diff --git a/include/llvm/CodeGen/TargetInstrInfo.h b/include/llvm/CodeGen/TargetInstrInfo.h
index e6418fb..b732be6 100644
--- a/include/llvm/CodeGen/TargetInstrInfo.h
+++ b/include/llvm/CodeGen/TargetInstrInfo.h
@@ -428,6 +428,13 @@
 
     RegSubRegPair(unsigned Reg = 0, unsigned SubReg = 0)
         : Reg(Reg), SubReg(SubReg) {}
+
+    bool operator==(const RegSubRegPair& P) const {
+      return Reg == P.Reg && SubReg == P.SubReg;
+    }
+    bool operator!=(const RegSubRegPair& P) const {
+      return !(*this == P);
+    }
   };
 
   /// A pair composed of a pair of a register and a sub-register index,
diff --git a/lib/Target/AMDGPU/GCNDPPCombine.cpp b/lib/Target/AMDGPU/GCNDPPCombine.cpp
index a77bb8a..430cf48 100644
--- a/lib/Target/AMDGPU/GCNDPPCombine.cpp
+++ b/lib/Target/AMDGPU/GCNDPPCombine.cpp
@@ -6,31 +6,35 @@
 //
 //===----------------------------------------------------------------------===//
 // The pass combines V_MOV_B32_dpp instruction with its VALU uses as a DPP src0
-// operand.If any of the use instruction cannot be combined with the mov the
+// operand. If any of the use instruction cannot be combined with the mov the
 // whole sequence is reverted.
 //
 // $old = ...
 // $dpp_value = V_MOV_B32_dpp $old, $vgpr_to_be_read_from_other_lane,
-//                            dpp_controls..., $bound_ctrl
-// $res = VALU $dpp_value, ...
+//                            dpp_controls..., $row_mask, $bank_mask, $bound_ctrl
+// $res = VALU $dpp_value [, src1]
 //
 // to
 //
-// $res = VALU_DPP $folded_old, $vgpr_to_be_read_from_other_lane, ...,
-//                 dpp_controls..., $folded_bound_ctrl
+// $res = VALU_DPP $combined_old, $vgpr_to_be_read_from_other_lane, [src1,]
+//                 dpp_controls..., $row_mask, $bank_mask, $combined_bound_ctrl
 //
 // Combining rules :
 //
-// $bound_ctrl is DPP_BOUND_ZERO, $old is any
-// $bound_ctrl is DPP_BOUND_OFF, $old is 0
+// if $row_mask and $bank_mask are fully enabled (0xF) and
+//    $bound_ctrl==DPP_BOUND_ZERO or $old==0
+// -> $combined_old = undef,
+//    $combined_bound_ctrl = DPP_BOUND_ZERO
 //
-// ->$folded_old = undef, $folded_bound_ctrl = DPP_BOUND_ZERO
-// $bound_ctrl is DPP_BOUND_OFF, $old is undef
+// if the VALU op is binary and
+//    $bound_ctrl==DPP_BOUND_OFF and
+//    $old==identity value (immediate) for the VALU op
+// -> $combined_old = src1,
+//    $combined_bound_ctrl = DPP_BOUND_OFF
 //
-// ->$folded_old = undef, $folded_bound_ctrl = DPP_BOUND_OFF
-// $bound_ctrl is DPP_BOUND_OFF, $old is foldable
+// Othervise cancel.
 //
-// ->$folded_old = folded value, $folded_bound_ctrl = DPP_BOUND_OFF
+// The mov_dpp instruction should recide in the same BB as all it's uses
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPU.h"
@@ -66,20 +70,16 @@
 
   MachineOperand *getOldOpndValue(MachineOperand &OldOpnd) const;
 
-  RegSubRegPair foldOldOpnd(MachineInstr &OrigMI,
-                            RegSubRegPair OldOpndVGPR,
-                            MachineOperand &OldOpndValue) const;
-
   MachineInstr *createDPPInst(MachineInstr &OrigMI,
                               MachineInstr &MovMI,
-                              RegSubRegPair OldOpndVGPR,
+                              RegSubRegPair CombOldVGPR,
                               MachineOperand *OldOpnd,
-                              bool BoundCtrlZero) const;
+                              bool CombBCZ) const;
 
   MachineInstr *createDPPInst(MachineInstr &OrigMI,
                               MachineInstr &MovMI,
-                              RegSubRegPair OldOpndVGPR,
-                              bool BoundCtrlZero) const;
+                              RegSubRegPair CombOldVGPR,
+                              bool CombBCZ) const;
 
   bool hasNoImmOrEqual(MachineInstr &MI,
                        unsigned OpndName,
@@ -152,8 +152,8 @@
 
 MachineInstr *GCNDPPCombine::createDPPInst(MachineInstr &OrigMI,
                                            MachineInstr &MovMI,
-                                           RegSubRegPair OldOpndVGPR,
-                                           bool BoundCtrlZero) const {
+                                           RegSubRegPair CombOldVGPR,
+                                           bool CombBCZ) const {
   assert(MovMI.getOpcode() == AMDGPU::V_MOV_B32_dpp);
   assert(TII->getNamedOperand(MovMI, AMDGPU::OpName::vdst)->getReg() ==
          TII->getNamedOperand(OrigMI, AMDGPU::OpName::src0)->getReg());
@@ -177,9 +177,15 @@
     const int OldIdx = AMDGPU::getNamedOperandIdx(DPPOp, AMDGPU::OpName::old);
     if (OldIdx != -1) {
       assert(OldIdx == NumOperands);
-      assert(isOfRegClass(OldOpndVGPR, AMDGPU::VGPR_32RegClass, *MRI));
-      DPPInst.addReg(OldOpndVGPR.Reg, 0, OldOpndVGPR.SubReg);
+      assert(isOfRegClass(CombOldVGPR, AMDGPU::VGPR_32RegClass, *MRI));
+      DPPInst.addReg(CombOldVGPR.Reg, 0, CombOldVGPR.SubReg);
       ++NumOperands;
+    } else {
+      // TODO: this discards MAC/FMA instructions for now, let's add it later
+      LLVM_DEBUG(dbgs() << "  failed: no old operand in DPP instruction,"
+                           " TBD\n");
+      Fail = true;
+      break;
     }
 
     if (auto *Mod0 = TII->getNamedOperand(OrigMI,
@@ -198,6 +204,7 @@
       break;
     }
     DPPInst.add(*Src0);
+    DPPInst->getOperand(NumOperands).setIsKill(false);
     ++NumOperands;
 
     if (auto *Mod1 = TII->getNamedOperand(OrigMI,
@@ -230,7 +237,7 @@
     DPPInst.add(*TII->getNamedOperand(MovMI, AMDGPU::OpName::dpp_ctrl));
     DPPInst.add(*TII->getNamedOperand(MovMI, AMDGPU::OpName::row_mask));
     DPPInst.add(*TII->getNamedOperand(MovMI, AMDGPU::OpName::bank_mask));
-    DPPInst.addImm(BoundCtrlZero ? 1 : 0);
+    DPPInst.addImm(CombBCZ ? 1 : 0);
   } while (false);
 
   if (Fail) {
@@ -241,64 +248,68 @@
   return DPPInst.getInstr();
 }
 
-GCNDPPCombine::RegSubRegPair
-GCNDPPCombine::foldOldOpnd(MachineInstr &OrigMI,
-                           RegSubRegPair OldOpndVGPR,
-                           MachineOperand &OldOpndValue) const {
-  assert(OldOpndValue.isImm());
-  switch (OrigMI.getOpcode()) {
+static bool isIdentityValue(unsigned OrigMIOp, MachineOperand *OldOpnd) {
+  assert(OldOpnd->isImm());
+  switch (OrigMIOp) {
   default: break;
+  case AMDGPU::V_ADD_U32_e32:
+  case AMDGPU::V_ADD_I32_e32:
+  case AMDGPU::V_OR_B32_e32:
+  case AMDGPU::V_SUBREV_U32_e32:
+  case AMDGPU::V_SUBREV_I32_e32:
   case AMDGPU::V_MAX_U32_e32:
-    if (OldOpndValue.getImm() == std::numeric_limits<uint32_t>::max())
-      return OldOpndVGPR;
+  case AMDGPU::V_XOR_B32_e32:
+    if (OldOpnd->getImm() == 0)
+      return true;
     break;
-  case AMDGPU::V_MAX_I32_e32:
-    if (OldOpndValue.getImm() == std::numeric_limits<int32_t>::max())
-      return OldOpndVGPR;
+  case AMDGPU::V_AND_B32_e32:
+  case AMDGPU::V_MIN_U32_e32:
+    if (static_cast<uint32_t>(OldOpnd->getImm()) ==
+        std::numeric_limits<uint32_t>::max())
+      return true;
     break;
   case AMDGPU::V_MIN_I32_e32:
-    if (OldOpndValue.getImm() == std::numeric_limits<int32_t>::min())
-      return OldOpndVGPR;
+    if (static_cast<int32_t>(OldOpnd->getImm()) ==
+        std::numeric_limits<int32_t>::max())
+      return true;
     break;
-
+  case AMDGPU::V_MAX_I32_e32:
+    if (static_cast<int32_t>(OldOpnd->getImm()) ==
+        std::numeric_limits<int32_t>::min())
+      return true;
+    break;
   case AMDGPU::V_MUL_I32_I24_e32:
   case AMDGPU::V_MUL_U32_U24_e32:
-    if (OldOpndValue.getImm() == 1) {
-      auto *Src1 = TII->getNamedOperand(OrigMI, AMDGPU::OpName::src1);
-      assert(Src1 && Src1->isReg());
-      return getRegSubRegPair(*Src1);
-    }
+    if (OldOpnd->getImm() == 1)
+      return true;
     break;
   }
-  return RegSubRegPair();
+  return false;
 }
 
-// Cases to combine:
-//  $bound_ctrl is DPP_BOUND_ZERO, $old is any
-//  $bound_ctrl is DPP_BOUND_OFF, $old is 0
-//  -> $old = undef, $bound_ctrl = DPP_BOUND_ZERO
-
-//  $bound_ctrl is DPP_BOUND_OFF, $old is undef
-//  -> $old = undef, $bound_ctrl = DPP_BOUND_OFF
-
-//  $bound_ctrl is DPP_BOUND_OFF, $old is foldable
-//  -> $old = folded value, $bound_ctrl = DPP_BOUND_OFF
-
 MachineInstr *GCNDPPCombine::createDPPInst(MachineInstr &OrigMI,
                                            MachineInstr &MovMI,
-                                           RegSubRegPair OldOpndVGPR,
+                                           RegSubRegPair CombOldVGPR,
                                            MachineOperand *OldOpndValue,
-                                           bool BoundCtrlZero) const {
-  assert(OldOpndVGPR.Reg);
-  if (!BoundCtrlZero && OldOpndValue) {
-    assert(OldOpndValue->isImm());
-    OldOpndVGPR = foldOldOpnd(OrigMI, OldOpndVGPR, *OldOpndValue);
-    if (!OldOpndVGPR.Reg) {
-      LLVM_DEBUG(dbgs() << "  failed: old immediate cannot be folded\n");
+                                           bool CombBCZ) const {
+  assert(CombOldVGPR.Reg);
+  if (!CombBCZ && OldOpndValue && OldOpndValue->isImm()) {
+    auto *Src1 = TII->getNamedOperand(OrigMI, AMDGPU::OpName::src1);
+    if (!Src1 || !Src1->isReg()) {
+      LLVM_DEBUG(dbgs() << "  failed: no src1 or it isn't a register\n");
+      return nullptr;
+    }
+    if (!isIdentityValue(OrigMI.getOpcode(), OldOpndValue)) {
+      LLVM_DEBUG(dbgs() << "  failed: old immediate ins't an identity\n");
+      return nullptr;
+    }
+    CombOldVGPR = getRegSubRegPair(*Src1);
+    if (!isOfRegClass(CombOldVGPR, AMDGPU::VGPR_32RegClass, *MRI)) {
+      LLVM_DEBUG(dbgs() << "  failed: src1 isn't a VGPR32 register\n");
       return nullptr;
     }
   }
-  return createDPPInst(OrigMI, MovMI, OldOpndVGPR, BoundCtrlZero);
+  return createDPPInst(OrigMI, MovMI, CombOldVGPR, CombBCZ);
 }
 
 // returns true if MI doesn't have OpndName immediate operand or the
@@ -315,31 +326,64 @@
 
 bool GCNDPPCombine::combineDPPMov(MachineInstr &MovMI) const {
   assert(MovMI.getOpcode() == AMDGPU::V_MOV_B32_dpp);
+  LLVM_DEBUG(dbgs() << "\nDPP combine: " << MovMI);
+
+  auto *DstOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::vdst);
+  assert(DstOpnd && DstOpnd->isReg());
+  auto DPPMovReg = DstOpnd->getReg();
+  if (!isEXECMaskConstantBetweenDefAndUses(DPPMovReg, *MRI)) {
+    LLVM_DEBUG(dbgs() << "  failed: EXEC mask should remain the same"
+                         " for all uses\n");
+    return false;
+  }
+
+  auto *RowMaskOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::row_mask);
+  assert(RowMaskOpnd && RowMaskOpnd->isImm());
+  auto *BankMaskOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::bank_mask);
+  assert(BankMaskOpnd && BankMaskOpnd->isImm());
+  const bool MaskAllLanes = RowMaskOpnd->getImm() == 0xF &&
+                            BankMaskOpnd->getImm() == 0xF;
+
   auto *BCZOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::bound_ctrl);
   assert(BCZOpnd && BCZOpnd->isImm());
-  bool BoundCtrlZero = 0 != BCZOpnd->getImm();
-
-  LLVM_DEBUG(dbgs() << "\nDPP combine: " << MovMI);
+  bool BoundCtrlZero = BCZOpnd->getImm();
 
   auto *OldOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::old);
   assert(OldOpnd && OldOpnd->isReg());
-  auto OldOpndVGPR = getRegSubRegPair(*OldOpnd);
-  auto *OldOpndValue = getOldOpndValue(*OldOpnd);
+
+  auto * const OldOpndValue = getOldOpndValue(*OldOpnd);
+  // OldOpndValue is either undef (IMPLICIT_DEF) or immediate or something else
+  // We could use: assert(!OldOpndValue || OldOpndValue->isImm())
+  // but the third option is used to distinguish undef from non-immediate
+  // to reuse IMPLICIT_DEF instruction later
   assert(!OldOpndValue || OldOpndValue->isImm() || OldOpndValue == OldOpnd);
-  if (OldOpndValue) {
-    if (BoundCtrlZero) {
-      OldOpndVGPR.Reg = AMDGPU::NoRegister; // should be undef, ignore old opnd
-      OldOpndValue = nullptr;
-    } else {
-      if (!OldOpndValue->isImm()) {
-        LLVM_DEBUG(dbgs() << "  failed: old operand isn't an imm or undef\n");
-        return false;
+
+  bool CombBCZ = false;
+
+  if (MaskAllLanes && BoundCtrlZero) { // [1]
+    CombBCZ = true;
+  } else {
+    if (!OldOpndValue || !OldOpndValue->isImm()) {
+      LLVM_DEBUG(dbgs() << "  failed: the DPP mov isn't combinable\n");
+      return false;
+    }
+
+    if (OldOpndValue->getParent()->getParent() != MovMI.getParent()) {
+      LLVM_DEBUG(dbgs() <<
+        "  failed: old reg def and mov should be in the same BB\n");
+      return false;
+    }
+
+    if (OldOpndValue->getImm() == 0) {
+      if (MaskAllLanes) {
+        assert(!BoundCtrlZero); // by check [1]
+        CombBCZ = true;
       }
-      if (OldOpndValue->getImm() == 0) {
-        OldOpndVGPR.Reg = AMDGPU::NoRegister; // should be undef
-        OldOpndValue = nullptr;
-        BoundCtrlZero = true;
-      }
+    } else if (BoundCtrlZero) {
+      assert(!MaskAllLanes); // by check [1]
+      LLVM_DEBUG(dbgs() <<
+        "  failed: old!=0 and bctrl:0 and not all lanes isn't combinable\n");
+      return false;
     }
   }
 
@@ -347,25 +391,28 @@
     if (!OldOpndValue)
       dbgs() << "undef";
     else
-      dbgs() << OldOpndValue->getImm();
-    dbgs() << ", bound_ctrl=" << BoundCtrlZero << '\n');
+      dbgs() << *OldOpndValue;
+    dbgs() << ", bound_ctrl=" << CombBCZ << '\n');
 
-  std::vector<MachineInstr*> OrigMIs, DPPMIs;
-  if (!OldOpndVGPR.Reg) { // OldOpndVGPR = undef
-    OldOpndVGPR = RegSubRegPair(
+  SmallVector<MachineInstr*, 4> OrigMIs, DPPMIs;
+  auto CombOldVGPR = getRegSubRegPair(*OldOpnd);
+  // try to reuse previous old reg if its undefined (IMPLICIT_DEF)
+  if (CombBCZ && OldOpndValue) { // CombOldVGPR should be undef
+    CombOldVGPR = RegSubRegPair(
       MRI->createVirtualRegister(&AMDGPU::VGPR_32RegClass));
     auto UndefInst = BuildMI(*MovMI.getParent(), MovMI, MovMI.getDebugLoc(),
-                             TII->get(AMDGPU::IMPLICIT_DEF), OldOpndVGPR.Reg);
+                             TII->get(AMDGPU::IMPLICIT_DEF), CombOldVGPR.Reg);
     DPPMIs.push_back(UndefInst.getInstr());
   }
 
   OrigMIs.push_back(&MovMI);
   bool Rollback = true;
-  for (auto &Use : MRI->use_nodbg_operands(
-       TII->getNamedOperand(MovMI, AMDGPU::OpName::vdst)->getReg())) {
+  for (auto &Use : MRI->use_nodbg_operands(DPPMovReg)) {
     Rollback = true;
 
     auto &OrigMI = *Use.getParent();
+    LLVM_DEBUG(dbgs() << "  try: " << OrigMI);
+
     auto OrigOp = OrigMI.getOpcode();
     if (TII->isVOP3(OrigOp)) {
       if (!TII->hasVALU32BitEncoding(OrigOp)) {
@@ -388,8 +435,8 @@
 
     LLVM_DEBUG(dbgs() << "  combining: " << OrigMI);
     if (&Use == TII->getNamedOperand(OrigMI, AMDGPU::OpName::src0)) {
-      if (auto *DPPInst = createDPPInst(OrigMI, MovMI, OldOpndVGPR,
-                                        OldOpndValue, BoundCtrlZero)) {
+      if (auto *DPPInst = createDPPInst(OrigMI, MovMI, CombOldVGPR,
+                                        OldOpndValue, CombBCZ)) {
         DPPMIs.push_back(DPPInst);
         Rollback = false;
       }
@@ -400,8 +447,8 @@
       BB->insert(OrigMI, NewMI);
       if (TII->commuteInstruction(*NewMI)) {
         LLVM_DEBUG(dbgs() << "  commuted:  " << *NewMI);
-        if (auto *DPPInst = createDPPInst(*NewMI, MovMI, OldOpndVGPR,
-                                          OldOpndValue, BoundCtrlZero)) {
+        if (auto *DPPInst = createDPPInst(*NewMI, MovMI, CombOldVGPR,
+                                          OldOpndValue, CombBCZ)) {
           DPPMIs.push_back(DPPInst);
           Rollback = false;
         }
diff --git a/lib/Target/AMDGPU/SIInstrInfo.cpp b/lib/Target/AMDGPU/SIInstrInfo.cpp
index 06c080c..c6cd7a1 100644
--- a/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -5646,3 +5646,29 @@
   }
   return nullptr;
 }
+
+bool llvm::isEXECMaskConstantBetweenDefAndUses(unsigned VReg,
+                                               MachineRegisterInfo &MRI) {
+  assert(MRI.isSSA() && "Must be run on SSA");
+  auto *TRI = MRI.getTargetRegisterInfo();
+
+  auto *DefI = MRI.getVRegDef(VReg);
+  auto *BB = DefI->getParent();
+
+  DenseSet<MachineInstr*> Uses;
+  for (auto &Use : MRI.use_nodbg_operands(VReg)) {
+    auto *I = Use.getParent();
+    if (I->getParent() != BB)
+      return false;
+    Uses.insert(I);
+  }
+
+  auto E = BB->end();
+  for (auto I = std::next(DefI->getIterator()); I != E; ++I) {
+    Uses.erase(&*I);
+    // don't check the last use
+    if (Uses.empty() || I->modifiesRegister(AMDGPU::EXEC, TRI))
+      break;
+  }
+  return Uses.empty();
+}
diff --git a/lib/Target/AMDGPU/SIInstrInfo.h b/lib/Target/AMDGPU/SIInstrInfo.h
index 2aa9a33..b96c40d 100644
--- a/lib/Target/AMDGPU/SIInstrInfo.h
+++ b/lib/Target/AMDGPU/SIInstrInfo.h
@@ -953,6 +953,12 @@
 MachineInstr *getVRegSubRegDef(const TargetInstrInfo::RegSubRegPair &P,
                                MachineRegisterInfo &MRI);
 
+/// \brief Return true if EXEC mask isnt' changed between the def and
+/// all uses of VReg. Currently if def and uses are in different BBs -
+/// simply return false. Should be run on SSA.
+bool isEXECMaskConstantBetweenDefAndUses(unsigned VReg,
+                                         MachineRegisterInfo &MRI);
+
 namespace AMDGPU {
 
   LLVM_READONLY
diff --git a/test/CodeGen/AMDGPU/dpp_combine.ll b/test/CodeGen/AMDGPU/dpp_combine.ll
deleted file mode 100644
index 36356a7..0000000
--- a/test/CodeGen/AMDGPU/dpp_combine.ll
+++ /dev/null
@@ -1,185 +0,0 @@
-; RUN: llc -march=amdgcn -mcpu=tonga -amdgpu-dpp-combine -verify-machineinstrs < %s | FileCheck %s
-
-; VOP2 with literal cannot be combined
-; CHECK-LABEL: {{^}}dpp_combine_i32_literal:
-; CHECK: v_mov_b32_dpp [[OLD:v[0-9]+]], {{v[0-9]+}} quad_perm:[1,0,0,0] row_mask:0x2 bank_mask:0x1 bound_ctrl:0
-; CHECK: v_add_u32_e32 {{v[0-9]+}}, vcc, 42, [[OLD]]
-define amdgpu_kernel void @dpp_combine_i32_literal(i32 addrspace(1)* %out, i32 %in) {
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 1, i32 2, i32 1, i1 1) #0
-  %res = add nsw i32 %dpp, 42
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_i32_bz:
-; CHECK: v_add_u32_dpp {{v[0-9]+}}, vcc, {{v[0-9]+}}, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-define amdgpu_kernel void @dpp_combine_i32_bz(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 1, i32 1, i32 1, i1 1) #0
-  %res = add nsw i32 %dpp, %x
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_i32_boff_undef:
-; CHECK: v_add_u32_dpp {{v[0-9]+}}, vcc, {{v[0-9]+}}, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1
-define amdgpu_kernel void @dpp_combine_i32_boff_undef(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 1, i32 1, i32 1, i1 0) #0
-  %res = add nsw i32 %dpp, %x
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_i32_boff_0:
-; CHECK: v_add_u32_dpp {{v[0-9]+}}, vcc, {{v[0-9]+}}, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-define amdgpu_kernel void @dpp_combine_i32_boff_0(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 0, i32 %in, i32 1, i32 1, i32 1, i1 0) #0
-  %res = add nsw i32 %dpp, %x
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_i32_boff_max:
-; CHECK: v_bfrev_b32_e32 [[OLD:v[0-9]+]], -2
-; CHECK: v_max_i32_dpp [[OLD]], {{v[0-9]+}}, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1
-define amdgpu_kernel void @dpp_combine_i32_boff_max(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 2147483647, i32 %in, i32 1, i32 1, i32 1, i1 0) #0
-  %cmp = icmp sge i32 %dpp, %x
-  %res = select i1 %cmp, i32 %dpp, i32 %x
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_i32_boff_min:
-; CHECK: v_bfrev_b32_e32 [[OLD:v[0-9]+]], 1
-; CHECK: v_min_i32_dpp [[OLD]], {{v[0-9]+}}, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1
-define amdgpu_kernel void @dpp_combine_i32_boff_min(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 -2147483648, i32 %in, i32 1, i32 1, i32 1, i1 0) #0
-  %cmp = icmp sle i32 %dpp, %x
-  %res = select i1 %cmp, i32 %dpp, i32 %x
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_i32_boff_mul:
-; CHECK: v_mul_i32_i24_dpp v0, v3, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1
-define amdgpu_kernel void @dpp_combine_i32_boff_mul(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 1, i32 %in, i32 1, i32 1, i32 1, i1 0) #0
-
-  %dpp.shl = shl i32 %dpp, 8
-  %dpp.24 = ashr i32 %dpp.shl, 8
-  %x.shl = shl i32 %x, 8
-  %x.24 = ashr i32 %x.shl, 8
-  %res = mul i32 %dpp.24, %x.24
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_i32_commute:
-; CHECK: v_subrev_u32_dpp {{v[0-9]+}}, vcc, {{v[0-9]+}}, v0  quad_perm:[2,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-define amdgpu_kernel void @dpp_combine_i32_commute(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 2, i32 1, i32 1, i1 1) #0
-  %res = sub nsw i32 %x, %dpp
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_f32:
-; CHECK: v_add_f32_dpp {{v[0-9]+}}, {{v[0-9]+}}, v0  quad_perm:[3,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-define amdgpu_kernel void @dpp_combine_f32(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 3, i32 1, i32 1, i1 1) #0
-  %dpp.f32 = bitcast i32 %dpp to float
-  %x.f32 = bitcast i32 %x to float
-  %res.f32 = fadd float %x.f32, %dpp.f32
-  %res = bitcast float %res.f32 to i32
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_test_f32_mods:
-; CHECK: v_mul_f32_dpp {{v[0-9]+}}, |{{v[0-9]+}}|, -v0  quad_perm:[0,1,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-define amdgpu_kernel void @dpp_combine_test_f32_mods(i32 addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 4, i32 1, i32 1, i1 1) #0
-
-  %x.f32 = bitcast i32 %x to float
-  %x.f32.neg = fsub float -0.000000e+00, %x.f32
-
-  %dpp.f32 = bitcast i32 %dpp to float
-  %dpp.f32.cmp = fcmp fast olt float %dpp.f32, 0.000000e+00
-  %dpp.f32.sign = select i1 %dpp.f32.cmp, float -1.000000e+00, float 1.000000e+00
-  %dpp.f32.abs = fmul fast float %dpp.f32, %dpp.f32.sign
-
-  %res.f32 = fmul float %x.f32.neg, %dpp.f32.abs
-  %res = bitcast float %res.f32 to i32
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_mac:
-; CHECK: v_mac_f32_dpp v0, {{v[0-9]+}}, v1  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-define amdgpu_kernel void @dpp_combine_mac(float addrspace(1)* %out, i32 %in) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %y = tail call i32 @llvm.amdgcn.workitem.id.y()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 1, i32 1, i32 1, i1 1) #0
-  %dpp.f32 = bitcast i32 %dpp to float
-  %x.f32 = bitcast i32 %x to float
-  %y.f32 = bitcast i32 %y to float
-
-  %mult = fmul float %dpp.f32, %y.f32
-  %res = fadd float %mult, %x.f32
-  store float %res, float addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_sequence:
-define amdgpu_kernel void @dpp_combine_sequence(i32 addrspace(1)* %out, i32 %in, i1 %cmp) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 1, i32 1, i32 1, i1 1) #0
-  br i1 %cmp, label %bb1, label %bb2
-bb1:
-; CHECK: v_add_u32_dpp {{v[0-9]+}}, vcc, {{v[0-9]+}}, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-  %resadd = add nsw i32 %dpp, %x
-  br label %bb3
-bb2:
-; CHECK: v_subrev_u32_dpp {{v[0-9]+}}, vcc, {{v[0-9]+}}, v0  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-  %ressub = sub nsw i32 %x, %dpp
-  br label %bb3
-bb3:
-  %res = phi i32 [%resadd, %bb1], [%ressub, %bb2]
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK-LABEL: {{^}}dpp_combine_sequence_negative:
-; CHECK: v_mov_b32_dpp v1, v1  quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-define amdgpu_kernel void @dpp_combine_sequence_negative(i32 addrspace(1)* %out, i32 %in, i1 %cmp) {
-  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
-  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 undef, i32 %in, i32 1, i32 1, i32 1, i1 1) #0
-  br i1 %cmp, label %bb1, label %bb2
-bb1:
-  %resadd = add nsw i32 %dpp, %x
-  br label %bb3
-bb2:
-  %ressub = sub nsw i32 2, %dpp ; break seq
-  br label %bb3
-bb3:
-  %res = phi i32 [%resadd, %bb1], [%ressub, %bb2]
-  store i32 %res, i32 addrspace(1)* %out
-  ret void
-}
-
-declare i32 @llvm.amdgcn.workitem.id.x()
-declare i32 @llvm.amdgcn.workitem.id.y()
-declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32, i32, i32, i1) #0
-
-attributes #0 = { nounwind readnone convergent }
diff --git a/test/CodeGen/AMDGPU/dpp_combine.mir b/test/CodeGen/AMDGPU/dpp_combine.mir
new file mode 100644
index 0000000..fbeadcf
--- /dev/null
+++ b/test/CodeGen/AMDGPU/dpp_combine.mir
@@ -0,0 +1,472 @@
+# RUN: llc -march=amdgcn -mcpu=tonga  -run-pass=gcn-dpp-combine  -o - %s | FileCheck %s
+
+---
+# old is undefined: only combine when masks are fully enabled and
+# bound_ctrl:0 is set, otherwise the result of DPP VALU op can be undefined.
+# CHECK-LABEL: name: old_is_undef
+# CHECK: %2:vgpr_32 = IMPLICIT_DEF
+# VOP2:
+# CHECK: %4:vgpr_32 = V_ADD_U32_dpp %2, %0, %1, 1, 15, 15, 1, implicit $exec
+# CHECK: %6:vgpr_32 = V_ADD_U32_e32 %5, %1, implicit $exec
+# CHECK: %8:vgpr_32 = V_ADD_U32_e32 %7, %1, implicit $exec
+# CHECK: %10:vgpr_32 = V_ADD_U32_e32 %9, %1, implicit $exec
+# VOP1:
+# CHECK: %12:vgpr_32 = V_NOT_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+# CHECK: %14:vgpr_32 = V_NOT_B32_e32 %13, implicit $exec
+# CHECK: %16:vgpr_32 = V_NOT_B32_e32 %15, implicit $exec
+# CHECK: %18:vgpr_32 = V_NOT_B32_e32 %17, implicit $exec
+name: old_is_undef
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = IMPLICIT_DEF
+
+    ; VOP2
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+    %4:vgpr_32 = V_ADD_U32_e32 %3, %1, implicit $exec
+
+    %5:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 0, implicit $exec
+    %6:vgpr_32 = V_ADD_U32_e32 %5, %1, implicit $exec
+
+    %7:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 1, implicit $exec
+    %8:vgpr_32 = V_ADD_U32_e32 %7, %1, implicit $exec
+
+    %9:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %10:vgpr_32 = V_ADD_U32_e32 %9, %1, implicit $exec
+
+    ; VOP1
+    %11:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+    %12:vgpr_32 = V_NOT_B32_e32 %11, implicit $exec
+
+    %13:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 0, implicit $exec
+    %14:vgpr_32 = V_NOT_B32_e32 %13, implicit $exec
+
+    %15:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 1, implicit $exec
+    %16:vgpr_32 = V_NOT_B32_e32 %15, implicit $exec
+
+    %17:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %18:vgpr_32 = V_NOT_B32_e32 %17, implicit $exec
+...
+
+# old is zero cases:
+
+# CHECK-LABEL: name: old_is_0
+
+# VOP2:
+# case 1: old is zero, masks are fully enabled, bound_ctrl:0 is on:
+# the DPP mov result would be either zero ({src lane disabled}|{src lane is
+# out of range}) or active src lane result - can combine with old = undef.
+# undef is preffered as it makes life easier for the regalloc.
+# CHECK: [[U1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+# CHECK: %4:vgpr_32 = V_ADD_U32_dpp [[U1]], %0, %1, 1, 15, 15, 1, implicit $exec
+
+# case 2: old is zero, masks are fully enabled, bound_ctrl:0 is off:
+# as the DPP mov old is zero this case is no different from case 1 - combine it
+# setting bound_ctrl0 on for the combined DPP VALU op to make old undefined
+# CHECK: [[U2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+# CHECK: %6:vgpr_32 = V_ADD_U32_dpp [[U2]], %0, %1, 1, 15, 15, 1, implicit $exec
+
+# case 3: masks are partialy disabled, bound_ctrl:0 is on:
+# the DPP mov result would be either zero ({src lane disabled}|{src lane is
+# out of range} or {the DPP mov's dest VGPR write is disabled by masks}) or
+# active src lane result - can combine with old = src1 of the VALU op.
+# The VALU op should have the same masks as DPP mov as they select lanes
+# with identity value.
+# Special case: the bound_ctrl for the combined DPP VALU op isn't important
+# here but let's make it off to keep the combiner's logic simpler.
+# CHECK: %8:vgpr_32 = V_ADD_U32_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec
+
+# case 4: masks are partialy disabled, bound_ctrl:0 is off:
+# the DPP mov result would be either zero ({src lane disabled}|{src lane is
+# out of range} or {the DPP mov's dest VGPR write is disabled by masks}) or
+# active src lane result - can combine with old = src1 of the VALU op.
+# The VALU op should have the same masks as DPP mov as they select
+# lanes with identity value
+# CHECK: %10:vgpr_32 = V_ADD_U32_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec
+
+# VOP1:
+# see case 1
+# CHECK: [[U3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+# CHECK: %12:vgpr_32 = V_NOT_B32_dpp [[U3]], %0, 1, 15, 15, 1, implicit $exec
+# see case 2
+# CHECK: [[U4:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+# CHECK: %14:vgpr_32 = V_NOT_B32_dpp [[U4]], %0, 1, 15, 15, 1, implicit $exec
+# case 3 and 4 not appliable as there is no way to specify unchanged result
+# for the unary VALU op
+# CHECK: %16:vgpr_32 = V_NOT_B32_e32 %15, implicit $exec
+# CHECK: %18:vgpr_32 = V_NOT_B32_e32 %17, implicit $exec
+
+name: old_is_0
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+
+    ; VOP2
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+    %4:vgpr_32 = V_ADD_U32_e32 %3, %1, implicit $exec
+
+    %5:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 0, implicit $exec
+    %6:vgpr_32 = V_ADD_U32_e32 %5, %1, implicit $exec
+
+    %7:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 1, implicit $exec
+    %8:vgpr_32 = V_ADD_U32_e32 %7, %1, implicit $exec
+
+    %9:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %10:vgpr_32 = V_ADD_U32_e32 %9, %1, implicit $exec
+
+    ; VOP1
+    %11:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+    %12:vgpr_32 = V_NOT_B32_e32 %11, implicit $exec
+
+    %13:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 0, implicit $exec
+    %14:vgpr_32 = V_NOT_B32_e32 %13, implicit $exec
+
+    %15:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 1, implicit $exec
+    %16:vgpr_32 = V_NOT_B32_e32 %15, implicit $exec
+
+    %17:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %18:vgpr_32 = V_NOT_B32_e32 %17, implicit $exec
+...
+
+# old is nonzero identity cases:
+
+# old is nonzero identity, masks are fully enabled, bound_ctrl:0 is off:
+# the DPP mov result would be either identity ({src lane disabled}|{out of
+# range}) or src lane result - can combine with old = src1 of the VALU op
+# The DPP VALU op should have the same masks (and bctrl) as DPP mov as they
+# select lanes with identity value
+
+# CHECK-LABEL: name: nonzero_old_is_identity_masks_enabled_bctl_off
+# CHECK: %4:vgpr_32 = V_MUL_U32_U24_dpp %1, %0, %1, 1, 15, 15, 0, implicit $exec
+# CHECK: %7:vgpr_32 = V_AND_B32_dpp %1, %0, %1, 1, 15, 15, 0, implicit $exec
+# CHECK: %10:vgpr_32 = V_MAX_I32_dpp %1, %0, %1, 1, 15, 15, 0, implicit $exec
+# CHECK: %13:vgpr_32 = V_MIN_I32_dpp %1, %0, %1, 1, 15, 15, 0, implicit $exec
+
+name: nonzero_old_is_identity_masks_enabled_bctl_off
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+
+    %2:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 0, implicit $exec
+    %4:vgpr_32 = V_MUL_U32_U24_e32 %3, %1, implicit $exec
+
+    %5:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
+    %6:vgpr_32 = V_MOV_B32_dpp %5, %0, 1, 15, 15, 0, implicit $exec
+    %7:vgpr_32 = V_AND_B32_e32 %6, %1, implicit $exec
+
+    %8:vgpr_32 = V_MOV_B32_e32 -2147483648, implicit $exec
+    %9:vgpr_32 = V_MOV_B32_dpp %8, %0, 1, 15, 15, 0, implicit $exec
+    %10:vgpr_32 = V_MAX_I32_e32 %9, %1, implicit $exec
+
+    %11:vgpr_32 = V_MOV_B32_e32 2147483647, implicit $exec
+    %12:vgpr_32 = V_MOV_B32_dpp %11, %0, 1, 15, 15, 0, implicit $exec
+    %13:vgpr_32 = V_MIN_I32_e32 %12, %1, implicit $exec
+...
+
+# old is nonzero identity, masks are partially enabled, bound_ctrl:0 is off:
+# the DPP mov result would be either identity ({src lane disabled}|{src lane is
+# out of range} or {the DPP mov's dest VGPR write is disabled by masks}) or
+# active src lane result - can combine with old = src1 of the VALU op.
+# The DPP VALU op should have the same masks (and bctrl) as DPP mov as they
+# select lanes with identity value
+
+# CHECK-LABEL: name: nonzero_old_is_identity_masks_partially_disabled_bctl_off
+# CHECK: %4:vgpr_32 = V_MUL_U32_U24_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec
+# CHECK: %7:vgpr_32 = V_AND_B32_dpp %1, %0, %1, 1, 15, 14, 0, implicit $exec
+# CHECK: %10:vgpr_32 = V_MAX_I32_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec
+# CHECK: %13:vgpr_32 = V_MIN_I32_dpp %1, %0, %1, 1, 15, 14, 0, implicit $exec
+
+name: nonzero_old_is_identity_masks_partially_disabled_bctl_off
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+
+    %2:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %4:vgpr_32 = V_MUL_U32_U24_e32 %3, %1, implicit $exec
+
+    %5:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
+    %6:vgpr_32 = V_MOV_B32_dpp %5, %0, 1, 15, 14, 0, implicit $exec
+    %7:vgpr_32 = V_AND_B32_e32 %6, %1, implicit $exec
+
+    %8:vgpr_32 = V_MOV_B32_e32 -2147483648, implicit $exec
+    %9:vgpr_32 = V_MOV_B32_dpp %8, %0, 1, 14, 15, 0, implicit $exec
+    %10:vgpr_32 = V_MAX_I32_e32 %9, %1, implicit $exec
+
+    %11:vgpr_32 = V_MOV_B32_e32 2147483647, implicit $exec
+    %12:vgpr_32 = V_MOV_B32_dpp %11, %0, 1, 15, 14, 0, implicit $exec
+    %13:vgpr_32 = V_MIN_I32_e32 %12, %1, implicit $exec
+...
+
+# old is nonzero identity, masks are partially enabled, bound_ctrl:0 is on:
+# the DPP mov result may have 3 different values:
+#   1. the active src lane result
+#   2. 0 if the src lane is disabled|out of range
+#   3. DPP mov's old value if the mov's dest VGPR write is disabled by masks
+# can't combine
+
+# CHECK-LABEL: name: nonzero_old_is_identity_masks_partially_disabled_bctl0
+# CHECK: %4:vgpr_32 = V_MUL_U32_U24_e32 %3, %1, implicit $exec
+# CHECK: %7:vgpr_32 = V_AND_B32_e32 %6, %1, implicit $exec
+# CHECK: %10:vgpr_32 = V_MAX_I32_e32 %9, %1, implicit $exec
+# CHECK: %13:vgpr_32 = V_MIN_I32_e32 %12, %1, implicit $exec
+
+name: nonzero_old_is_identity_masks_partially_disabled_bctl0
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+
+    %2:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 1, implicit $exec
+    %4:vgpr_32 = V_MUL_U32_U24_e32 %3, %1, implicit $exec
+
+    %5:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
+    %6:vgpr_32 = V_MOV_B32_dpp %5, %0, 1, 15, 14, 1, implicit $exec
+    %7:vgpr_32 = V_AND_B32_e32 %6, %1, implicit $exec
+
+    %8:vgpr_32 = V_MOV_B32_e32 -2147483648, implicit $exec
+    %9:vgpr_32 = V_MOV_B32_dpp %8, %0, 1, 14, 15, 1, implicit $exec
+    %10:vgpr_32 = V_MAX_I32_e32 %9, %1, implicit $exec
+
+    %11:vgpr_32 = V_MOV_B32_e32 2147483647, implicit $exec
+    %12:vgpr_32 = V_MOV_B32_dpp %11, %0, 1, 15, 14, 1, implicit $exec
+    %13:vgpr_32 = V_MIN_I32_e32 %12, %1, implicit $exec
+...
+
+# when the DPP source isn't a src0 operand the operation should be commuted if possible
+# CHECK-LABEL: name: dpp_commute
+# CHECK: %4:vgpr_32 = V_MUL_U32_U24_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec
+# CHECK: %7:vgpr_32 = V_AND_B32_dpp %1, %0, %1, 1, 15, 14, 0, implicit $exec
+# CHECK: %10:vgpr_32 = V_MAX_I32_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec
+# CHECK: %13:vgpr_32 = V_MIN_I32_dpp %1, %0, %1, 1, 15, 14, 0, implicit $exec
+# CHECK: %16:vgpr_32 = V_SUBREV_I32_dpp %1, %0, %1, 1, 14, 15, 0, implicit-def $vcc, implicit $exec
+# CHECK: %19:vgpr_32 = V_ADD_I32_e32 5, %18, implicit-def $vcc, implicit $exec
+name: dpp_commute
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+
+    %2:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %4:vgpr_32 = V_MUL_U32_U24_e32 %1, %3, implicit $exec
+
+    %5:vgpr_32 = V_MOV_B32_e32 4294967295, implicit $exec
+    %6:vgpr_32 = V_MOV_B32_dpp %5, %0, 1, 15, 14, 0, implicit $exec
+    %7:vgpr_32 = V_AND_B32_e32 %1, %6, implicit $exec
+
+    %8:vgpr_32 = V_MOV_B32_e32 -2147483648, implicit $exec
+    %9:vgpr_32 = V_MOV_B32_dpp %8, %0, 1, 14, 15, 0, implicit $exec
+    %10:vgpr_32 = V_MAX_I32_e32 %1, %9, implicit $exec
+
+    %11:vgpr_32 = V_MOV_B32_e32 2147483647, implicit $exec
+    %12:vgpr_32 = V_MOV_B32_dpp %11, %0, 1, 15, 14, 0, implicit $exec
+    %13:vgpr_32 = V_MIN_I32_e32 %1, %12, implicit $exec
+
+    %14:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %15:vgpr_32 = V_MOV_B32_dpp %14, %0, 1, 14, 15, 0, implicit $exec
+    %16:vgpr_32 = V_SUB_I32_e32 %1, %15, implicit-def $vcc, implicit $exec
+
+    ; this cannot be combined because immediate as src0 isn't commutable
+    %17:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %18:vgpr_32 = V_MOV_B32_dpp %17, %0, 1, 14, 15, 0, implicit $exec
+    %19:vgpr_32 = V_ADD_I32_e32 5, %18, implicit-def $vcc, implicit $exec
+...
+
+# check for floating point modifiers
+# CHECK-LABEL: name: add_f32_e64
+# CHECK: %3:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 15, 15, 1, implicit $exec
+# CHECK: %4:vgpr_32 = V_ADD_F32_e64 0, %3, 0, %0, 0, 1, implicit $exec
+# CHECK: %6:vgpr_32 = V_ADD_F32_dpp %2, 0, %1, 0, %0, 1, 15, 15, 1, implicit $exec
+# CHECK: %8:vgpr_32 = V_ADD_F32_dpp %2, 1, %1, 2, %0, 1, 15, 15, 1, implicit $exec
+# CHECK: %10:vgpr_32 = V_ADD_F32_e64 4, %9, 8, %0, 0, 0, implicit $exec
+
+name: add_f32_e64
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = IMPLICIT_DEF
+
+    ; this shouldn't be combined as omod is set
+    %3:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 15, 15, 1, implicit $exec
+    %4:vgpr_32 = V_ADD_F32_e64 0, %3, 0, %0, 0, 1, implicit $exec
+
+    ; this should be combined as all modifiers are default
+    %5:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 15, 15, 1, implicit $exec
+    %6:vgpr_32 = V_ADD_F32_e64 0, %5, 0, %0, 0, 0, implicit $exec
+
+    ; this should be combined as modifiers other than abs|neg are default
+    %7:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 15, 15, 1, implicit $exec
+    %8:vgpr_32 = V_ADD_F32_e64 1, %7, 2, %0, 0, 0, implicit $exec
+
+    ; this shouldn't be combined as modifiers aren't abs|neg
+    %9:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 15, 15, 1, implicit $exec
+    %10:vgpr_32 = V_ADD_F32_e64 4, %9, 8, %0, 0, 0, implicit $exec
+...
+
+# tests on sequences of dpp consumers
+# CHECK-LABEL: name: dpp_seq
+# CHECK: %4:vgpr_32 = V_ADD_I32_dpp %1, %0, %1, 1, 14, 15, 0, implicit-def $vcc, implicit $exec
+# CHECK: %5:vgpr_32 = V_SUBREV_I32_dpp %1, %0, %1, 1, 14, 15, 0, implicit-def $vcc, implicit $exec
+# CHECK: %6:vgpr_32 = V_OR_B32_dpp %1, %0, %1, 1, 14, 15, 0, implicit $exec
+# broken sequence:
+# CHECK: %7:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+
+name: dpp_seq
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %4:vgpr_32 = V_ADD_I32_e32 %3, %1, implicit-def $vcc, implicit $exec
+    %5:vgpr_32 = V_SUB_I32_e32 %1, %3, implicit-def $vcc, implicit $exec
+    %6:vgpr_32 = V_OR_B32_e32 %3, %1, implicit $exec
+
+    %7:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 14, 15, 0, implicit $exec
+    %8:vgpr_32 = V_ADD_I32_e32 %7, %1, implicit-def $vcc, implicit $exec
+    ; this breaks the sequence
+    %9:vgpr_32 = V_SUB_I32_e32 5, %7, implicit-def $vcc, implicit $exec
+...
+
+# old reg def is in diff BB - cannot combine
+# CHECK-LABEL: name: old_in_diff_bb
+# CHECK: %3:vgpr_32 = V_MOV_B32_dpp %2, %1, 1, 1, 1, 0, implicit $exec
+
+name: old_in_diff_bb
+tracksRegLiveness: true
+body: |
+  bb.0:
+    successors: %bb.1
+    liveins: $vgpr0, $vgpr1
+
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    S_BRANCH %bb.1
+
+  bb.1:
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %1, 1, 1, 1, 0, implicit $exec
+    %4:vgpr_32 = V_ADD_U32_e32 %3, %0, implicit $exec
+...
+
+# old reg def is in diff BB but bound_ctrl:0 - can combine
+# CHECK-LABEL: name: old_in_diff_bb_bctrl_zero
+# CHECK: %4:vgpr_32 = V_ADD_U32_dpp {{%[0-9]}}, %0, %1, 1, 15, 15, 1, implicit $exec
+
+name: old_in_diff_bb_bctrl_zero
+tracksRegLiveness: true
+body: |
+  bb.0:
+    successors: %bb.1
+    liveins: $vgpr0, $vgpr1
+
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    S_BRANCH %bb.1
+
+  bb.1:
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+    %4:vgpr_32 = V_ADD_U32_e32 %3, %1, implicit $exec
+...
+
+# EXEC mask changed between def and use - cannot combine
+# CHECK-LABEL: name: exec_changed
+# CHECK: %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+
+name: exec_changed
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %3:vgpr_32 = V_MOV_B32_dpp %2, %0, 1, 15, 15, 1, implicit $exec
+    %4:vgpr_32 = V_ADD_U32_e32 %3, %1, implicit $exec
+    %5:sreg_64 = COPY $exec, implicit-def $exec
+    %6:vgpr_32 = V_ADD_U32_e32 %3, %1, implicit $exec
+...
+
+# test if $old definition is correctly tracked through subreg manipulation pseudos
+
+# CHECK-LABEL: name: mul_old_subreg
+# CHECK: %7:vgpr_32 = V_MUL_I32_I24_dpp %0.sub1, %1, %0.sub1, 1, 1, 1, 0, implicit $exec
+
+name:            mul_old_subreg
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    %0:vreg_64 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+    %3:vgpr_32 = V_MOV_B32_e32 42, implicit $exec
+    %4:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, %3, %subreg.sub1
+    %5:vreg_64 = INSERT_SUBREG %4, %1, %subreg.sub1 ; %5.sub0 is taken from %4
+    %6:vgpr_32 = V_MOV_B32_dpp %5.sub0, %1, 1, 1, 1, 0, implicit $exec
+    %7:vgpr_32 = V_MUL_I32_I24_e32 %6, %0.sub1, implicit $exec
+...
+
+# CHECK-LABEL: name: add_old_subreg
+# CHECK: %5:vgpr_32 = V_ADD_U32_dpp %0.sub1, %1, %0.sub1, 1, 1, 1, 0, implicit $exec
+
+name:            add_old_subreg
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    %0:vreg_64 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %3:vreg_64 = INSERT_SUBREG %0, %2, %subreg.sub1 ; %3.sub1 is inserted
+    %4:vgpr_32 = V_MOV_B32_dpp %3.sub1, %1, 1, 1, 1, 0, implicit $exec
+    %5:vgpr_32 = V_ADD_U32_e32 %4, %0.sub1, implicit $exec
+...
+
+# CHECK-LABEL: name: add_old_subreg_undef
+# CHECK: %5:vgpr_32 = V_ADD_U32_dpp %3.sub1, %1, %0.sub1, 1, 15, 15, 1, implicit $exec
+
+name:            add_old_subreg_undef
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    %0:vreg_64 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %3:vreg_64 = REG_SEQUENCE %2, %subreg.sub0 ; %3.sub1 is undef
+    %4:vgpr_32 = V_MOV_B32_dpp %3.sub1, %1, 1, 15, 15, 1, implicit $exec
+    %5:vgpr_32 = V_ADD_U32_e32 %4, %0.sub1, implicit $exec
diff --git a/test/CodeGen/AMDGPU/dpp_combine_subregs.mir b/test/CodeGen/AMDGPU/dpp_combine_subregs.mir
deleted file mode 100644
index 83f992f..0000000
--- a/test/CodeGen/AMDGPU/dpp_combine_subregs.mir
+++ /dev/null
@@ -1,143 +0,0 @@
-# RUN: llc -march=amdgcn -mcpu=tonga  -run-pass=gcn-dpp-combine  -o - %s | FileCheck %s
-
-# test if $old definition is correctly tracked through subreg manipulation pseudos
-
----
-# CHECK-LABEL: name: mul_old_subreg
-# CHECK: %7:vgpr_32 = V_MUL_I32_I24_dpp %0.sub1, %1, %0.sub1, 1, 1, 1, 0, implicit $exec
-
-name:            mul_old_subreg
-tracksRegLiveness: true
-registers:
-  - { id: 0, class: vreg_64 }
-  - { id: 1, class: vgpr_32 }
-  - { id: 2, class: vgpr_32 }
-  - { id: 3, class: vgpr_32 }
-  - { id: 4, class: vreg_64 }
-  - { id: 5, class: vreg_64 }
-  - { id: 6, class: vgpr_32 }
-  - { id: 7, class: vgpr_32 }
-
-liveins:
-  - { reg: '$vgpr0', virtual-reg: '%0' }
-  - { reg: '$vgpr1', virtual-reg: '%1' }
-body:             |
-  bb.0:
-    liveins: $vgpr0, $vgpr1
-
-    %0:vreg_64 = COPY $vgpr0
-    %1:vgpr_32 = COPY $vgpr1
-    %2:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
-    %3:vgpr_32 = V_MOV_B32_e32 42, implicit $exec
-    %4 = REG_SEQUENCE %2, %subreg.sub0, %3, %subreg.sub1
-    %5 = INSERT_SUBREG %4, %1, %subreg.sub1 ; %5.sub0 is taken from %4
-    %6:vgpr_32 = V_MOV_B32_dpp %5.sub0, %1, 1, 1, 1, 0, implicit $exec
-    %7:vgpr_32 = V_MUL_I32_I24_e32 %6, %0.sub1, implicit $exec
-...
-
-# CHECK-LABEL: name: add_old_subreg
-# CHECK: [[OLD:\%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
-# CHECK: %5:vgpr_32 = V_ADD_U32_dpp [[OLD]], %1, %0.sub1, 1, 1, 1, 1, implicit $exec
-
-name:            add_old_subreg
-tracksRegLiveness: true
-registers:
-  - { id: 0, class: vreg_64 }
-  - { id: 1, class: vgpr_32 }
-  - { id: 2, class: vgpr_32 }
-  - { id: 3, class: vreg_64 }
-  - { id: 4, class: vgpr_32 }
-  - { id: 5, class: vgpr_32 }
-
-liveins:
-  - { reg: '$vgpr0', virtual-reg: '%0' }
-  - { reg: '$vgpr1', virtual-reg: '%1' }
-body:             |
-  bb.0:
-    liveins: $vgpr0, $vgpr1
-
-    %0:vreg_64 = COPY $vgpr0
-    %1:vgpr_32 = COPY $vgpr1
-    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
-    %3:vreg_64 = INSERT_SUBREG %0, %2, %subreg.sub1 ; %3.sub1 is inserted
-    %4:vgpr_32 = V_MOV_B32_dpp %3.sub1, %1, 1, 1, 1, 0, implicit $exec
-    %5:vgpr_32 = V_ADD_U32_e32 %4, %0.sub1, implicit $exec
-...
-
-# CHECK-LABEL: name: add_old_subreg_undef
-# CHECK: %5:vgpr_32 = V_ADD_U32_dpp %3.sub1, %1, %0.sub1, 1, 1, 1, 0, implicit $exec
-
-name:            add_old_subreg_undef
-tracksRegLiveness: true
-registers:
-  - { id: 0, class: vreg_64 }
-  - { id: 1, class: vgpr_32 }
-  - { id: 2, class: vgpr_32 }
-  - { id: 3, class: vreg_64 }
-  - { id: 4, class: vgpr_32 }
-  - { id: 5, class: vgpr_32 }
-
-liveins:
-  - { reg: '$vgpr0', virtual-reg: '%0' }
-  - { reg: '$vgpr1', virtual-reg: '%1' }
-body:             |
-  bb.0:
-    liveins: $vgpr0, $vgpr1
-
-    %0:vreg_64 = COPY $vgpr0
-    %1:vgpr_32 = COPY $vgpr1
-    %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
-    %3:vreg_64 = REG_SEQUENCE %2, %subreg.sub0 ; %3.sub1 is undef
-    %4:vgpr_32 = V_MOV_B32_dpp %3.sub1, %1, 1, 1, 1, 0, implicit $exec
-    %5:vgpr_32 = V_ADD_U32_e32 %4, %0.sub1, implicit $exec
-...
-
-# CHECK-LABEL: name: add_f32_e64
-# CHECK: %3:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 1, 1, 1, implicit $exec
-# CHECK: %4:vgpr_32 = V_ADD_F32_e64 0, %3, 0, %0, 0, 1, implicit $exec
-# CHECK: %6:vgpr_32 = V_ADD_F32_dpp %2, 0, %1, 0, %0, 1, 1, 1, 1, implicit $exec
-# CHECK: %7:vgpr_32 = V_ADD_F32_dpp %2, 1, %1, 2, %0, 1, 1, 1, 1, implicit $exec
-# CHECK: %9:vgpr_32 = V_ADD_F32_e64 4, %8, 8, %0, 0, 0, implicit $exec
-
-name:            add_f32_e64
-tracksRegLiveness: true
-registers:
-  - { id: 0, class: vgpr_32 }
-  - { id: 1, class: vgpr_32 }
-  - { id: 2, class: vgpr_32 }
-  - { id: 3, class: vgpr_32 }
-  - { id: 4, class: vgpr_32 }
-  - { id: 5, class: vgpr_32 }
-  - { id: 6, class: vgpr_32 }
-  - { id: 7, class: vgpr_32 }
-  - { id: 8, class: vgpr_32 }
-  - { id: 9, class: vgpr_32 }
-
-liveins:
-  - { reg: '$vgpr0', virtual-reg: '%0' }
-  - { reg: '$vgpr1', virtual-reg: '%1' }
-body:             |
-  bb.0:
-    liveins: $vgpr0, $vgpr1
-
-    %0:vgpr_32 = COPY $vgpr0
-    %1:vgpr_32 = COPY $vgpr1
-    %2:vgpr_32 = IMPLICIT_DEF
-    %3:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 1, 1, 1, implicit $exec
-
-    ; this shouldn't be combined as omod is set
-    %4:vgpr_32 = V_ADD_F32_e64 0, %3, 0, %0, 0, 1, implicit $exec
-
-    %5:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 1, 1, 1, implicit $exec
-
-    ; this should be combined as all modifiers are default
-    %6:vgpr_32 = V_ADD_F32_e64 0, %5, 0, %0, 0, 0, implicit $exec
-
-    ; this should be combined as modifiers other than abs|neg are default
-    %7:vgpr_32 = V_ADD_F32_e64 1, %5, 2, %0, 0, 0, implicit $exec
-
-    %8:vgpr_32 = V_MOV_B32_dpp undef %2, %1, 1, 1, 1, 1, implicit $exec
-
-    ; this shouldn't be combined as modifiers aren't abs|neg
-    %9:vgpr_32 = V_ADD_F32_e64 4, %8, 8, %0, 0, 0, implicit $exec
-...