Index: lib/Target/AMDGPU/AMDGPU.h
===================================================================
--- lib/Target/AMDGPU/AMDGPU.h
+++ lib/Target/AMDGPU/AMDGPU.h
@@ -51,6 +51,7 @@
 FunctionPass *createSIDebuggerInsertNopsPass();
 FunctionPass *createSIInsertWaitcntsPass();
 FunctionPass *createSIFixWWMLivenessPass();
+FunctionPass *createSIFormMemoryClausesPass();
 FunctionPass *createAMDGPUSimplifyLibCallsPass(const TargetOptions &);
 FunctionPass *createAMDGPUUseNativeCallsPass();
 FunctionPass *createAMDGPUCodeGenPreparePass();
@@ -177,6 +178,9 @@
 void initializeSIInsertWaitcntsPass(PassRegistry&);
 extern char &SIInsertWaitcntsID;
 
+void initializeSIFormMemoryClausesPass(PassRegistry&);
+extern char &SIFormMemoryClausesID;
+
 void initializeAMDGPUUnifyDivergentExitNodesPass(PassRegistry&);
 extern char &AMDGPUUnifyDivergentExitNodesID;
 
Index: lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -171,6 +171,7 @@
   initializeSIDebuggerInsertNopsPass(*PR);
   initializeSIOptimizeExecMaskingPass(*PR);
   initializeSIFixWWMLivenessPass(*PR);
+  initializeSIFormMemoryClausesPass(*PR);
   initializeAMDGPUUnifyDivergentExitNodesPass(*PR);
   initializeAMDGPUAAWrapperPassPass(*PR);
   initializeAMDGPUUseNativeCallsPass(*PR);
@@ -842,6 +843,8 @@
 void GCNPassConfig::addOptimizedRegAlloc(FunctionPass *RegAllocPass) {
   insertPass(&MachineSchedulerID, &SIOptimizeExecMaskingPreRAID);
 
+  insertPass(&SIOptimizeExecMaskingPreRAID, &SIFormMemoryClausesID);
+
   // This must be run immediately after phi elimination and before
   // TwoAddressInstructions, otherwise the processing of the tied operand of
   // SI_ELSE will introduce a copy of the tied operand source after the else.
Index: lib/Target/AMDGPU/CMakeLists.txt
===================================================================
--- lib/Target/AMDGPU/CMakeLists.txt
+++ lib/Target/AMDGPU/CMakeLists.txt
@@ -85,6 +85,7 @@
   SIFixVGPRCopies.cpp
   SIFixWWMLiveness.cpp
   SIFoldOperands.cpp
+  SIFormMemoryClauses.cpp
   SIFrameLowering.cpp
   SIInsertSkips.cpp
   SIInsertWaitcnts.cpp
Index: lib/Target/AMDGPU/SIFormMemoryClauses.cpp
===================================================================
--- /dev/null
+++ lib/Target/AMDGPU/SIFormMemoryClauses.cpp
@@ -0,0 +1,398 @@
+//===-- SIFormMemoryClauses.cpp -------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+/// \file
+/// This pass creates bundles of SMEM and VMEM instructions forming memory
+/// clauses if XNACK is enabled. Def operands of clauses are marked as early
+/// clobber to make sure we will not override any source within a clause.
+///
+//===----------------------------------------------------------------------===//
+
+#include "AMDGPU.h"
+#include "AMDGPUSubtarget.h"
+#include "GCNRegPressure.h"
+#include "SIInstrInfo.h"
+#include "SIMachineFunctionInfo.h"
+#include "SIRegisterInfo.h"
+#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/CodeGen/LiveIntervals.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+
+using namespace llvm;
+
+#define DEBUG_TYPE "si-form-memory-clauses"
+
+// Clauses longer then 15 instructions would overflow one of the counters
+// and stall. They can stall even earlier if there are outstanding counters.
+static cl::opt<unsigned>
+MaxClause("amdgpu-max-memory-clause", cl::Hidden, cl::init(15),
+          cl::desc("Maximum length of a memory clause, instructions"));
+
+namespace {
+
+class SIFormMemoryClauses : public MachineFunctionPass {
+  typedef DenseMap<unsigned, std::pair<unsigned, LaneBitmask>> RegUse;
+
+public:
+  static char ID;
+
+public:
+  SIFormMemoryClauses() : MachineFunctionPass(ID) {
+    initializeSIFormMemoryClausesPass(*PassRegistry::getPassRegistry());
+  }
+
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  StringRef getPassName() const override {
+    return "SI Form memory clauses";
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<LiveIntervals>();
+    AU.setPreservesAll();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+
+private:
+  template <typename Callable>
+  void forAllLanes(unsigned Reg, LaneBitmask LaneMask, Callable Func) const;
+
+  bool canBundle(const MachineInstr &MI, RegUse &Defs, RegUse &Uses) const;
+  bool checkPressure(const MachineInstr &MI, GCNDownwardRPTracker &RPT);
+  void collectRegUses(const MachineInstr &MI, RegUse &Defs, RegUse &Uses) const;
+  bool processRegUses(const MachineInstr &MI, RegUse &Defs, RegUse &Uses,
+                      GCNDownwardRPTracker &RPT);
+
+  const SISubtarget *ST;
+  const SIRegisterInfo *TRI;
+  const MachineRegisterInfo *MRI;
+  SIMachineFunctionInfo *MFI;
+
+  unsigned LastRecordedOccupancy;
+  unsigned MaxVGPRs;
+  unsigned MaxSGPRs;
+};
+
+} // End anonymous namespace.
+
+INITIALIZE_PASS_BEGIN(SIFormMemoryClauses, DEBUG_TYPE,
+                      "SI Form memory clauses", false, false)
+INITIALIZE_PASS_DEPENDENCY(LiveIntervals)
+INITIALIZE_PASS_END(SIFormMemoryClauses, DEBUG_TYPE,
+                    "SI Form memory clauses", false, false)
+
+
+char SIFormMemoryClauses::ID = 0;
+
+char &llvm::SIFormMemoryClausesID = SIFormMemoryClauses::ID;
+
+FunctionPass *llvm::createSIFormMemoryClausesPass() {
+  return new SIFormMemoryClauses();
+}
+
+static bool isVMEMClauseInst(const MachineInstr &MI) {
+  return SIInstrInfo::isFLAT(MI) || SIInstrInfo::isVMEM(MI);
+}
+
+static bool isSMEMClauseInst(const MachineInstr &MI) {
+  return SIInstrInfo::isSMRD(MI);
+}
+
+// There no sense to create store clauses, they do not define anything,
+// thus there is nothing to set early-clobber.
+static bool isValidClauseInst(const MachineInstr &MI, bool IsVMEMClause) {
+  if (MI.isDebugValue() || MI.isBundled())
+    return false;
+  if (!MI.mayLoad() || MI.mayStore())
+    return false;
+  if (AMDGPU::getAtomicNoRetOp(MI.getOpcode()) != -1 ||
+      AMDGPU::getAtomicRetOp(MI.getOpcode()) != -1)
+    return false;
+  if (IsVMEMClause && !isVMEMClauseInst(MI))
+    return false;
+  if (!IsVMEMClause && !isSMEMClauseInst(MI))
+    return false;
+  return true;
+}
+
+static unsigned getMopState(const MachineOperand &MO) {
+  unsigned S = 0;
+  if (MO.isImplicit())
+    S |= RegState::Implicit;
+  if (MO.isDead())
+    S |= RegState::Dead;
+  if (MO.isUndef())
+    S |= RegState::Undef;
+  if (MO.isKill())
+    S |= RegState::Kill;
+  if (MO.isEarlyClobber())
+    S |= RegState::EarlyClobber;
+  if (TargetRegisterInfo::isPhysicalRegister(MO.getReg()) && MO.isRenamable())
+    S |= RegState::Renamable;
+  return S;
+}
+
+template <typename Callable>
+void SIFormMemoryClauses::forAllLanes(unsigned Reg, LaneBitmask LaneMask,
+                                      Callable Func) const {
+  if (LaneMask.all() || TargetRegisterInfo::isPhysicalRegister(Reg) ||
+      LaneMask == MRI->getMaxLaneMaskForVReg(Reg)) {
+    Func(0);
+    return;
+  }
+
+  const TargetRegisterClass *RC = MRI->getRegClass(Reg);
+  unsigned E = TRI->getNumSubRegIndices();
+  SmallVector<unsigned, AMDGPU::NUM_TARGET_SUBREGS> CoveringSubregs;
+  for (unsigned Idx = 1; Idx < E; ++Idx) {
+    // Is this index even compatible with the given class?
+    if (TRI->getSubClassWithSubReg(RC, Idx) != RC)
+      continue;
+    LaneBitmask SubRegMask = TRI->getSubRegIndexLaneMask(Idx);
+    // Early exit if we found a perfect match.
+    if (SubRegMask == LaneMask) {
+      Func(Idx);
+      return;
+    }
+
+    if ((SubRegMask & ~LaneMask).any() || (SubRegMask & LaneMask).none())
+      continue;
+
+    CoveringSubregs.push_back(Idx);
+  }
+
+  llvm::sort(CoveringSubregs.begin(), CoveringSubregs.end(),
+             [this](unsigned A, unsigned B) {
+               LaneBitmask MaskA = TRI->getSubRegIndexLaneMask(A);
+               LaneBitmask MaskB = TRI->getSubRegIndexLaneMask(B);
+               unsigned NA = MaskA.getNumLanes();
+               unsigned NB = MaskB.getNumLanes();
+               if (NA != NB)
+                 return NA > NB;
+               return MaskA.getHighestLane() > MaskB.getHighestLane();
+             });
+
+  for (unsigned Idx : CoveringSubregs) {
+    LaneBitmask SubRegMask = TRI->getSubRegIndexLaneMask(Idx);
+    if ((SubRegMask & ~LaneMask).any() || (SubRegMask & LaneMask).none())
+      continue;
+
+    Func(Idx);
+    LaneMask &= ~SubRegMask;
+    if (LaneMask.none())
+      return;
+  }
+
+  llvm_unreachable("Failed to find all subregs to cover lane mask");
+}
+
+// Returns false if there is a use of a def already in the map.
+// In this case we must break the clause.
+bool SIFormMemoryClauses::canBundle(const MachineInstr &MI,
+                                    RegUse &Defs, RegUse &Uses) const {
+  // Check interference with defs.
+  for (const MachineOperand &MO : MI.operands()) {
+    // TODO: Prologue/Epilogue Insertion pass does not process bundled
+    //       instructions.
+    if (MO.isFI())
+      return false;
+
+    if (!MO.isReg())
+      continue;
+
+    unsigned Reg = MO.getReg();
+
+    // If it is tied we will need to write same register as we read.
+    if (MO.isTied())
+      return false;
+
+    RegUse &Map = MO.isDef() ? Uses : Defs;
+    auto Conflict = Map.find(Reg);
+    if (Conflict == Map.end())
+      continue;
+
+    if (TargetRegisterInfo::isPhysicalRegister(Reg))
+      return false;
+
+    LaneBitmask Mask = TRI->getSubRegIndexLaneMask(MO.getSubReg());
+    if ((Conflict->second.second & Mask).any())
+      return false;
+  }
+
+  return true;
+}
+
+// Since all defs in the clause are early clobber we can run out of registers.
+// Function returns false if pressure would hit the limit if instruction is
+// bundled into a memory clause.
+bool SIFormMemoryClauses::checkPressure(const MachineInstr &MI,
+                                        GCNDownwardRPTracker &RPT) {
+  // NB: skip advanceBeforeNext() call. Since all defs will be marked
+  // early-clobber they will all stay alive at least to the end of the
+  // clause. Therefor we should not decrease pressure even if load
+  // pointer becomes dead and could otherwise be reused for destination.
+  RPT.advanceToNext();
+  GCNRegPressure MaxPressure = RPT.moveMaxPressure();
+  unsigned Occupancy = MaxPressure.getOccupancy(*ST);
+  if (Occupancy >= MFI->getMinAllowedOccupancy() &&
+      MaxPressure.getVGPRNum() <= MaxVGPRs &&
+      MaxPressure.getSGPRNum() <= MaxSGPRs) {
+    LastRecordedOccupancy = Occupancy;
+    return true;
+  }
+  return false;
+}
+
+// Collect register defs and uses along with their lane masks and states.
+void SIFormMemoryClauses::collectRegUses(const MachineInstr &MI,
+                                         RegUse &Defs, RegUse &Uses) const {
+  for (const MachineOperand &MO : MI.operands()) {
+    if (!MO.isReg())
+      continue;
+    unsigned Reg = MO.getReg();
+    if (!Reg)
+      continue;
+
+    LaneBitmask Mask = TargetRegisterInfo::isVirtualRegister(Reg) ?
+                         TRI->getSubRegIndexLaneMask(MO.getSubReg()) :
+                         LaneBitmask::getAll();
+    RegUse &Map = MO.isDef() ? Defs : Uses;
+
+    auto Loc = Map.find(Reg);
+    unsigned State = getMopState(MO);
+    if (Loc == Map.end()) {
+      Map[Reg] = std::make_pair(State, Mask);
+    } else {
+      Loc->second.first |= State;
+      Loc->second.second |= Mask;
+    }
+  }
+}
+
+// Check register def/use conflicts, occupancy limits and collect def/use maps.
+// Return true if instruction can be bundled with previous. It it cannot
+// def/use maps are not updated.
+bool SIFormMemoryClauses::processRegUses(const MachineInstr &MI,
+                                         RegUse &Defs, RegUse &Uses,
+                                         GCNDownwardRPTracker &RPT) {
+  if (!canBundle(MI, Defs, Uses))
+    return false;
+
+  if (!checkPressure(MI, RPT))
+    return false;
+
+  collectRegUses(MI, Defs, Uses);
+  return true;
+}
+
+bool SIFormMemoryClauses::runOnMachineFunction(MachineFunction &MF) {
+  if (skipFunction(MF.getFunction()))
+    return false;
+
+  ST = &MF.getSubtarget<SISubtarget>();
+  if (!ST->isXNACKEnabled())
+    return false;
+
+  const SIInstrInfo *TII = ST->getInstrInfo();
+  TRI = ST->getRegisterInfo();
+  MRI = &MF.getRegInfo();
+  MFI = MF.getInfo<SIMachineFunctionInfo>();
+  LiveIntervals *LIS = &getAnalysis<LiveIntervals>();
+  SlotIndexes *Ind = LIS->getSlotIndexes();
+  bool Changed = false;
+
+  MaxVGPRs = TRI->getAllocatableSet(MF, &AMDGPU::VGPR_32RegClass).count();
+  MaxSGPRs = TRI->getAllocatableSet(MF, &AMDGPU::SGPR_32RegClass).count();
+
+  for (MachineBasicBlock &MBB : MF) {
+    MachineBasicBlock::instr_iterator Next;
+    for (auto I = MBB.instr_begin(), E = MBB.instr_end(); I != E; I = Next) {
+      MachineInstr &MI = *I;
+      Next = std::next(I);
+
+      bool IsVMEM = isVMEMClauseInst(MI);
+
+      if (!isValidClauseInst(MI, IsVMEM))
+        continue;
+
+      RegUse Defs, Uses;
+      GCNDownwardRPTracker RPT(*LIS);
+      RPT.reset(MI);
+
+      if (!processRegUses(MI, Defs, Uses, RPT))
+        continue;
+
+      unsigned Length = 1;
+      for ( ; Next != E && Length < MaxClause; ++Next) {
+        if (!isValidClauseInst(*Next, IsVMEM))
+          break;
+
+        // A load from pointer which was loaded inside the same bundle is an
+        // impossible clause because we will need to write and read the same
+        // register inside. In this case processRegUses will return false.
+        if (!processRegUses(*Next, Defs, Uses, RPT))
+          break;
+
+        ++Length;
+      }
+      if (Length < 2)
+        continue;
+
+      Changed = true;
+      MFI->limitOccupancy(LastRecordedOccupancy);
+
+      auto B = BuildMI(MBB, I, DebugLoc(), TII->get(TargetOpcode::BUNDLE));
+      Ind->insertMachineInstrInMaps(*B);
+
+      for (auto BI = I; BI != Next; ++BI) {
+        BI->bundleWithPred();
+        Ind->removeSingleMachineInstrFromMaps(*BI);
+
+        for (MachineOperand &MO : BI->defs())
+          if (MO.readsReg())
+            MO.setIsInternalRead(true);
+      }
+
+      for (auto &&R : Defs) {
+        forAllLanes(R.first, R.second.second, [&R, &B](unsigned SubReg) {
+          unsigned S = R.second.first | RegState::EarlyClobber;
+          if (!SubReg)
+            S &= ~(RegState::Undef | RegState::Dead);
+          B.addDef(R.first, S, SubReg);
+        });
+      }
+
+      for (auto &&R : Uses) {
+        forAllLanes(R.first, R.second.second, [&R, &B](unsigned SubReg) {
+          B.addUse(R.first, R.second.first & ~RegState::Kill, SubReg);
+        });
+      }
+
+      for (auto &&R : Defs) {
+        unsigned Reg = R.first;
+        Uses.erase(Reg);
+        if (TargetRegisterInfo::isPhysicalRegister(Reg))
+          continue;
+        LIS->removeInterval(Reg);
+        LIS->createAndComputeVirtRegInterval(Reg);
+      }
+
+      for (auto &&R : Uses) {
+        unsigned Reg = R.first;
+        if (TargetRegisterInfo::isPhysicalRegister(Reg))
+          continue;
+        LIS->removeInterval(Reg);
+        LIS->createAndComputeVirtRegInterval(Reg);
+      }
+    }
+  }
+
+  return Changed;
+}
Index: lib/Target/AMDGPU/SIInstrInfo.cpp
===================================================================
--- lib/Target/AMDGPU/SIInstrInfo.cpp
+++ lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -1266,6 +1266,22 @@
     MI.setDesc(get(AMDGPU::S_MOV_B64));
     break;
   }
+  case TargetOpcode::BUNDLE: {
+    if (!MI.mayLoad())
+      return false;
+
+    // If it is a load it must be a memory clause
+    for (MachineBasicBlock::instr_iterator I = MI.getIterator();
+         I->isBundledWithSucc(); ++I) {
+      I->unbundleFromSucc();
+      for (MachineOperand &MO : I->operands())
+        if (MO.isReg())
+          MO.setIsInternalRead(false);
+    }
+
+    MI.eraseFromParent();
+    break;
+  }
   }
   return true;
 }
Index: test/CodeGen/AMDGPU/memory_clause.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/memory_clause.ll
@@ -0,0 +1,166 @@
+; RUN: llc -march=amdgcn -mcpu=gfx902 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+; GCN-LABEL: {{^}}vector_clause:
+; GCN:      global_load_dwordx4
+; GCN-NEXT: global_load_dwordx4
+; GCN-NEXT: global_load_dwordx4
+; GCN-NEXT: global_load_dwordx4
+; GCN-NEXT: s_nop
+define amdgpu_kernel void @vector_clause(<4 x i32> addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture %arg1) {
+bb:
+  %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %tmp2 = zext i32 %tmp to i64
+  %tmp3 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp2
+  %tmp4 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp3, align 16
+  %tmp5 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp2
+  %tmp6 = add nuw nsw i64 %tmp2, 1
+  %tmp7 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp6
+  %tmp8 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp7, align 16
+  %tmp9 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp6
+  %tmp10 = add nuw nsw i64 %tmp2, 2
+  %tmp11 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp10
+  %tmp12 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp11, align 16
+  %tmp13 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp10
+  %tmp14 = add nuw nsw i64 %tmp2, 3
+  %tmp15 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp14
+  %tmp16 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp15, align 16
+  %tmp17 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp14
+  store <4 x i32> %tmp4, <4 x i32> addrspace(1)* %tmp5, align 16
+  store <4 x i32> %tmp8, <4 x i32> addrspace(1)* %tmp9, align 16
+  store <4 x i32> %tmp12, <4 x i32> addrspace(1)* %tmp13, align 16
+  store <4 x i32> %tmp16, <4 x i32> addrspace(1)* %tmp17, align 16
+  ret void
+}
+
+; GCN-LABEL: {{^}}scalar_clause:
+; GCN:      s_load_dwordx2
+; GCN-NEXT: s_load_dwordx2
+; GCN-NEXT: s_nop
+; GCN-NEXT: s_waitcnt lgkmcnt(0)
+; GCN-NEXT: s_load_dwordx4
+; GCN-NEXT: s_load_dwordx4
+; GCN-NEXT: s_load_dwordx4
+; GCN-NEXT: s_load_dwordx4
+define amdgpu_kernel void @scalar_clause(<4 x i32> addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture %arg1) {
+bb:
+  %tmp = load <4 x i32>, <4 x i32> addrspace(1)* %arg, align 16
+  %tmp2 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 1
+  %tmp3 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp2, align 16
+  %tmp4 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 1
+  %tmp5 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 2
+  %tmp6 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp5, align 16
+  %tmp7 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 2
+  %tmp8 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 3
+  %tmp9 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp8, align 16
+  %tmp10 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 3
+  store <4 x i32> %tmp, <4 x i32> addrspace(1)* %arg1, align 16
+  store <4 x i32> %tmp3, <4 x i32> addrspace(1)* %tmp4, align 16
+  store <4 x i32> %tmp6, <4 x i32> addrspace(1)* %tmp7, align 16
+  store <4 x i32> %tmp9, <4 x i32> addrspace(1)* %tmp10, align 16
+  ret void
+}
+
+; GCN-LABEL: {{^}}mubuf_clause:
+; GCN:      buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: buffer_load_dword
+; GCN-NEXT: s_nop
+; GCN-NEXT: buffer_load_dword
+define void @mubuf_clause(<4 x i32> addrspace(5)* noalias nocapture readonly %arg, <4 x i32> addrspace(5)* noalias nocapture %arg1) {
+bb:
+  %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %tmp2 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg, i32 %tmp
+  %tmp3 = load <4 x i32>, <4 x i32> addrspace(5)* %tmp2, align 16
+  %tmp4 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg1, i32 %tmp
+  %tmp5 = add nuw nsw i32 %tmp, 1
+  %tmp6 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg, i32 %tmp5
+  %tmp7 = load <4 x i32>, <4 x i32> addrspace(5)* %tmp6, align 16
+  %tmp8 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg1, i32 %tmp5
+  %tmp9 = add nuw nsw i32 %tmp, 2
+  %tmp10 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg, i32 %tmp9
+  %tmp11 = load <4 x i32>, <4 x i32> addrspace(5)* %tmp10, align 16
+  %tmp12 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg1, i32 %tmp9
+  %tmp13 = add nuw nsw i32 %tmp, 3
+  %tmp14 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg, i32 %tmp13
+  %tmp15 = load <4 x i32>, <4 x i32> addrspace(5)* %tmp14, align 16
+  %tmp16 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(5)* %arg1, i32 %tmp13
+  store <4 x i32> %tmp3, <4 x i32> addrspace(5)* %tmp4, align 16
+  store <4 x i32> %tmp7, <4 x i32> addrspace(5)* %tmp8, align 16
+  store <4 x i32> %tmp11, <4 x i32> addrspace(5)* %tmp12, align 16
+  store <4 x i32> %tmp15, <4 x i32> addrspace(5)* %tmp16, align 16
+  ret void
+}
+
+; GCN-LABEL: {{^}}vector_clause_indirect:
+; GCN: global_load_dwordx2 [[ADDR:v\[[0-9:]+\]]], v[{{[0-9:]+}}], off
+; GCN-NEXT: s_nop
+; GCN-NEXT: s_waitcnt vmcnt(0)
+; GCN-NEXT: global_load_dwordx4 v[{{[0-9:]+}}], [[ADDR]], off
+; GCN-NEXT: global_load_dwordx4 v[{{[0-9:]+}}], [[ADDR]], off offset:16
+define amdgpu_kernel void @vector_clause_indirect(i64 addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture readnone %arg1, <4 x i32> addrspace(1)* noalias nocapture %arg2) {
+bb:
+  %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %tmp3 = zext i32 %tmp to i64
+  %tmp4 = getelementptr inbounds i64, i64 addrspace(1)* %arg, i64 %tmp3
+  %tmp5 = bitcast i64 addrspace(1)* %tmp4 to <4 x i32> addrspace(1)* addrspace(1)*
+  %tmp6 = load <4 x i32> addrspace(1)*, <4 x i32> addrspace(1)* addrspace(1)* %tmp5, align 8
+  %tmp7 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp6, align 16
+  %tmp8 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %tmp6, i64 1
+  %tmp9 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp8, align 16
+  store <4 x i32> %tmp7, <4 x i32> addrspace(1)* %arg2, align 16
+  %tmp10 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg2, i64 1
+  store <4 x i32> %tmp9, <4 x i32> addrspace(1)* %tmp10, align 16
+  ret void
+}
+
+; GCN-LABEL: {{^}}load_global_d16_hi:
+; GCN:      global_load_short_d16_hi v
+; GCN-NEXT: s_nop
+; GCN-NEXT: global_load_short_d16_hi v
+define void @load_global_d16_hi(i16 addrspace(1)* %in, i16 %reg, <2 x i16> addrspace(1)* %out) {
+entry:
+  %gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 32
+  %load1 = load i16, i16 addrspace(1)* %in
+  %load2 = load i16, i16 addrspace(1)* %gep
+  %build0 = insertelement <2 x i16> undef, i16 %reg, i32 0
+  %build1 = insertelement <2 x i16> %build0, i16 %load1, i32 1
+  store <2 x i16> %build1, <2 x i16> addrspace(1)* %out
+  %build2 = insertelement <2 x i16> undef, i16 %reg, i32 0
+  %build3 = insertelement <2 x i16> %build2, i16 %load2, i32 1
+  %gep2 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 32
+  store <2 x i16> %build3, <2 x i16> addrspace(1)* %gep2
+  ret void
+}
+
+; GCN-LABEL: {{^}}load_global_d16_lo:
+; GCN:      global_load_short_d16 v
+; GCN-NEXT: s_nop
+; GCN-NEXT: global_load_short_d16 v
+define void @load_global_d16_lo(i16 addrspace(1)* %in, i32 %reg, <2 x i16> addrspace(1)* %out) {
+entry:
+  %gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 32
+  %reg.bc1 = bitcast i32 %reg to <2 x i16>
+  %reg.bc2 = bitcast i32 %reg to <2 x i16>
+  %load1 = load i16, i16 addrspace(1)* %in
+  %load2 = load i16, i16 addrspace(1)* %gep
+  %build1 = insertelement <2 x i16> %reg.bc1, i16 %load1, i32 0
+  %build2 = insertelement <2 x i16> %reg.bc2, i16 %load2, i32 0
+  %gep2 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 32
+  store <2 x i16> %build1, <2 x i16> addrspace(1)* %out
+  store <2 x i16> %build2, <2 x i16> addrspace(1)* %gep2
+  ret void
+}
+
+declare i32 @llvm.amdgcn.workitem.id.x()
Index: test/CodeGen/AMDGPU/memory_clause.mir
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/memory_clause.mir
@@ -0,0 +1,388 @@
+# RUN: llc -march=amdgcn -mcpu=gfx902 -verify-machineinstrs -run-pass=phi-node-elimination,si-form-memory-clauses %s -o - | FileCheck -check-prefix=GCN %s
+
+# GCN-LABEL: {{^}}name: vector_clause{{$}}
+# GCN:         early-clobber %2:vreg_128, early-clobber %4:vreg_128, early-clobber %1:vreg_128, early-clobber %3:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:    %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT:    %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+# GCN-NEXT:    %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+# GCN-NEXT:    %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+# GCN-NEXT:  }
+# GCN-NEXT:  GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+
+---
+name:            vector_clause
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vreg_128 }
+  - { id: 2, class: vreg_128 }
+  - { id: 3, class: vreg_128 }
+  - { id: 4, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+    %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+    %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+    %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %2, 16, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %3, 32, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %4, 48, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: subreg_full{{$}}
+# GCN:      early-clobber %1:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:   undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+# GCN-NEXT:   internal %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+# GCN-NEXT:   internal %1.sub2:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+# GCN-NEXT:   internal %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+
+---
+name:            subreg_full
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_128 }
+  - { id: 1, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+    %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+    %1.sub2:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+    %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: subreg_part{{$}}
+# GCN:      undef early-clobber %1.sub0_sub1:vreg_128, undef early-clobber %1.sub3:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:   undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+# GCN-NEXT:   internal %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+# GCN-NEXT:   internal %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+
+---
+name:            subreg_part
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_128 }
+  - { id: 1, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+    %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+    %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: dead{{$}}
+# GCN:      dead early-clobber %2:vreg_128, dead early-clobber %4:vreg_128, dead early-clobber %1:vreg_128, dead early-clobber %3:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:   dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+# GCN-NEXT:   dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+# GCN-NEXT:   dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name:            dead
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vreg_128 }
+  - { id: 2, class: vreg_128 }
+  - { id: 3, class: vreg_128 }
+  - { id: 4, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+    dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+    dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+    dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: subreg_dead{{$}}
+# GCN:      early-clobber %1:vreg_64 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:    %1.sub0:vreg_64 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+# GCN-NEXT:    dead %1.sub1:vreg_64 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: GLOBAL_STORE_DWORD %0, %1.sub0, 0, 0, 0, implicit $exec
+
+---
+name:            subreg_dead
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vreg_64 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    undef %1.sub0:vreg_64 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+    dead %1.sub1:vreg_64 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORD %0, %1.sub0, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: kill{{$}}
+# GCN:      early-clobber %2:vreg_128, early-clobber %3:vreg_128 = BUNDLE %0, %1, implicit $exec {
+# GCN-NEXT:   %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name:            kill
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vreg_64 }
+  - { id: 2, class: vreg_128 }
+  - { id: 3, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = IMPLICIT_DEF
+    %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+    %3:vreg_128 = GLOBAL_LOAD_DWORDX4 killed %1, 16, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %2, 0, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %3, 16, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: indirect{{$}}
+# GCN:      %1:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   early-clobber %2:vreg_128, early-clobber %3:vreg_128 = BUNDLE %1, implicit $exec {
+# GCN-NEXT:   %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 0, 0, 0, implicit $exec
+# GCN-NEXT:   %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name:            indirect
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vreg_64 }
+  - { id: 2, class: vreg_128 }
+  - { id: 3, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, 0, implicit $exec
+    %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 0, 0, 0, implicit $exec
+    %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %2, 0, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %3, 16, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: stack{{$}}
+# GCN:      %0:vreg_64 = IMPLICIT_DEF
+# GCN-NEXT: %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 0, 0, 0, implicit $exec
+# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 16, 0, 0, implicit $exec
+# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+
+---
+name:            stack
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vreg_128 }
+  - { id: 2, class: vreg_128 }
+stack:
+  - { id: 0, type: default, offset: 0, size: 64, alignment: 8 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 0, 0, 0, implicit $exec
+    %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 16, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+    GLOBAL_STORE_DWORDX4 %0, %2, 16, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: overflow_counter{{$}}
+# GCN:      dead early-clobber %7:vgpr_32, dead early-clobber %14:vgpr_32, dead early-clobber %2:vgpr_32, dead early-clobber %9:vgpr_32, dead early-clobber %4:vgpr_32, dead early-clobber %11:vgpr_32, dead early-clobber %6:vgpr_32, dead early-clobber %13:vgpr_32, dead early-clobber %1:vgpr_32, dead early-clobber %8:vgpr_32, dead early-clobber %15:vgpr_32, dead early-clobber %3:vgpr_32, dead early-clobber %10:vgpr_32, dead early-clobber %5:vgpr_32, dead early-clobber %12:vgpr_32 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:   dead %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   dead %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, 0, implicit $exec
+# GCN-NEXT:   dead %3:vgpr_32 = GLOBAL_LOAD_DWORD %0, 8, 0, 0, implicit $exec
+# GCN-NEXT:   dead %4:vgpr_32 = GLOBAL_LOAD_DWORD %0, 12, 0, 0, implicit $exec
+# GCN-NEXT:   dead %5:vgpr_32 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+# GCN-NEXT:   dead %6:vgpr_32 = GLOBAL_LOAD_DWORD %0, 20, 0, 0, implicit $exec
+# GCN-NEXT:   dead %7:vgpr_32 = GLOBAL_LOAD_DWORD %0, 24, 0, 0, implicit $exec
+# GCN-NEXT:   dead %8:vgpr_32 = GLOBAL_LOAD_DWORD %0, 28, 0, 0, implicit $exec
+# GCN-NEXT:   dead %9:vgpr_32 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+# GCN-NEXT:   dead %10:vgpr_32 = GLOBAL_LOAD_DWORD %0, 36, 0, 0, implicit $exec
+# GCN-NEXT:   dead %11:vgpr_32 = GLOBAL_LOAD_DWORD %0, 40, 0, 0, implicit $exec
+# GCN-NEXT:   dead %12:vgpr_32 = GLOBAL_LOAD_DWORD %0, 44, 0, 0, implicit $exec
+# GCN-NEXT:   dead %13:vgpr_32 = GLOBAL_LOAD_DWORD %0, 48, 0, 0, implicit $exec
+# GCN-NEXT:   dead %14:vgpr_32 = GLOBAL_LOAD_DWORD %0, 52, 0, 0, implicit $exec
+# GCN-NEXT:   dead %15:vgpr_32 = GLOBAL_LOAD_DWORD %0, 56, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: dead early-clobber %16:vgpr_32, dead early-clobber %17:vgpr_32 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:   dead %16:vgpr_32 = GLOBAL_LOAD_DWORD %0, 60, 0, 0, implicit $exec
+# GCN-NEXT:   dead %17:vgpr_32 = GLOBAL_LOAD_DWORD %0, 64, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name:            overflow_counter
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vgpr_32 }
+  - { id: 2, class: vgpr_32 }
+  - { id: 3, class: vgpr_32 }
+  - { id: 4, class: vgpr_32 }
+  - { id: 5, class: vgpr_32 }
+  - { id: 6, class: vgpr_32 }
+  - { id: 7, class: vgpr_32 }
+  - { id: 8, class: vgpr_32 }
+  - { id: 9, class: vgpr_32 }
+  - { id: 10, class: vgpr_32 }
+  - { id: 11, class: vgpr_32 }
+  - { id: 12, class: vgpr_32 }
+  - { id: 13, class: vgpr_32 }
+  - { id: 14, class: vgpr_32 }
+  - { id: 15, class: vgpr_32 }
+  - { id: 16, class: vgpr_32 }
+  - { id: 17, class: vgpr_32 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, 0, implicit $exec
+    %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, 0, implicit $exec
+    %3:vgpr_32 = GLOBAL_LOAD_DWORD %0, 8, 0, 0, implicit $exec
+    %4:vgpr_32 = GLOBAL_LOAD_DWORD %0, 12, 0, 0, implicit $exec
+    %5:vgpr_32 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+    %6:vgpr_32 = GLOBAL_LOAD_DWORD %0, 20, 0, 0, implicit $exec
+    %7:vgpr_32 = GLOBAL_LOAD_DWORD %0, 24, 0, 0, implicit $exec
+    %8:vgpr_32 = GLOBAL_LOAD_DWORD %0, 28, 0, 0, implicit $exec
+    %9:vgpr_32 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+    %10:vgpr_32 = GLOBAL_LOAD_DWORD %0, 36, 0, 0, implicit $exec
+    %11:vgpr_32 = GLOBAL_LOAD_DWORD %0, 40, 0, 0, implicit $exec
+    %12:vgpr_32 = GLOBAL_LOAD_DWORD %0, 44, 0, 0, implicit $exec
+    %13:vgpr_32 = GLOBAL_LOAD_DWORD %0, 48, 0, 0, implicit $exec
+    %14:vgpr_32 = GLOBAL_LOAD_DWORD %0, 52, 0, 0, implicit $exec
+    %15:vgpr_32 = GLOBAL_LOAD_DWORD %0, 56, 0, 0, implicit $exec
+    %16:vgpr_32 = GLOBAL_LOAD_DWORD %0, 60, 0, 0, implicit $exec
+    %17:vgpr_32 = GLOBAL_LOAD_DWORD %0, 64, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: reg_pressure{{$}}
+# GCN:      dead early-clobber %2:vreg_128, dead early-clobber %4:vreg_128, dead early-clobber %1:vreg_128, dead early-clobber %3:vreg_128, dead early-clobber %5:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:   dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+# GCN-NEXT:   dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+# GCN-NEXT:   dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+# GCN-NEXT:   dead %5:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 64, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: dead early-clobber %7:vreg_128, dead early-clobber %6:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT:   dead %6:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 80, 0, 0, implicit $exec
+# GCN-NEXT:   dead %7:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 96, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name:            reg_pressure
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vreg_128 }
+  - { id: 2, class: vreg_128 }
+  - { id: 3, class: vreg_128 }
+  - { id: 4, class: vreg_128 }
+  - { id: 5, class: vreg_128 }
+  - { id: 6, class: vreg_128 }
+  - { id: 7, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+    %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+    %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+    %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+    %5:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 64, 0, 0, implicit $exec
+    %6:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 80, 0, 0, implicit $exec
+    %7:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 96, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: image_clause{{$}}
+# GCN:      early-clobber %4:vreg_128, early-clobber %3:vreg_128, early-clobber %5:vreg_128 = BUNDLE %0, undef %2:sreg_128, %1, implicit $exec {
+# GCN-NEXT:   %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   %4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   %5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+
+---
+name:            image_clause
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: sreg_256 }
+  - { id: 2, class: sreg_128 }
+  - { id: 3, class: vreg_128 }
+  - { id: 4, class: vreg_128 }
+  - { id: 5, class: vreg_128 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = IMPLICIT_DEF
+    %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    %4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    %5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+    IMAGE_STORE_V4_V2 %4, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+    IMAGE_STORE_V4_V2 %5, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: mixed_clause{{$}}
+# GCN:      dead early-clobber %4:vreg_128, dead early-clobber %3:vreg_128, dead early-clobber %5:vgpr_32 = BUNDLE %0, %2, %1, implicit $exec {
+# GCN-NEXT:   dead %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT:   dead %5:vgpr_32 = BUFFER_LOAD_DWORD_ADDR64 %0, %2, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name:            mixed_clause
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: sreg_256 }
+  - { id: 2, class: sreg_128 }
+  - { id: 3, class: vreg_128 }
+  - { id: 4, class: vreg_128 }
+  - { id: 5, class: vgpr_32 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = IMPLICIT_DEF
+    %2 = IMPLICIT_DEF
+    %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+    %5:vgpr_32 = BUFFER_LOAD_DWORD_ADDR64 %0, %2, 0, 0, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: atomic{{$}}
+# GCN:      %1:vgpr_32 = IMPLICIT_DEF
+# GCN-NEXT: dead %2:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: dead %3:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: S_ENDPGM
+
+---
+name:            atomic
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vreg_64 }
+  - { id: 1, class: vgpr_32 }
+  - { id: 2, class: vgpr_32 }
+  - { id: 3, class: vgpr_32 }
+body:             |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+    %3:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+    FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+    FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+    S_ENDPGM
+...