "llvm/ADT/iterator.h"
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/Analysis/AliasAnalysis.h"
+#include "llvm/Analysis/DivergenceAnalysis.h"
 #include "llvm/CodeGen/DAGCombine.h"
 #include "llvm/CodeGen/ISDOpcodes.h"
+#include "llvm/CodeGen/FunctionLoweringInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineMemOperand.h"
 #include "llvm/CodeGen/MachineValueType.h"
@@ -217,6 +219,9 @@
   LLVMContext *Context;
   CodeGenOpt::Level OptLevel;
 
+  DivergenceAnalysis * DA = nullptr;
+  FunctionLoweringInfo * FLI = nullptr;
+
   /// The function-level optimization remark emitter.  Used to emit remarks
   /// whenever manipulating the DAG.
   OptimizationRemarkEmitter *ORE;
@@ -346,19 +351,7 @@
          .getRawSubclassData();
   }
 
-  void createOperands(SDNode *Node, ArrayRef<SDValue> Vals) {
-    assert(!Node->OperandList && "Node already has operands");
-    SDUse *Ops = OperandRecycler.allocate(
-        ArrayRecycler<SDUse>::Capacity::get(Vals.size()), OperandAllocator);
-
-    for (unsigned I = 0; I != Vals.size(); ++I) {
-      Ops[I].setUser(Node);
-      Ops[I].setInitial(Vals[I]);
-    }
-    Node->NumOperands = Vals.size();
-    Node->OperandList = Ops;
-    checkForCycles(Node);
-  }
+  void createOperands(SDNode *Node, ArrayRef<SDValue> Vals);
 
   void removeOperands(SDNode *Node) {
     if (!Node->OperandList)
@@ -369,7 +362,7 @@
     Node->NumOperands = 0;
     Node->OperandList = nullptr;
   }
-
+  void CreateTopologicalOrder(std::vector<SDNode*>& Order);
 public:
   explicit SelectionDAG(const TargetMachine &TM, CodeGenOpt::Level);
   SelectionDAG(const SelectionDAG &) = delete;
@@ -378,7 +371,12 @@
 
   /// Prepare this SelectionDAG to process code in the given MachineFunction.
   void init(MachineFunction &NewMF, OptimizationRemarkEmitter &NewORE,
-            Pass *PassPtr, const TargetLibraryInfo *LibraryInfo);
+            Pass *PassPtr, const TargetLibraryInfo *LibraryInfo,
+            DivergenceAnalysis * DA);
+
+  void setFunctionLoweringInfo(FunctionLoweringInfo * FuncInfo) {
+    FLI = FuncInfo;
+  }
 
   /// Clear state and free memory necessary to make this
   /// SelectionDAG ready to process a new block.
@@ -463,6 +461,8 @@
     return Root;
   }
 
+  void VerifyDAGDiverence();
+
   /// This iterates over the nodes in the SelectionDAG, folding
   /// certain types of nodes together, or eliminating superfluous nodes.  The
   /// Level argument controls whether Combine is allowed to produce nodes and
@@ -1128,6 +1128,9 @@
                                SDValue Op3, SDValue Op4, SDValue Op5);
   SDNode *UpdateNodeOperands(SDNode *N, ArrayRef<SDValue> Ops);
 
+  // Propagates the change in divergence to users
+  void updateDivergence(SDNode * N);
+
   /// These are used for target selectors to *mutate* the
   /// specified node to have the specified return type, Target opcode, and
   /// operands.  Note that target opcodes are stored as
Index: llvm/trunk/include/llvm/CodeGen/SelectionDAGNodes.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/SelectionDAGNodes.h
+++ llvm/trunk/include/llvm/CodeGen/SelectionDAGNodes.h
@@ -466,11 +466,13 @@
     friend class SDNode;
     friend class MemIntrinsicSDNode;
     friend class MemSDNode;
+    friend class SelectionDAG;
 
     uint16_t HasDebugValue : 1;
     uint16_t IsMemIntrinsic : 1;
+    uint16_t IsDivergent : 1;
   };
-  enum { NumSDNodeBits = 2 };
+  enum { NumSDNodeBits = 3 };
 
   class ConstantSDNodeBitfields {
     friend class ConstantSDNode;
@@ -662,6 +664,8 @@
   bool getHasDebugValue() const { return SDNodeBits.HasDebugValue; }
   void setHasDebugValue(bool b) { SDNodeBits.HasDebugValue = b; }
 
+  bool isDivergent() const { return SDNodeBits.IsDivergent; }
+
   /// Return true if there are no uses of this node.
   bool use_empty() const { return UseList == nullptr; }
 
Index: llvm/trunk/include/llvm/CodeGen/TargetLowering.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/TargetLowering.h
+++ llvm/trunk/include/llvm/CodeGen/TargetLowering.h
@@ -29,6 +29,7 @@
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/Analysis/DivergenceAnalysis.h"
 #include "llvm/CodeGen/DAGCombine.h"
 #include "llvm/CodeGen/ISDOpcodes.h"
 #include "llvm/CodeGen/MachineValueType.h"
@@ -2562,6 +2563,16 @@
 
   bool isPositionIndependent() const;
 
+  virtual bool isSDNodeSourceOfDivergence(const SDNode *N,
+                                          FunctionLoweringInfo *FLI,
+                                          DivergenceAnalysis *DA) const {
+    return false;
+  }
+
+  virtual bool isSDNodeAlwaysUniform(const SDNode * N) const {
+    return false;
+  }
+
   /// Returns true by value, base pointer and offset pointer and addressing mode
   /// by reference if the node's address can be legally represented as
   /// pre-indexed load / store address.
Index: llvm/trunk/lib/CodeGen/SelectionDAG/FunctionLoweringInfo.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/FunctionLoweringInfo.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/FunctionLoweringInfo.cpp
@@ -547,3 +547,13 @@
   }
   return std::make_pair(It->second, false);
 }
+
+const Value *
+FunctionLoweringInfo::getValueFromVirtualReg(unsigned Vreg) {
+  if (VirtReg2Value.empty()) {
+    for (auto &P : ValueMap) {
+      VirtReg2Value[P.second] = P.first;
+    }
+  }
+  return VirtReg2Value[Vreg];
+}
Index: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -950,7 +950,8 @@
 
 void SelectionDAG::init(MachineFunction &NewMF,
                         OptimizationRemarkEmitter &NewORE,
-                        Pass *PassPtr, const TargetLibraryInfo *LibraryInfo) {
+                        Pass *PassPtr, const TargetLibraryInfo *LibraryInfo,
+                        DivergenceAnalysis * Divergence) {
   MF = &NewMF;
   SDAGISelPass = PassPtr;
   ORE = &NewORE;
@@ -958,6 +959,7 @@
   TSI = getSubtarget().getSelectionDAGInfo();
   LibInfo = LibraryInfo;
   Context = &MF->getFunction().getContext();
+  DA = Divergence;
 }
 
 SelectionDAG::~SelectionDAG() {
@@ -1713,6 +1715,7 @@
     return SDValue(E, 0);
 
   auto *N = newSDNode<RegisterSDNode>(RegNo, VT);
+  N->SDNodeBits.IsDivergent = TLI->isSDNodeSourceOfDivergence(N, FLI, DA);
   CSEMap.InsertNode(N, IP);
   InsertNode(N);
   return SDValue(N, 0);
@@ -6699,6 +6702,7 @@
   if (N->OperandList[1] != Op2)
     N->OperandList[1].set(Op2);
 
+  updateDivergence(N);
   // If this gets put into a CSE map, add it.
   if (InsertPos) CSEMap.InsertNode(N, InsertPos);
   return N;
@@ -7340,8 +7344,9 @@
       SDUse &Use = UI.getUse();
       ++UI;
       Use.set(To);
+      if (To->isDivergent() != From->isDivergent())
+        updateDivergence(User);
     } while (UI != UE && *UI == User);
-
     // Now that we have modified User, add it back to the CSE maps.  If it
     // already exists there, recursively merge the results together.
     AddModifiedNodeToCSEMaps(User);
@@ -7395,6 +7400,8 @@
       SDUse &Use = UI.getUse();
       ++UI;
       Use.setNode(To);
+      if (To->isDivergent() != From->isDivergent())
+        updateDivergence(User);
     } while (UI != UE && *UI == User);
 
     // Now that we have modified User, add it back to the CSE maps.  If it
@@ -7439,8 +7446,9 @@
       const SDValue &ToOp = To[Use.getResNo()];
       ++UI;
       Use.set(ToOp);
+      if (To->getNode()->isDivergent() != From->isDivergent())
+        updateDivergence(User);
     } while (UI != UE && *UI == User);
-
     // Now that we have modified User, add it back to the CSE maps.  If it
     // already exists there, recursively merge the results together.
     AddModifiedNodeToCSEMaps(User);
@@ -7498,8 +7506,9 @@
 
       ++UI;
       Use.set(To);
+      if (To->isDivergent() != From->isDivergent())
+        updateDivergence(User);
     } while (UI != UE && *UI == User);
-
     // We are iterating over all uses of the From node, so if a use
     // doesn't use the specific value, no changes are made.
     if (!UserRemovedFromCSEMaps)
@@ -7532,6 +7541,70 @@
 
 } // end anonymous namespace
 
+void SelectionDAG::updateDivergence(SDNode * N)
+{
+  if (TLI->isSDNodeAlwaysUniform(N))
+    return;
+  bool IsDivergent = TLI->isSDNodeSourceOfDivergence(N, FLI, DA);
+  for (auto &Op : N->ops()) {
+    if (Op.Val.getValueType() != MVT::Other)
+      IsDivergent |= Op.getNode()->isDivergent();
+  }
+  if (N->SDNodeBits.IsDivergent != IsDivergent) {
+    N->SDNodeBits.IsDivergent = IsDivergent;
+    for (auto U : N->uses()) {
+      updateDivergence(U);
+    }
+  }
+}
+
+
+void SelectionDAG::CreateTopologicalOrder(std::vector<SDNode*>& Order) {
+  DenseMap<SDNode *, unsigned> Degree;
+  Order.reserve(AllNodes.size());
+  for (auto & N : allnodes()) {
+    unsigned NOps = N.getNumOperands();
+    Degree[&N] = NOps;
+    if (0 == NOps)
+      Order.push_back(&N);
+  }
+  for (std::vector<SDNode *>::iterator I = Order.begin();
+  I!=Order.end();++I) {
+    SDNode * N = *I;
+    for (auto U : N->uses()) {
+      unsigned &UnsortedOps = Degree[U];
+      if (0 == --UnsortedOps)
+        Order.push_back(U);
+    }
+  }
+}
+
+void SelectionDAG::VerifyDAGDiverence()
+{
+  std::vector<SDNode*> TopoOrder;
+  CreateTopologicalOrder(TopoOrder);
+  const TargetLowering &TLI = getTargetLoweringInfo();
+  DenseMap<const SDNode *, bool> DivergenceMap;
+  for (auto &N : allnodes()) {
+    DivergenceMap[&N] = false;
+  }
+  for (auto N : TopoOrder) {
+    bool IsDivergent = DivergenceMap[N];
+    bool IsSDNodeDivergent = TLI.isSDNodeSourceOfDivergence(N, FLI, DA);
+    for (auto &Op : N->ops()) {
+      if (Op.Val.getValueType() != MVT::Other)
+        IsSDNodeDivergent |= DivergenceMap[Op.getNode()];
+    }
+    if (!IsDivergent && IsSDNodeDivergent && !TLI.isSDNodeAlwaysUniform(N)) {
+      DivergenceMap[N] = true;
+    }
+  }
+  for (auto &N : allnodes()) {
+    assert(DivergenceMap[&N] == N.isDivergent() && "Divergence bit inconsistency detected\n");
+  }
+}
+
+
 /// ReplaceAllUsesOfValuesWith - Replace any uses of From with To, leaving
 /// uses of other values produced by From.getNode() alone.  The same value
 /// may appear in both the From and To list.  The Deleted vector is
@@ -8337,6 +8410,26 @@
   return nullptr;
 }
 
+void SelectionDAG::createOperands(SDNode *Node, ArrayRef<SDValue> Vals) {
+  assert(!Node->OperandList && "Node already has operands");
+  SDUse *Ops = OperandRecycler.allocate(
+    ArrayRecycler<SDUse>::Capacity::get(Vals.size()), OperandAllocator);
+
+  bool IsDivergent = false;
+  for (unsigned I = 0; I != Vals.size(); ++I) {
+    Ops[I].setUser(Node);
+    Ops[I].setInitial(Vals[I]);
+    if (Ops[I].Val.getValueType() != MVT::Other) // Skip Chain. It does not carry divergence.
+      IsDivergent = IsDivergent || Ops[I].getNode()->isDivergent();
+  }
+  Node->NumOperands = Vals.size();
+  Node->OperandList = Ops;
+  IsDivergent |= TLI->isSDNodeSourceOfDivergence(Node, FLI, DA);
+  if (!TLI->isSDNodeAlwaysUniform(Node))
+    Node->SDNodeBits.IsDivergent = IsDivergent;
+  checkForCycles(Node);
+}
+
 #ifndef NDEBUG
 static void checkForCyclesHelper(const SDNode *N,
                                  SmallPtrSetImpl<const SDNode*> &Visited,
Index: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
@@ -629,6 +629,8 @@
 
     if (getNodeId() != -1)
       OS << " [ID=" << getNodeId() << ']';
+    if (!(isa<ConstantSDNode>(this) || (isa<ConstantFPSDNode>(this))))
+      OS << "# D:" << isDivergent();
 
     if (!G)
       return;
Index: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
@@ -29,6 +29,7 @@
 #include "llvm/Analysis/CFG.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/CodeGen/FastISel.h"
 #include "llvm/CodeGen/FunctionLoweringInfo.h"
 #include "llvm/CodeGen/GCMetadata.h"
@@ -329,6 +330,7 @@
   AU.addPreserved<StackProtector>();
   AU.addPreserved<GCModuleInfo>();
   AU.addRequired<TargetLibraryInfoWrapperPass>();
+  AU.addRequired<TargetTransformInfoWrapperPass>();
   if (UseMBPI && OptLevel != CodeGenOpt::None)
     AU.addRequired<BranchProbabilityInfoWrapperPass>();
   MachineFunctionPass::getAnalysisUsage(AU);
@@ -414,7 +416,8 @@
 
   SplitCriticalSideEffectEdges(const_cast<Function &>(Fn), DT, LI);
 
-  CurDAG->init(*MF, *ORE, this, LibInfo);
+  CurDAG->init(*MF, *ORE, this, LibInfo,
+   getAnalysisIfAvailable<DivergenceAnalysis>());
   FuncInfo->set(Fn, *MF, CurDAG);
 
   // Now get the optional analyzes if we want to.
@@ -711,6 +714,8 @@
   int BlockNumber = -1;
   (void)BlockNumber;
   bool MatchFilterBB = false; (void)MatchFilterBB;
+  TargetTransformInfo &TTI =
+      getAnalysis<TargetTransformInfoWrapperPass>().getTTI(*FuncInfo->Fn);
 
   // Pre-type legalization allow creation of any node types.
   CurDAG->NewNodesMustHaveLegalTypes = false;
@@ -744,6 +749,9 @@
     CurDAG->Combine(BeforeLegalizeTypes, AA, OptLevel);
   }
 
+  if (TTI.hasBranchDivergence())
+    CurDAG->VerifyDAGDiverence();
+
   DEBUG(dbgs() << "Optimized lowered selection DAG: "
                << printMBBReference(*FuncInfo->MBB) << " '" << BlockName
                << "'\n";
@@ -761,6 +769,9 @@
     Changed = CurDAG->LegalizeTypes();
   }
 
+  if (TTI.hasBranchDivergence())
+    CurDAG->VerifyDAGDiverence();
+
   DEBUG(dbgs() << "Type-legalized selection DAG: "
                << printMBBReference(*FuncInfo->MBB) << " '" << BlockName
                << "'\n";
@@ -780,6 +791,9 @@
       CurDAG->Combine(AfterLegalizeTypes, AA, OptLevel);
     }
 
+    if (TTI.hasBranchDivergence())
+      CurDAG->VerifyDAGDiverence();
+
     DEBUG(dbgs() << "Optimized type-legalized selection DAG: "
                  << printMBBReference(*FuncInfo->MBB) << " '" << BlockName
                  << "'\n";
@@ -823,6 +837,9 @@
                  << printMBBReference(*FuncInfo->MBB) << " '" << BlockName
                  << "'\n";
           CurDAG->dump());
+
+    if (TTI.hasBranchDivergence())
+      CurDAG->VerifyDAGDiverence();
   }
 
   if (ViewLegalizeDAGs && MatchFilterBB)
@@ -834,6 +851,9 @@
     CurDAG->Legalize();
   }
 
+  if (TTI.hasBranchDivergence())
+    CurDAG->VerifyDAGDiverence();
+
   DEBUG(dbgs() << "Legalized selection DAG: "
                << printMBBReference(*FuncInfo->MBB) << " '" << BlockName
                << "'\n";
@@ -849,6 +869,9 @@
     CurDAG->Combine(AfterLegalizeDAG, AA, OptLevel);
   }
 
+  if (TTI.hasBranchDivergence())
+    CurDAG->VerifyDAGDiverence();
+
   DEBUG(dbgs() << "Optimized legalized selection DAG: "
                << printMBBReference(*FuncInfo->MBB) << " '" << BlockName
                << "'\n";
@@ -1401,6 +1424,8 @@
   FuncInfo->MBB = FuncInfo->MBBMap[&Fn.getEntryBlock()];
   FuncInfo->InsertPt = FuncInfo->MBB->begin();
 
+  CurDAG->setFunctionLoweringInfo(FuncInfo);
+
   if (!FastIS) {
     LowerArguments(Fn);
   } else {
Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
@@ -27,6 +27,7 @@
 #include "llvm/ADT/APInt.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/Analysis/DivergenceAnalysis.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/FunctionLoweringInfo.h"
 #include "llvm/CodeGen/ISDOpcodes.h"
@@ -83,6 +84,7 @@
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<AMDGPUArgumentUsageInfo>();
+    AU.addRequired<DivergenceAnalysis>();
     SelectionDAGISel::getAnalysisUsage(AU);
   }
 
Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.h
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.h
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.h
@@ -168,6 +168,9 @@
   bool isCheapToSpeculateCttz() const override;
   bool isCheapToSpeculateCtlz() const override;
 
+  bool isSDNodeSourceOfDivergence(const SDNode * N,
+    FunctionLoweringInfo * FLI, DivergenceAnalysis * DA) const;
+  bool isSDNodeAlwaysUniform(const SDNode * N) const;
   static CCAssignFn *CCAssignFnForCall(CallingConv::ID CC, bool IsVarArg);
   static CCAssignFn *CCAssignFnForReturn(CallingConv::ID CC, bool IsVarArg);
 
Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -25,6 +25,7 @@
 #include "AMDGPURegisterInfo.h"
 #include "AMDGPUSubtarget.h"
 #include "AMDGPUTargetMachine.h"
+#include "Utils/AMDGPUBaseInfo.h"
 #include "R600MachineFunctionInfo.h"
 #include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
@@ -748,6 +749,101 @@
   return true;
 }
 
+bool AMDGPUTargetLowering::isSDNodeAlwaysUniform(const SDNode * N) const {
+  switch (N->getOpcode()) {
+    default:
+    return false;
+    case ISD::EntryToken:
+    case ISD::TokenFactor:
+      return true;
+    case ISD::INTRINSIC_WO_CHAIN:
+    {
+      unsigned IntrID = cast<ConstantSDNode>(N->getOperand(0))->getZExtValue();
+      switch (IntrID) {
+        default:
+        return false;
+        case Intrinsic::amdgcn_readfirstlane:
+        case Intrinsic::amdgcn_readlane:
+          return true;
+      }
+    }
+    break;
+    case ISD::LOAD:
+    {
+      const LoadSDNode * L = dyn_cast<LoadSDNode>(N);
+      if (L->getMemOperand()->getAddrSpace()
+      == Subtarget->getAMDGPUAS().CONSTANT_ADDRESS_32BIT)
+        return true;
+      return false;
+    }
+    break;
+  }
+}
+
+bool AMDGPUTargetLowering::isSDNodeSourceOfDivergence(const SDNode * N,
+  FunctionLoweringInfo * FLI, DivergenceAnalysis * DA) const
+{
+  switch (N->getOpcode()) {
+    case ISD::Register:
+    case ISD::CopyFromReg:
+    {
+      const RegisterSDNode *R = nullptr;
+      if (N->getOpcode() == ISD::Register) {
+        R = dyn_cast<RegisterSDNode>(N);
+      }
+      else {
+        R = dyn_cast<RegisterSDNode>(N->getOperand(1));
+      }
+      if (R)
+      {
+        const MachineFunction * MF = FLI->MF;
+        const SISubtarget &ST = MF->getSubtarget<SISubtarget>();
+        const MachineRegisterInfo &MRI = MF->getRegInfo();
+        const SIRegisterInfo &TRI = ST.getInstrInfo()->getRegisterInfo();
+        unsigned Reg = R->getReg();
+        if (TRI.isPhysicalRegister(Reg))
+          return TRI.isVGPR(MRI, Reg);
+
+        if (MRI.isLiveIn(Reg)) {
+          // workitem.id.x workitem.id.y workitem.id.z
+          if ((MRI.getLiveInPhysReg(Reg) == AMDGPU::T0_X) ||
+              (MRI.getLiveInPhysReg(Reg) == AMDGPU::T0_Y) ||
+              (MRI.getLiveInPhysReg(Reg) == AMDGPU::T0_Z)||
+              (MRI.getLiveInPhysReg(Reg) == AMDGPU::VGPR0) ||
+            (MRI.getLiveInPhysReg(Reg) == AMDGPU::VGPR1) ||
+            (MRI.getLiveInPhysReg(Reg) == AMDGPU::VGPR2))
+              return true;
+          // Formal arguments of non-entry functions
+          // are conservatively considered divergent
+          else if (!AMDGPU::isEntryFunctionCC(FLI->Fn->getCallingConv()))
+            return true;
+        }
+        return !DA || DA->isDivergent(FLI->getValueFromVirtualReg(Reg));
+      }
+    }
+    break;
+    case ISD::LOAD: {
+      const LoadSDNode *L = dyn_cast<LoadSDNode>(N);
+      if (L->getMemOperand()->getAddrSpace() ==
+          Subtarget->getAMDGPUAS().PRIVATE_ADDRESS)
+        return true;
+    } break;
+    case ISD::CALLSEQ_END:
+    return true;
+    break;
+    case ISD::INTRINSIC_WO_CHAIN:
+    {
+
+    }
+      return AMDGPU::isIntrinsicSourceOfDivergence(
+      cast<ConstantSDNode>(N->getOperand(0))->getZExtValue());
+    case ISD::INTRINSIC_W_CHAIN:
+      return AMDGPU::isIntrinsicSourceOfDivergence(
+      cast<ConstantSDNode>(N->getOperand(1))->getZExtValue());
+  }
+  return false;
+}
+
 //===---------------------------------------------------------------------===//
 // Target Properties
 //===---------------------------------------------------------------------===//
Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -17,6 +17,7 @@
 
 #include "AMDGPUTargetTransformInfo.h"
 #include "AMDGPUSubtarget.h"
+#include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
@@ -464,55 +465,7 @@
   }
 }
 
-static bool isIntrinsicSourceOfDivergence(const IntrinsicInst *I) {
-  switch (I->getIntrinsicID()) {
-  case Intrinsic::amdgcn_workitem_id_x:
-  case Intrinsic::amdgcn_workitem_id_y:
-  case Intrinsic::amdgcn_workitem_id_z:
-  case Intrinsic::amdgcn_interp_mov:
-  case Intrinsic::amdgcn_interp_p1:
-  case Intrinsic::amdgcn_interp_p2:
-  case Intrinsic::amdgcn_mbcnt_hi:
-  case Intrinsic::amdgcn_mbcnt_lo:
-  case Intrinsic::r600_read_tidig_x:
-  case Intrinsic::r600_read_tidig_y:
-  case Intrinsic::r600_read_tidig_z:
-  case Intrinsic::amdgcn_atomic_inc:
-  case Intrinsic::amdgcn_atomic_dec:
-  case Intrinsic::amdgcn_ds_fadd:
-  case Intrinsic::amdgcn_ds_fmin:
-  case Intrinsic::amdgcn_ds_fmax:
-  case Intrinsic::amdgcn_image_atomic_swap:
-  case Intrinsic::amdgcn_image_atomic_add:
-  case Intrinsic::amdgcn_image_atomic_sub:
-  case Intrinsic::amdgcn_image_atomic_smin:
-  case Intrinsic::amdgcn_image_atomic_umin:
-  case Intrinsic::amdgcn_image_atomic_smax:
-  case Intrinsic::amdgcn_image_atomic_umax:
-  case Intrinsic::amdgcn_image_atomic_and:
-  case Intrinsic::amdgcn_image_atomic_or:
-  case Intrinsic::amdgcn_image_atomic_xor:
-  case Intrinsic::amdgcn_image_atomic_inc:
-  case Intrinsic::amdgcn_image_atomic_dec:
-  case Intrinsic::amdgcn_image_atomic_cmpswap:
-  case Intrinsic::amdgcn_buffer_atomic_swap:
-  case Intrinsic::amdgcn_buffer_atomic_add:
-  case Intrinsic::amdgcn_buffer_atomic_sub:
-  case Intrinsic::amdgcn_buffer_atomic_smin:
-  case Intrinsic::amdgcn_buffer_atomic_umin:
-  case Intrinsic::amdgcn_buffer_atomic_smax:
-  case Intrinsic::amdgcn_buffer_atomic_umax:
-  case Intrinsic::amdgcn_buffer_atomic_and:
-  case Intrinsic::amdgcn_buffer_atomic_or:
-  case Intrinsic::amdgcn_buffer_atomic_xor:
-  case Intrinsic::amdgcn_buffer_atomic_cmpswap:
-  case Intrinsic::amdgcn_ps_live:
-  case Intrinsic::amdgcn_ds_swizzle:
-    return true;
-  default:
-    return false;
-  }
-}
+
 
 static bool isArgPassedInSGPR(const Argument *A) {
   const Function *F = A->getParent();
@@ -563,7 +516,7 @@
     return true;
 
   if (const IntrinsicInst *Intrinsic = dyn_cast<IntrinsicInst>(V))
-    return isIntrinsicSourceOfDivergence(Intrinsic);
+    return AMDGPU::isIntrinsicSourceOfDivergence(Intrinsic->getIntrinsicID());
 
   // Assume all function calls are a source of divergence.
   if (isa<CallInst>(V) || isa<InvokeInst>(V))
Index: llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
+++ llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -5372,7 +5372,7 @@
   unsigned NumElements = MemVT.getVectorNumElements();
   if (AS == AMDGPUASI.CONSTANT_ADDRESS ||
       AS == AMDGPUASI.CONSTANT_ADDRESS_32BIT) {
-    if (isMemOpUniform(Load))
+    if (!Op->isDivergent())
       return SDValue();
     // Non-uniform loads will be selected to MUBUF instructions, so they
     // have the same legalization requirements as global and private
@@ -5382,7 +5382,7 @@
   if (AS == AMDGPUASI.CONSTANT_ADDRESS ||
       AS == AMDGPUASI.CONSTANT_ADDRESS_32BIT ||
       AS == AMDGPUASI.GLOBAL_ADDRESS) {
-    if (Subtarget->getScalarizeGlobalBehavior() && isMemOpUniform(Load) &&
+    if (Subtarget->getScalarizeGlobalBehavior() && !Op->isDivergent() &&
         !Load->isVolatile() && isMemOpHasNoClobberedMemOperand(Load))
       return SDValue();
     // Non-uniform loads will be selected to MUBUF instructions, so they
Index: llvm/trunk/lib/Target/AMDGPU/SMInstructions.td
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SMInstructions.td
+++ llvm/trunk/lib/Target/AMDGPU/SMInstructions.td
@@ -223,12 +223,9 @@
 def smrd_load : PatFrag <(ops node:$ptr), (load node:$ptr), [{
   auto Ld = cast<LoadSDNode>(N);
   return Ld->getAlignment() >= 4  &&
-    (((Ld->getAddressSpace() == AMDGPUASI.CONSTANT_ADDRESS ||
-       Ld->getAddressSpace() == AMDGPUASI.CONSTANT_ADDRESS_32BIT) &&
-    static_cast<const SITargetLowering *>(getTargetLowering())->isMemOpUniform(N)) ||
+    ((((Ld->getAddressSpace() == AMDGPUASI.CONSTANT_ADDRESS) || (Ld->getAddressSpace() == AMDGPUASI.CONSTANT_ADDRESS_32BIT)) && !N->isDivergent()) ||
     (Subtarget->getScalarizeGlobalBehavior() && Ld->getAddressSpace() == AMDGPUASI.GLOBAL_ADDRESS &&
-    !Ld->isVolatile() &&
-    static_cast<const SITargetLowering *>(getTargetLowering())->isMemOpUniform(N) &&
+     !Ld->isVolatile() && !N->isDivergent() &&
     static_cast<const SITargetLowering *>(getTargetLowering())->isMemOpHasNoClobberedMemOperand(N)));
 }]>;
 
Index: llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
+++ llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
@@ -382,6 +382,9 @@
 /// not the encoded offset.
 bool isLegalSMRDImmOffset(const MCSubtargetInfo &ST, int64_t ByteOffset);
 
+/// \returns true if the intrinsic is divergent
+bool isIntrinsicSourceOfDivergence(unsigned IntrID);
+
 } // end namespace AMDGPU
 } // end namespace llvm
 
Index: llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
+++ llvm/trunk/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
@@ -8,6 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUBaseInfo.h"
+#include "AMDGPUTargetTransformInfo.h"
 #include "AMDGPU.h"
 #include "SIDefines.h"
 #include "llvm/ADT/StringRef.h"
@@ -938,5 +939,55 @@
 AMDGPUAS getAMDGPUAS(const Module &M) {
   return getAMDGPUAS(Triple(M.getTargetTriple()));
 }
+
+bool isIntrinsicSourceOfDivergence(unsigned IntrID) {
+  switch (IntrID) {
+  case Intrinsic::amdgcn_workitem_id_x:
+  case Intrinsic::amdgcn_workitem_id_y:
+  case Intrinsic::amdgcn_workitem_id_z:
+  case Intrinsic::amdgcn_interp_mov:
+  case Intrinsic::amdgcn_interp_p1:
+  case Intrinsic::amdgcn_interp_p2:
+  case Intrinsic::amdgcn_mbcnt_hi:
+  case Intrinsic::amdgcn_mbcnt_lo:
+  case Intrinsic::r600_read_tidig_x:
+  case Intrinsic::r600_read_tidig_y:
+  case Intrinsic::r600_read_tidig_z:
+  case Intrinsic::amdgcn_atomic_inc:
+  case Intrinsic::amdgcn_atomic_dec:
+  case Intrinsic::amdgcn_ds_fadd:
+  case Intrinsic::amdgcn_ds_fmin:
+  case Intrinsic::amdgcn_ds_fmax:
+  case Intrinsic::amdgcn_image_atomic_swap:
+  case Intrinsic::amdgcn_image_atomic_add:
+  case Intrinsic::amdgcn_image_atomic_sub:
+  case Intrinsic::amdgcn_image_atomic_smin:
+  case Intrinsic::amdgcn_image_atomic_umin:
+  case Intrinsic::amdgcn_image_atomic_smax:
+  case Intrinsic::amdgcn_image_atomic_umax:
+  case Intrinsic::amdgcn_image_atomic_and:
+  case Intrinsic::amdgcn_image_atomic_or:
+  case Intrinsic::amdgcn_image_atomic_xor:
+  case Intrinsic::amdgcn_image_atomic_inc:
+  case Intrinsic::amdgcn_image_atomic_dec:
+  case Intrinsic::amdgcn_image_atomic_cmpswap:
+  case Intrinsic::amdgcn_buffer_atomic_swap:
+  case Intrinsic::amdgcn_buffer_atomic_add:
+  case Intrinsic::amdgcn_buffer_atomic_sub:
+  case Intrinsic::amdgcn_buffer_atomic_smin:
+  case Intrinsic::amdgcn_buffer_atomic_umin:
+  case Intrinsic::amdgcn_buffer_atomic_smax:
+  case Intrinsic::amdgcn_buffer_atomic_umax:
+  case Intrinsic::amdgcn_buffer_atomic_and:
+  case Intrinsic::amdgcn_buffer_atomic_or:
+  case Intrinsic::amdgcn_buffer_atomic_xor:
+  case Intrinsic::amdgcn_buffer_atomic_cmpswap:
+  case Intrinsic::amdgcn_ps_live:
+  case Intrinsic::amdgcn_ds_swizzle:
+    return true;
+  default:
+    return false;
+  }
+}
 } // namespace AMDGPU
 } // namespace llvm
Index: llvm/trunk/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
@@ -2,7 +2,9 @@
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-ipra=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
 
 ; GCN-LABEL: {{^}}use_dispatch_ptr:
-; GCN: s_load_dword s{{[0-9]+}}, s[6:7], 0x0
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s6
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s7
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
 define void @use_dispatch_ptr() #1 {
   %dispatch_ptr = call noalias i8 addrspace(4)* @llvm.amdgcn.dispatch.ptr() #0
   %header_ptr = bitcast i8 addrspace(4)* %dispatch_ptr to i32 addrspace(4)*
@@ -19,7 +21,9 @@
 }
 
 ; GCN-LABEL: {{^}}use_queue_ptr:
-; GCN: s_load_dword s{{[0-9]+}}, s[6:7], 0x0
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s6
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s7
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
 define void @use_queue_ptr() #1 {
   %queue_ptr = call noalias i8 addrspace(4)* @llvm.amdgcn.queue.ptr() #0
   %header_ptr = bitcast i8 addrspace(4)* %queue_ptr to i32 addrspace(4)*
@@ -37,11 +41,12 @@
 }
 
 ; GCN-LABEL: {{^}}use_queue_ptr_addrspacecast:
-; CIVI: s_load_dword [[APERTURE_LOAD:s[0-9]+]], s[6:7], 0x10
+; CIVI: flat_load_dword v[[HI:[0-9]+]], v[0:1]
 ; GFX9: s_getreg_b32 [[APERTURE_LOAD:s[0-9]+]]
-
-; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], [[APERTURE_LOAD]]
-; GCN: {{flat|global}}_store_dword v{{\[[0-9]+}}:[[HI]]{{\]}}
+; CIVI: v_mov_b32_e32 v[[LO:[0-9]+]], 16
+; GFX9: v_mov_b32_e32 v[[HI:[0-9]+]], [[APERTURE_LOAD]]
+; GFX9: {{flat|global}}_store_dword v{{\[[0-9]+}}:[[HI]]{{\]}}
+; CIVI: {{flat|global}}_store_dword v{{\[}}[[LO]]:[[HI]]{{\]}}
 define void @use_queue_ptr_addrspacecast() #1 {
   %asc = addrspacecast i32 addrspace(3)* inttoptr (i32 16 to i32 addrspace(3)*) to i32*
   store volatile i32 0, i32* %asc
@@ -60,7 +65,9 @@
 }
 
 ; GCN-LABEL: {{^}}use_kernarg_segment_ptr:
-; GCN: s_load_dword s{{[0-9]+}}, s[6:7], 0x0
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s6
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s7
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
 define void @use_kernarg_segment_ptr() #1 {
   %kernarg_segment_ptr = call noalias i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr() #0
   %header_ptr = bitcast i8 addrspace(4)* %kernarg_segment_ptr to i32 addrspace(4)*
@@ -424,9 +431,15 @@
 
 ; GCN-LABEL: {{^}}use_every_sgpr_input:
 ; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s5 offset:4
-; GCN: s_load_dword s{{[0-9]+}}, s[6:7], 0x0
-; GCN: s_load_dword s{{[0-9]+}}, s[8:9], 0x0
-; GCN: s_load_dword s{{[0-9]+}}, s[10:11], 0x0
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s6
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s7
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s8
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s9
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s10
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s11
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
 ; GCN: ; use s[12:13]
 ; GCN: ; use s14
 ; GCN: ; use s15
@@ -557,12 +570,23 @@
 ; GCN-DAG: s_mov_b32 s6, s14
 ; GCN-DAG: s_mov_b32 s7, s15
 ; GCN-DAG: s_mov_b32 s8, s16
+
+; GCN-DAG: s_mov_b64 s{{\[}}[[LO_X:[0-9]+]]{{\:}}[[HI_X:[0-9]+]]{{\]}}, s[6:7]
+; GCN-DAG: s_mov_b64 s{{\[}}[[LO_Y:[0-9]+]]{{\:}}[[HI_Y:[0-9]+]]{{\]}}, s[8:9]
+; GCN-DAG: s_mov_b64 s{{\[}}[[LO_Z:[0-9]+]]{{\:}}[[HI_Z:[0-9]+]]{{\]}}, s[10:11]
+
 ; GCN: s_swappc_b64
 
 ; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s5 offset:4
-; GCN: s_load_dword s{{[0-9]+}},
-; GCN: s_load_dword s{{[0-9]+}},
-; GCN: s_load_dword s{{[0-9]+}},
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s[[LO_X]]
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s[[HI_X]]
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s[[LO_Y]]
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s[[HI_Y]]
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
+; GCN: v_mov_b32_e32 v[[LO:[0-9]+]], s[[LO_Z]]
+; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], s[[HI_Z]]
+; GCN: {{flat|global}}_load_dword v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
 ; GCN: ; use
 ; GCN: ; use [[SAVE_X]]
 ; GCN: ; use [[SAVE_Y]]
Index: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll
@@ -34,7 +34,13 @@
 
 ; GCN-LABEL: {{^}}func_implicitarg_ptr:
 ; GCN: s_waitcnt
-; GCN-NEXT: s_load_dword s{{[0-9]+}}, s[6:7], 0x0{{$}}
+; MESA: s_mov_b64 s[8:9], s[6:7]
+; MESA: s_mov_b32 s11, 0xf000
+; MESA: s_mov_b32 s10, -1
+; MESA: buffer_load_dword v0, off, s[8:11], 0
+; HSA: v_mov_b32_e32 v0, s6
+; HSA: v_mov_b32_e32 v1, s7
+; HSA: flat_load_dword v0, v[0:1]
 ; GCN-NEXT: s_waitcnt
 ; GCN-NEXT: s_setpc_b64
 define void @func_implicitarg_ptr() #1 {
@@ -83,8 +89,21 @@
 
 ; GCN-LABEL: {{^}}func_kernarg_implicitarg_ptr:
 ; GCN: s_waitcnt
-; GCN: s_load_dword s{{[0-9]+}}, s[6:7], 0x0{{$}}
-; GCN: s_load_dword s{{[0-9]+}}, s[8:9], 0x0{{$}}
+; MESA: s_mov_b64 s[12:13], s[6:7]
+; MESA: s_mov_b32 s15, 0xf000
+; MESA: s_mov_b32 s14, -1
+; MESA: buffer_load_dword v0, off, s[12:15], 0
+; HSA: v_mov_b32_e32 v0, s6
+; HSA: v_mov_b32_e32 v1, s7
+; HSA: flat_load_dword v0, v[0:1]
+; MESA: s_mov_b32 s10, s14
+; MESA: s_mov_b32 s11, s15
+; MESA: buffer_load_dword v0, off, s[8:11], 0
+; HSA: v_mov_b32_e32 v0, s8
+; HSA: v_mov_b32_e32 v1, s9
+; HSA: flat_load_dword v0, v[0:1]
+
+; GCN: s_waitcnt vmcnt(0)
 define void @func_kernarg_implicitarg_ptr() #1 {
   %kernarg.segment.ptr = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
   %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()