Masked Load / Store Intrinsics - the CodeGen part.

I'm recommiting the codegen part of the patch.
The vectorizer part will be send to review again.

Masked Vector Load and Store Intrinsics.
Introduced new target-independent intrinsics in order to support masked vector loads and stores. The loop vectorizer optimizes loops containing conditional memory accesses by generating these intrinsics for existing targets AVX2 and AVX-512. The vectorizer asks the target about availability of masked vector loads and stores.
Added SDNodes for masked operations and lowering patterns for X86 code generator.
Examples:
<16 x i32> @llvm.masked.load.v16i32(i8* %addr, <16 x i32> %passthru, i32 4 /* align */, <16 x i1> %mask)
declare void @llvm.masked.store.v8f64(i8* %addr, <8 x double> %value, i32 4, <8 x i1> %mask)

Scalarizer for other targets (not AVX2/AVX-512) will be done in a separate patch.

http://reviews.llvm.org/D6191

llvm-svn: 223348

16 files changed, 661 insertions, 6 deletions

diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 3d8a37811ba..d10bdd83150 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -101,6 +101,17 @@ bool TargetTransformInfo::isLegalICmpImmediate(int64_t Imm) const {
   return PrevTTI->isLegalICmpImmediate(Imm);
 }
 
+bool TargetTransformInfo::isLegalPredicatedLoad(Type *DataType,
+                                                int Consecutive) const {
+  return false;
+}
+
+bool TargetTransformInfo::isLegalPredicatedStore(Type *DataType,
+                                                 int Consecutive) const {
+  return false;
+}
+
+
 bool TargetTransformInfo::isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV,
                                                 int64_t BaseOffset,
                                                 bool HasBaseReg,
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 201429fe754..7347111728e 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -303,6 +303,8 @@ namespace {
     SDValue visitEXTRACT_SUBVECTOR(SDNode *N);
     SDValue visitVECTOR_SHUFFLE(SDNode *N);
     SDValue visitINSERT_SUBVECTOR(SDNode *N);
+    SDValue visitMLOAD(SDNode *N);
+    SDValue visitMSTORE(SDNode *N);
 
     SDValue XformToShuffleWithZero(SDNode *N);
     SDValue ReassociateOps(unsigned Opc, SDLoc DL, SDValue LHS, SDValue RHS);
@@ -1351,6 +1353,8 @@ SDValue DAGCombiner::visit(SDNode *N) {
   case ISD::EXTRACT_SUBVECTOR:  return visitEXTRACT_SUBVECTOR(N);
   case ISD::VECTOR_SHUFFLE:     return visitVECTOR_SHUFFLE(N);
   case ISD::INSERT_SUBVECTOR:   return visitINSERT_SUBVECTOR(N);
+  case ISD::MLOAD:              return visitMLOAD(N);
+  case ISD::MSTORE:             return visitMSTORE(N);
   }
   return SDValue();
 }
@@ -4771,6 +4775,162 @@ static SDValue ConvertSelectToConcatVector(SDNode *N, SelectionDAG &DAG) {
       TopHalf->isNullValue() ? RHS->getOperand(1) : LHS->getOperand(1));
 }
 
+SDValue DAGCombiner::visitMSTORE(SDNode *N) {
+
+  if (Level >= AfterLegalizeTypes)
+    return SDValue();
+
+  MaskedStoreSDNode *MST = dyn_cast<MaskedStoreSDNode>(N);
+  SDValue Mask = MST->getMask();
+  SDValue Data  = MST->getData();
+  SDLoc DL(N);
+
+  // If the MSTORE data type requires splitting and the mask is provided by a
+  // SETCC, then split both nodes and its operands before legalization. This
+  // prevents the type legalizer from unrolling SETCC into scalar comparisons
+  // and enables future optimizations (e.g. min/max pattern matching on X86).
+  if (Mask.getOpcode() == ISD::SETCC) {
+
+    // Check if any splitting is required.
+    if (TLI.getTypeAction(*DAG.getContext(), Data.getValueType()) !=
+        TargetLowering::TypeSplitVector)
+      return SDValue();
+
+    SDValue MaskLo, MaskHi, Lo, Hi;
+    std::tie(MaskLo, MaskHi) = SplitVSETCC(Mask.getNode(), DAG);
+
+    EVT LoVT, HiVT;
+    std::tie(LoVT, HiVT) = DAG.GetSplitDestVTs(MST->getValueType(0));
+
+    SDValue Chain = MST->getChain();
+    SDValue Ptr   = MST->getBasePtr();
+
+    EVT MemoryVT = MST->getMemoryVT();
+    unsigned Alignment = MST->getOriginalAlignment();
+
+    // if Alignment is equal to the vector size,
+    // take the half of it for the second part
+    unsigned SecondHalfAlignment =
+      (Alignment == Data->getValueType(0).getSizeInBits()/8) ?
+         Alignment/2 : Alignment;
+
+    EVT LoMemVT, HiMemVT;
+    std::tie(LoMemVT, HiMemVT) = DAG.GetSplitDestVTs(MemoryVT);
+
+    SDValue DataLo, DataHi;
+    std::tie(DataLo, DataHi) = DAG.SplitVector(Data, DL);
+
+    MachineMemOperand *MMO = DAG.getMachineFunction().
+      getMachineMemOperand(MST->getPointerInfo(), 
+                           MachineMemOperand::MOStore,  LoMemVT.getStoreSize(),
+                           Alignment, MST->getAAInfo(), MST->getRanges());
+
+    Lo = DAG.getMaskedStore(Chain, DL, DataLo, Ptr, MaskLo, MMO);
+
+    unsigned IncrementSize = LoMemVT.getSizeInBits()/8;
+    Ptr = DAG.getNode(ISD::ADD, DL, Ptr.getValueType(), Ptr,
+                      DAG.getConstant(IncrementSize, Ptr.getValueType()));
+
+    MMO = DAG.getMachineFunction().
+      getMachineMemOperand(MST->getPointerInfo(), 
+                           MachineMemOperand::MOStore,  HiMemVT.getStoreSize(),
+                           SecondHalfAlignment, MST->getAAInfo(),
+                           MST->getRanges());
+
+    Hi = DAG.getMaskedStore(Chain, DL, DataHi, Ptr, MaskHi, MMO);
+
+    AddToWorklist(Lo.getNode());
+    AddToWorklist(Hi.getNode());
+
+    return DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Lo, Hi);
+  }
+  return SDValue();
+}
+
+SDValue DAGCombiner::visitMLOAD(SDNode *N) {
+
+  if (Level >= AfterLegalizeTypes)
+    return SDValue();
+
+  MaskedLoadSDNode *MLD = dyn_cast<MaskedLoadSDNode>(N);
+  SDValue Mask = MLD->getMask();
+  SDLoc DL(N);
+
+  // If the MLOAD result requires splitting and the mask is provided by a
+  // SETCC, then split both nodes and its operands before legalization. This
+  // prevents the type legalizer from unrolling SETCC into scalar comparisons
+  // and enables future optimizations (e.g. min/max pattern matching on X86).
+
+  if (Mask.getOpcode() == ISD::SETCC) {
+    EVT VT = N->getValueType(0);
+
+    // Check if any splitting is required.
+    if (TLI.getTypeAction(*DAG.getContext(), VT) !=
+        TargetLowering::TypeSplitVector)
+      return SDValue();
+
+    SDValue MaskLo, MaskHi, Lo, Hi;
+    std::tie(MaskLo, MaskHi) = SplitVSETCC(Mask.getNode(), DAG);
+
+    SDValue Src0 = MLD->getSrc0();
+    SDValue Src0Lo, Src0Hi;
+    std::tie(Src0Lo, Src0Hi) = DAG.SplitVector(Src0, DL);
+
+    EVT LoVT, HiVT;
+    std::tie(LoVT, HiVT) = DAG.GetSplitDestVTs(MLD->getValueType(0));
+
+    SDValue Chain = MLD->getChain();
+    SDValue Ptr   = MLD->getBasePtr();
+    EVT MemoryVT = MLD->getMemoryVT();
+    unsigned Alignment = MLD->getOriginalAlignment();
+
+    // if Alignment is equal to the vector size,
+    // take the half of it for the second part
+    unsigned SecondHalfAlignment =
+      (Alignment == MLD->getValueType(0).getSizeInBits()/8) ?
+         Alignment/2 : Alignment;
+
+    EVT LoMemVT, HiMemVT;
+    std::tie(LoMemVT, HiMemVT) = DAG.GetSplitDestVTs(MemoryVT);
+
+    MachineMemOperand *MMO = DAG.getMachineFunction().
+    getMachineMemOperand(MLD->getPointerInfo(), 
+                         MachineMemOperand::MOLoad,  LoMemVT.getStoreSize(),
+                         Alignment, MLD->getAAInfo(), MLD->getRanges());
+
+    Lo = DAG.getMaskedLoad(LoVT, DL, Chain, Ptr, MaskLo, Src0Lo, MMO);
+
+    unsigned IncrementSize = LoMemVT.getSizeInBits()/8;
+    Ptr = DAG.getNode(ISD::ADD, DL, Ptr.getValueType(), Ptr,
+                      DAG.getConstant(IncrementSize, Ptr.getValueType()));
+
+    MMO = DAG.getMachineFunction().
+    getMachineMemOperand(MLD->getPointerInfo(), 
+                         MachineMemOperand::MOLoad,  HiMemVT.getStoreSize(),
+                         SecondHalfAlignment, MLD->getAAInfo(), MLD->getRanges());
+
+    Hi = DAG.getMaskedLoad(HiVT, DL, Chain, Ptr, MaskHi, Src0Hi, MMO);
+
+    AddToWorklist(Lo.getNode());
+    AddToWorklist(Hi.getNode());
+
+    // Build a factor node to remember that this load is independent of the
+    // other one.
+    Chain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Lo.getValue(1),
+                        Hi.getValue(1));
+
+    // Legalized the chain result - switch anything that used the old chain to
+    // use the new one.
+    DAG.ReplaceAllUsesOfValueWith(SDValue(MLD, 1), Chain);
+
+    SDValue LoadRes = DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, Lo, Hi);
+
+    SDValue RetOps[] = { LoadRes, Chain };
+    return DAG.getMergeValues(RetOps, DL);
+  }
+  return SDValue();
+}
+
 SDValue DAGCombiner::visitVSELECT(SDNode *N) {
   SDValue N0 = N->getOperand(0);
   SDValue N1 = N->getOperand(1);
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
index b73bb0a897b..52c2d1be430 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
@@ -825,6 +825,10 @@ bool DAGTypeLegalizer::PromoteIntegerOperand(SDNode *N, unsigned OpNo) {
   case ISD::SINT_TO_FP:   Res = PromoteIntOp_SINT_TO_FP(N); break;
   case ISD::STORE:        Res = PromoteIntOp_STORE(cast<StoreSDNode>(N),
                                                    OpNo); break;
+  case ISD::MSTORE:       Res = PromoteIntOp_MSTORE(cast<MaskedStoreSDNode>(N),
+                                                    OpNo); break;
+  case ISD::MLOAD:        Res = PromoteIntOp_MLOAD(cast<MaskedLoadSDNode>(N),
+                                                    OpNo); break;
   case ISD::TRUNCATE:     Res = PromoteIntOp_TRUNCATE(N); break;
   case ISD::FP16_TO_FP:
   case ISD::UINT_TO_FP:   Res = PromoteIntOp_UINT_TO_FP(N); break;
@@ -1091,6 +1095,25 @@ SDValue DAGTypeLegalizer::PromoteIntOp_STORE(StoreSDNode *N, unsigned OpNo){
                            N->getMemoryVT(), N->getMemOperand());
 }
 
+SDValue DAGTypeLegalizer::PromoteIntOp_MSTORE(MaskedStoreSDNode *N, unsigned OpNo){
+
+  assert(OpNo == 2 && "Only know how to promote the mask!");
+  EVT DataVT = N->getOperand(3).getValueType();
+  SDValue Mask = PromoteTargetBoolean(N->getOperand(OpNo), DataVT);
+  SmallVector<SDValue, 4> NewOps(N->op_begin(), N->op_end());
+  NewOps[OpNo] = Mask;
+  return SDValue(DAG.UpdateNodeOperands(N, NewOps), 0);
+}
+
+SDValue DAGTypeLegalizer::PromoteIntOp_MLOAD(MaskedLoadSDNode *N, unsigned OpNo){
+  assert(OpNo == 2 && "Only know how to promote the mask!");
+  EVT DataVT = N->getValueType(0);
+  SDValue Mask = PromoteTargetBoolean(N->getOperand(OpNo), DataVT);
+  SmallVector<SDValue, 4> NewOps(N->op_begin(), N->op_end());
+  NewOps[OpNo] = Mask;
+  return SDValue(DAG.UpdateNodeOperands(N, NewOps), 0);
+}
+
 SDValue DAGTypeLegalizer::PromoteIntOp_TRUNCATE(SDNode *N) {
   SDValue Op = GetPromotedInteger(N->getOperand(0));
   return DAG.getNode(ISD::TRUNCATE, SDLoc(N), N->getValueType(0), Op);
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
index 30f412ba317..805b0fc0463 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
@@ -285,6 +285,8 @@ private:
   SDValue PromoteIntOp_TRUNCATE(SDNode *N);
   SDValue PromoteIntOp_UINT_TO_FP(SDNode *N);
   SDValue PromoteIntOp_ZERO_EXTEND(SDNode *N);
+  SDValue PromoteIntOp_MSTORE(MaskedStoreSDNode *N, unsigned OpNo);
+  SDValue PromoteIntOp_MLOAD(MaskedLoadSDNode *N, unsigned OpNo);
 
   void PromoteSetCCOperands(SDValue &LHS,SDValue &RHS, ISD::CondCode Code);
 
@@ -578,6 +580,7 @@ private:
   void SplitVecRes_FPOWI(SDNode *N, SDValue &Lo, SDValue &Hi);
   void SplitVecRes_INSERT_VECTOR_ELT(SDNode *N, SDValue &Lo, SDValue &Hi);
   void SplitVecRes_LOAD(LoadSDNode *N, SDValue &Lo, SDValue &Hi);
+  void SplitVecRes_MLOAD(MaskedLoadSDNode *N, SDValue &Lo, SDValue &Hi);
   void SplitVecRes_SCALAR_TO_VECTOR(SDNode *N, SDValue &Lo, SDValue &Hi);
   void SplitVecRes_SIGN_EXTEND_INREG(SDNode *N, SDValue &Lo, SDValue &Hi);
   void SplitVecRes_SETCC(SDNode *N, SDValue &Lo, SDValue &Hi);
@@ -594,6 +597,7 @@ private:
   SDValue SplitVecOp_EXTRACT_SUBVECTOR(SDNode *N);
   SDValue SplitVecOp_EXTRACT_VECTOR_ELT(SDNode *N);
   SDValue SplitVecOp_STORE(StoreSDNode *N, unsigned OpNo);
+  SDValue SplitVecOp_MSTORE(MaskedStoreSDNode *N, unsigned OpNo);
   SDValue SplitVecOp_CONCAT_VECTORS(SDNode *N);
   SDValue SplitVecOp_TRUNCATE(SDNode *N);
   SDValue SplitVecOp_VSETCC(SDNode *N);
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
index 27f63d27823..88f67370228 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -597,6 +597,9 @@ void DAGTypeLegalizer::SplitVectorResult(SDNode *N, unsigned ResNo) {
   case ISD::LOAD:
     SplitVecRes_LOAD(cast<LoadSDNode>(N), Lo, Hi);
     break;
+  case ISD::MLOAD:
+    SplitVecRes_MLOAD(cast<MaskedLoadSDNode>(N), Lo, Hi);
+    break;
   case ISD::SETCC:
     SplitVecRes_SETCC(N, Lo, Hi);
     break;
@@ -979,6 +982,64 @@ void DAGTypeLegalizer::SplitVecRes_LOAD(LoadSDNode *LD, SDValue &Lo,
   ReplaceValueWith(SDValue(LD, 1), Ch);
 }
 
+void DAGTypeLegalizer::SplitVecRes_MLOAD(MaskedLoadSDNode *MLD,
+                                         SDValue &Lo, SDValue &Hi) {
+  EVT LoVT, HiVT;
+  SDLoc dl(MLD);
+  std::tie(LoVT, HiVT) = DAG.GetSplitDestVTs(MLD->getValueType(0));
+
+  SDValue Ch = MLD->getChain();
+  SDValue Ptr = MLD->getBasePtr();
+  SDValue Mask = MLD->getMask();
+  unsigned Alignment = MLD->getOriginalAlignment();
+
+  // if Alignment is equal to the vector size,
+  // take the half of it for the second part
+  unsigned SecondHalfAlignment =
+    (Alignment == MLD->getValueType(0).getSizeInBits()/8) ?
+     Alignment/2 : Alignment;
+
+  SDValue MaskLo, MaskHi;
+  std::tie(MaskLo, MaskHi) = DAG.SplitVector(Mask, dl);
+
+  EVT MemoryVT = MLD->getMemoryVT();
+  EVT LoMemVT, HiMemVT;
+  std::tie(LoMemVT, HiMemVT) = DAG.GetSplitDestVTs(MemoryVT);
+
+  SDValue Src0 = MLD->getSrc0();
+  SDValue Src0Lo, Src0Hi;
+  std::tie(Src0Lo, Src0Hi) = DAG.SplitVector(Src0, dl);
+
+  MachineMemOperand *MMO = DAG.getMachineFunction().
+    getMachineMemOperand(MLD->getPointerInfo(), 
+                         MachineMemOperand::MOLoad,  LoMemVT.getStoreSize(),
+                         Alignment, MLD->getAAInfo(), MLD->getRanges());
+
+  Lo = DAG.getMaskedLoad(LoVT, dl, Ch, Ptr, MaskLo, Src0Lo, MMO);
+
+  unsigned IncrementSize = LoMemVT.getSizeInBits()/8;
+  Ptr = DAG.getNode(ISD::ADD, dl, Ptr.getValueType(), Ptr,
+                    DAG.getConstant(IncrementSize, Ptr.getValueType()));
+
+  MMO = DAG.getMachineFunction().
+    getMachineMemOperand(MLD->getPointerInfo(), 
+                         MachineMemOperand::MOLoad,  HiMemVT.getStoreSize(),
+                         SecondHalfAlignment, MLD->getAAInfo(), MLD->getRanges());
+
+  Hi = DAG.getMaskedLoad(HiVT, dl, Ch, Ptr, MaskHi, Src0Hi, MMO);
+
+
+  // Build a factor node to remember that this load is independent of the
+  // other one.
+  Ch = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, Lo.getValue(1),
+                   Hi.getValue(1));
+
+  // Legalized the chain result - switch anything that used the old chain to
+  // use the new one.
+  ReplaceValueWith(SDValue(MLD, 1), Ch);
+
+}
+
 void DAGTypeLegalizer::SplitVecRes_SETCC(SDNode *N, SDValue &Lo, SDValue &Hi) {
   assert(N->getValueType(0).isVector() &&
          N->getOperand(0).getValueType().isVector() &&
@@ -1234,6 +1295,9 @@ bool DAGTypeLegalizer::SplitVectorOperand(SDNode *N, unsigned OpNo) {
     case ISD::STORE:
       Res = SplitVecOp_STORE(cast<StoreSDNode>(N), OpNo);
       break;
+    case ISD::MSTORE:
+      Res = SplitVecOp_MSTORE(cast<MaskedStoreSDNode>(N), OpNo);
+      break;
     case ISD::VSELECT:
       Res = SplitVecOp_VSELECT(N, OpNo);
       break;
@@ -1395,6 +1459,56 @@ SDValue DAGTypeLegalizer::SplitVecOp_EXTRACT_VECTOR_ELT(SDNode *N) {
                         MachinePointerInfo(), EltVT, false, false, false, 0);
 }
 
+SDValue DAGTypeLegalizer::SplitVecOp_MSTORE(MaskedStoreSDNode *N,
+                                            unsigned OpNo) {
+  SDValue Ch  = N->getChain();
+  SDValue Ptr = N->getBasePtr();
+  SDValue Mask = N->getMask();
+  SDValue Data = N->getData();
+  EVT MemoryVT = N->getMemoryVT();
+  unsigned Alignment = N->getOriginalAlignment();
+  SDLoc DL(N);
+  
+  EVT LoMemVT, HiMemVT;
+  std::tie(LoMemVT, HiMemVT) = DAG.GetSplitDestVTs(MemoryVT);
+
+  SDValue DataLo, DataHi;
+  GetSplitVector(Data, DataLo, DataHi);
+  SDValue MaskLo, MaskHi;
+  GetSplitVector(Mask, MaskLo, MaskHi);
+
+  // if Alignment is equal to the vector size,
+  // take the half of it for the second part
+  unsigned SecondHalfAlignment =
+    (Alignment == Data->getValueType(0).getSizeInBits()/8) ?
+       Alignment/2 : Alignment;
+
+  SDValue Lo, Hi;
+  MachineMemOperand *MMO = DAG.getMachineFunction().
+    getMachineMemOperand(N->getPointerInfo(), 
+                         MachineMemOperand::MOStore, LoMemVT.getStoreSize(),
+                         Alignment, N->getAAInfo(), N->getRanges());
+
+  Lo = DAG.getMaskedStore(Ch, DL, DataLo, Ptr, MaskLo, MMO);
+
+  unsigned IncrementSize = LoMemVT.getSizeInBits()/8;
+  Ptr = DAG.getNode(ISD::ADD, DL, Ptr.getValueType(), Ptr,
+                    DAG.getConstant(IncrementSize, Ptr.getValueType()));
+
+  MMO = DAG.getMachineFunction().
+    getMachineMemOperand(N->getPointerInfo(), 
+                         MachineMemOperand::MOStore,  HiMemVT.getStoreSize(),
+                         SecondHalfAlignment, N->getAAInfo(), N->getRanges());
+
+  Hi = DAG.getMaskedStore(Ch, DL, DataHi, Ptr, MaskHi, MMO);
+
+
+  // Build a factor node to remember that this store is independent of the
+  // other one.
+  return DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Lo, Hi);
+
+}
+
 SDValue DAGTypeLegalizer::SplitVecOp_STORE(StoreSDNode *N, unsigned OpNo) {
   assert(N->isUnindexed() && "Indexed store of vector?");
   assert(OpNo == 1 && "Can only split the stored value");
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 7961e66d8c8..57ec81bba4a 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -4917,6 +4917,60 @@ SelectionDAG::getIndexedStore(SDValue OrigStore, SDLoc dl, SDValue Base,
   return SDValue(N, 0);
 }
 
+SDValue
+SelectionDAG::getMaskedLoad(EVT VT, SDLoc dl, SDValue Chain,
+                            SDValue Ptr, SDValue Mask, SDValue Src0,
+                            MachineMemOperand *MMO) {
+
+  SDVTList VTs = getVTList(VT, MVT::Other);
+  SDValue Ops[] = { Chain, Ptr, Mask, Src0 };
+  FoldingSetNodeID ID;
+  AddNodeIDNode(ID, ISD::MLOAD, VTs, Ops);
+  ID.AddInteger(VT.getRawBits());
+  ID.AddInteger(encodeMemSDNodeFlags(ISD::NON_EXTLOAD, ISD::UNINDEXED,
+                                     MMO->isVolatile(),
+                                     MMO->isNonTemporal(),
+                                     MMO->isInvariant()));
+  ID.AddInteger(MMO->getPointerInfo().getAddrSpace());
+  void *IP = nullptr;
+  if (SDNode *E = CSEMap.FindNodeOrInsertPos(ID, IP)) {
+    cast<MaskedLoadSDNode>(E)->refineAlignment(MMO);
+    return SDValue(E, 0);
+  }
+  SDNode *N = new (NodeAllocator) MaskedLoadSDNode(dl.getIROrder(),
+                                             dl.getDebugLoc(), Ops, 4, VTs,
+                                             VT, MMO);
+  CSEMap.InsertNode(N, IP);
+  InsertNode(N);
+  return SDValue(N, 0);
+}
+
+SDValue SelectionDAG::getMaskedStore(SDValue Chain, SDLoc dl, SDValue Val,
+                               SDValue Ptr, SDValue Mask, MachineMemOperand *MMO) {
+  assert(Chain.getValueType() == MVT::Other &&
+        "Invalid chain type");
+  EVT VT = Val.getValueType();
+  SDVTList VTs = getVTList(MVT::Other);
+  SDValue Ops[] = { Chain, Ptr, Mask, Val };
+  FoldingSetNodeID ID;
+  AddNodeIDNode(ID, ISD::MSTORE, VTs, Ops);
+  ID.AddInteger(VT.getRawBits());
+  ID.AddInteger(encodeMemSDNodeFlags(false, ISD::UNINDEXED, MMO->isVolatile(),
+                                     MMO->isNonTemporal(), MMO->isInvariant()));
+  ID.AddInteger(MMO->getPointerInfo().getAddrSpace());
+  void *IP = nullptr;
+  if (SDNode *E = CSEMap.FindNodeOrInsertPos(ID, IP)) {
+    cast<MaskedStoreSDNode>(E)->refineAlignment(MMO);
+    return SDValue(E, 0);
+  }
+  SDNode *N = new (NodeAllocator) MaskedStoreSDNode(dl.getIROrder(),
+                                                    dl.getDebugLoc(), Ops, 4,
+                                                    VTs, VT, MMO);
+  CSEMap.InsertNode(N, IP);
+  InsertNode(N);
+  return SDValue(N, 0);
+}
+
 SDValue SelectionDAG::getVAArg(EVT VT, SDLoc dl,
                                SDValue Chain, SDValue Ptr,
                                SDValue SV,
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index eeecbf11bad..c3b197e97eb 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -3617,6 +3617,70 @@ void SelectionDAGBuilder::visitStore(const StoreInst &I) {
   DAG.setRoot(StoreNode);
 }
 
+void SelectionDAGBuilder::visitMaskedStore(const CallInst &I) {
+  SDLoc sdl = getCurSDLoc();
+
+  Value  *PtrOperand = I.getArgOperand(0);
+  SDValue Ptr = getValue(PtrOperand);
+  SDValue Src0 = getValue(I.getArgOperand(1));
+  SDValue Mask = getValue(I.getArgOperand(3));
+  EVT VT = Src0.getValueType();
+  unsigned Alignment = (cast<ConstantInt>(I.getArgOperand(2)))->getZExtValue();
+  if (!Alignment)
+    Alignment = DAG.getEVTAlignment(VT);
+
+  AAMDNodes AAInfo;
+  I.getAAMetadata(AAInfo);
+
+  MachineMemOperand *MMO =
+    DAG.getMachineFunction().
+    getMachineMemOperand(MachinePointerInfo(PtrOperand),
+                          MachineMemOperand::MOStore,  VT.getStoreSize(),
+                          Alignment, AAInfo);
+  SDValue StoreNode = DAG.getMaskedStore(getRoot(), sdl, Src0, Ptr, Mask, MMO);
+  DAG.setRoot(StoreNode);
+  setValue(&I, StoreNode);
+}
+
+void SelectionDAGBuilder::visitMaskedLoad(const CallInst &I) {
+  SDLoc sdl = getCurSDLoc();
+
+  Value  *PtrOperand = I.getArgOperand(0);
+  SDValue Ptr = getValue(PtrOperand);
+  SDValue Src0 = getValue(I.getArgOperand(1));
+  SDValue Mask = getValue(I.getArgOperand(3));
+
+  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+  EVT VT = TLI.getValueType(I.getType());
+  unsigned Alignment = (cast<ConstantInt>(I.getArgOperand(2)))->getZExtValue();
+  if (!Alignment)
+    Alignment = DAG.getEVTAlignment(VT);
+
+  AAMDNodes AAInfo;
+  I.getAAMetadata(AAInfo);
+  const MDNode *Ranges = I.getMetadata(LLVMContext::MD_range);
+
+  SDValue InChain = DAG.getRoot();
+  if (AA->pointsToConstantMemory(
+      AliasAnalysis::Location(PtrOperand,
+                              AA->getTypeStoreSize(I.getType()),
+                              AAInfo))) {
+    // Do not serialize (non-volatile) loads of constant memory with anything.
+    InChain = DAG.getEntryNode();
+  }
+
+  MachineMemOperand *MMO =
+    DAG.getMachineFunction().
+    getMachineMemOperand(MachinePointerInfo(PtrOperand),
+                          MachineMemOperand::MOLoad,  VT.getStoreSize(),
+                          Alignment, AAInfo, Ranges);
+
+  SDValue Load = DAG.getMaskedLoad(VT, sdl, InChain, Ptr, Mask, Src0, MMO);
+  SDValue OutChain = Load.getValue(1);
+  DAG.setRoot(OutChain);
+  setValue(&I, Load);
+}
+
 void SelectionDAGBuilder::visitAtomicCmpXchg(const AtomicCmpXchgInst &I) {
   SDLoc dl = getCurSDLoc();
   AtomicOrdering SuccessOrder = I.getSuccessOrdering();
@@ -4918,6 +4982,12 @@ SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, unsigned Intrinsic) {
     return nullptr;
   }
 
+  case Intrinsic::masked_load:
+    visitMaskedLoad(I);
+    return nullptr;
+  case Intrinsic::masked_store:
+    visitMaskedStore(I);
+    return nullptr;
   case Intrinsic::x86_mmx_pslli_w:
   case Intrinsic::x86_mmx_pslli_d:
   case Intrinsic::x86_mmx_pslli_q:
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.h b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.h
index 2ae1e96a63e..b2517b93e45 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.h
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.h
@@ -769,6 +769,8 @@ private:
   void visitAlloca(const AllocaInst &I);
   void visitLoad(const LoadInst &I);
   void visitStore(const StoreInst &I);
+  void visitMaskedLoad(const CallInst &I);
+  void visitMaskedStore(const CallInst &I);
   void visitAtomicCmpXchg(const AtomicCmpXchgInst &I);
   void visitAtomicRMW(const AtomicRMWInst &I);
   void visitFence(const FenceInst &I);
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
index c9f6cff9155..e8577d898c2 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
@@ -269,6 +269,8 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const {
     // Other operators
   case ISD::LOAD:                       return "load";
   case ISD::STORE:                      return "store";
+  case ISD::MLOAD:                      return "masked_load";
+  case ISD::MSTORE:                     return "masked_store";
   case ISD::VAARG:                      return "vaarg";
   case ISD::VACOPY:                     return "vacopy";
   case ISD::VAEND:                      return "vaend";
diff --git a/llvm/lib/IR/Function.cpp b/llvm/lib/IR/Function.cpp
index c7d3d149e0c..ba6e4ce79a1 100644
--- a/llvm/lib/IR/Function.cpp
+++ b/llvm/lib/IR/Function.cpp
@@ -551,7 +551,8 @@ enum IIT_Info {
   IIT_ANYPTR = 26,
   IIT_V1   = 27,
   IIT_VARARG = 28,
-  IIT_HALF_VEC_ARG = 29
+  IIT_HALF_VEC_ARG = 29,
+  IIT_SAME_VEC_WIDTH_ARG = 30
 };
 
 
@@ -659,6 +660,12 @@ static void DecodeIITType(unsigned &NextElt, ArrayRef<unsigned char> Infos,
                                              ArgInfo));
     return;
   }
+  case IIT_SAME_VEC_WIDTH_ARG: {
+    unsigned ArgInfo = (NextElt == Infos.size() ? 0 : Infos[NextElt++]);
+    OutputTable.push_back(IITDescriptor::get(IITDescriptor::SameVecWidthArgument,
+                                             ArgInfo));
+    return;
+  }
   case IIT_EMPTYSTRUCT:
     OutputTable.push_back(IITDescriptor::get(IITDescriptor::Struct, 0));
     return;
@@ -766,7 +773,14 @@ static Type *DecodeFixedType(ArrayRef<Intrinsic::IITDescriptor> &Infos,
   case IITDescriptor::HalfVecArgument:
     return VectorType::getHalfElementsVectorType(cast<VectorType>(
                                                   Tys[D.getArgumentNumber()]));
-  }
+  case IITDescriptor::SameVecWidthArgument:
+    Type *EltTy = DecodeFixedType(Infos, Tys, Context);
+    Type *Ty = Tys[D.getArgumentNumber()];
+    if (VectorType *VTy = dyn_cast<VectorType>(Ty)) {
+      return VectorType::get(EltTy, VTy->getNumElements());
+    }
+    llvm_unreachable("unhandled");
+ }
   llvm_unreachable("unhandled");
 }
 
diff --git a/llvm/lib/IR/IRBuilder.cpp b/llvm/lib/IR/IRBuilder.cpp
index a4c5d9766a2..5f63ded48fe 100644
--- a/llvm/lib/IR/IRBuilder.cpp
+++ b/llvm/lib/IR/IRBuilder.cpp
@@ -183,3 +183,29 @@ CallInst *IRBuilderBase::CreateAssumption(Value *Cond) {
   return createCallHelper(FnAssume, Ops, this);
 }
 
+/// Create a call to a Masked Load intrinsic.
+/// Ops - an array of operands.
+CallInst *IRBuilderBase::CreateMaskedLoad(ArrayRef<Value *> Ops) {
+  // The only one overloaded type - the type of passthru value in this case
+  Type *DataTy = Ops[1]->getType();
+  return CreateMaskedIntrinsic(Intrinsic::masked_load, Ops, DataTy);
+}
+
+/// Create a call to a Masked Store intrinsic.
+/// Ops - an array of operands.
+CallInst *IRBuilderBase::CreateMaskedStore(ArrayRef<Value *> Ops) {
+  // DataTy - type of the data to be stored - the only one overloaded type
+  Type *DataTy = Ops[1]->getType();
+  return CreateMaskedIntrinsic(Intrinsic::masked_store, Ops, DataTy);
+}
+
+/// Create a call to a Masked intrinsic, with given intrinsic Id,
+/// an array of operands - Ops, and one overloaded type - DataTy
+CallInst *IRBuilderBase::CreateMaskedIntrinsic(unsigned Id,
+                                               ArrayRef<Value *> Ops,
+                                               Type *DataTy) {
+  Module *M = BB->getParent()->getParent();
+  Type *OverloadedTypes[] = { DataTy };
+  Value *TheFn = Intrinsic::getDeclaration(M, (Intrinsic::ID)Id, OverloadedTypes);
+  return createCallHelper(TheFn, Ops, this);
+}
diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index 976786d047c..c025a958385 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -2406,6 +2406,19 @@ bool Verifier::VerifyIntrinsicType(Type *Ty,
            !isa<VectorType>(ArgTys[D.getArgumentNumber()]) ||
            VectorType::getHalfElementsVectorType(
                          cast<VectorType>(ArgTys[D.getArgumentNumber()])) != Ty;
+  case IITDescriptor::SameVecWidthArgument: {
+    if (D.getArgumentNumber() >= ArgTys.size())
+      return true;
+    VectorType * ReferenceType =
+      dyn_cast<VectorType>(ArgTys[D.getArgumentNumber()]);
+    VectorType *ThisArgType = dyn_cast<VectorType>(Ty);
+    if (!ThisArgType || !ReferenceType || 
+        (ReferenceType->getVectorNumElements() !=
+         ThisArgType->getVectorNumElements()))
+      return true;
+    return VerifyIntrinsicType(ThisArgType->getVectorElementType(),
+                               Infos, ArgTys);
+  }
   }
   llvm_unreachable("unhandled");
 }
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index c21e6146115..cdb691248ef 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -1319,13 +1319,21 @@ void X86TargetLowering::resetOperationActions() {
 
       // Extract subvector is special because the value type
       // (result) is 128-bit but the source is 256-bit wide.
-      if (VT.is128BitVector())
+      if (VT.is128BitVector()) {
+        if (VT.getScalarSizeInBits() >= 32) {
+          setOperationAction(ISD::MLOAD,  VT, Custom);
+          setOperationAction(ISD::MSTORE, VT, Custom);
+        }
         setOperationAction(ISD::EXTRACT_SUBVECTOR, VT, Custom);
-
+      }
       // Do not attempt to custom lower other non-256-bit vectors
       if (!VT.is256BitVector())
         continue;
 
+      if (VT.getScalarSizeInBits() >= 32) {
+        setOperationAction(ISD::MLOAD,  VT, Legal);
+        setOperationAction(ISD::MSTORE, VT, Legal);
+      }
       setOperationAction(ISD::BUILD_VECTOR,       VT, Custom);
       setOperationAction(ISD::VECTOR_SHUFFLE,     VT, Custom);
       setOperationAction(ISD::INSERT_VECTOR_ELT,  VT, Custom);
@@ -1492,9 +1500,13 @@ void X86TargetLowering::resetOperationActions() {
       unsigned EltSize = VT.getVectorElementType().getSizeInBits();
       // Extract subvector is special because the value type
       // (result) is 256/128-bit but the source is 512-bit wide.
-      if (VT.is128BitVector() || VT.is256BitVector())
+      if (VT.is128BitVector() || VT.is256BitVector()) {
         setOperationAction(ISD::EXTRACT_SUBVECTOR, VT, Custom);
-
+        if ( EltSize >= 32) {
+          setOperationAction(ISD::MLOAD,   VT, Legal);
+          setOperationAction(ISD::MSTORE,  VT, Legal);
+        }
+      }
       if (VT.getVectorElementType() == MVT::i1)
         setOperationAction(ISD::EXTRACT_SUBVECTOR, VT, Legal);
 
@@ -1510,6 +1522,8 @@ void X86TargetLowering::resetOperationActions() {
         setOperationAction(ISD::EXTRACT_VECTOR_ELT,  VT, Custom);
         setOperationAction(ISD::SCALAR_TO_VECTOR,    VT, Custom);
         setOperationAction(ISD::INSERT_SUBVECTOR,    VT, Custom);
+        setOperationAction(ISD::MLOAD,               VT, Legal);
+        setOperationAction(ISD::MSTORE,              VT, Legal);
       }
     }
     for (int i = MVT::v32i8; i != MVT::v8i64; ++i) {
diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td
index 273b4add5e7..1b24163f44b 100644
--- a/llvm/lib/Target/X86/X86InstrAVX512.td
+++ b/llvm/lib/Target/X86/X86InstrAVX512.td
@@ -2122,6 +2122,41 @@ def: Pat<(int_x86_avx512_mask_storeu_pd_512 addr:$ptr, (v8f64 VR512:$src),
          (VMOVUPDZmrk addr:$ptr, (v8i1 (COPY_TO_REGCLASS GR8:$mask, VK8WM)),
             VR512:$src)>;
 
+def: Pat<(masked_store addr:$ptr, VK8WM:$mask, (v8f32 VR256:$src)),
+         (VMOVUPSZmrk addr:$ptr,
+         (v16i1 (COPY_TO_REGCLASS VK8WM:$mask, VK16WM)),
+         (INSERT_SUBREG (v16f32 (IMPLICIT_DEF)), VR256:$src, sub_ymm))>;
+
+def: Pat<(v8f32 (masked_load addr:$ptr, VK8WM:$mask, undef)),
+         (v8f32 (EXTRACT_SUBREG (v16f32 (VMOVUPSZrmkz 
+          (v16i1 (COPY_TO_REGCLASS VK8WM:$mask, VK16WM)), addr:$ptr)), sub_ymm))>;
+
+def: Pat<(masked_store addr:$ptr, VK16WM:$mask, (v16f32 VR512:$src)),
+         (VMOVUPSZmrk addr:$ptr, VK16WM:$mask, VR512:$src)>;
+
+def: Pat<(masked_store addr:$ptr, VK8WM:$mask, (v8f64 VR512:$src)),
+         (VMOVUPDZmrk addr:$ptr, VK8WM:$mask, VR512:$src)>;
+
+def: Pat<(v16f32 (masked_load addr:$ptr, VK16WM:$mask, undef)),
+         (VMOVUPSZrmkz VK16WM:$mask, addr:$ptr)>;
+
+def: Pat<(v16f32 (masked_load addr:$ptr, VK16WM:$mask,
+                              (bc_v16f32 (v16i32 immAllZerosV)))),
+         (VMOVUPSZrmkz VK16WM:$mask, addr:$ptr)>;
+
+def: Pat<(v16f32 (masked_load addr:$ptr, VK16WM:$mask, (v16f32 VR512:$src0))),
+         (VMOVUPSZrmk VR512:$src0, VK16WM:$mask, addr:$ptr)>;
+
+def: Pat<(v8f64 (masked_load addr:$ptr, VK8WM:$mask, undef)),
+         (VMOVUPDZrmkz VK8WM:$mask, addr:$ptr)>;
+
+def: Pat<(v8f64 (masked_load addr:$ptr, VK8WM:$mask,
+                             (bc_v8f64 (v16i32 immAllZerosV)))),
+         (VMOVUPDZrmkz VK8WM:$mask, addr:$ptr)>;
+
+def: Pat<(v8f64 (masked_load addr:$ptr, VK8WM:$mask, (v8f64 VR512:$src0))),
+         (VMOVUPDZrmk VR512:$src0, VK8WM:$mask, addr:$ptr)>;
+
 defm VMOVDQA32 : avx512_load_vl<0x6F, "vmovdqa32", "alignedload", "i", "32",
                                 "16", "8", "4", SSEPackedInt, HasAVX512>,
                  avx512_store_vl<0x7F, "vmovdqa32", "alignedstore",
@@ -2196,6 +2231,46 @@ def : Pat<(v16i32 (vselect VK16WM:$mask, (v16i32 immAllZerosV),
                   (VMOVDQU32Zrrkz (KNOTWrr VK16WM:$mask), VR512:$src)>;
 }
 
+def: Pat<(v16i32 (masked_load addr:$ptr, VK16WM:$mask, (v16i32 immAllZerosV))),
+         (VMOVDQU32Zrmkz VK16WM:$mask, addr:$ptr)>;
+
+def: Pat<(v16i32 (masked_load addr:$ptr, VK16WM:$mask, undef)),
+         (VMOVDQU32Zrmkz VK16WM:$mask, addr:$ptr)>;
+
+def: Pat<(v16i32 (masked_load addr:$ptr, VK16WM:$mask, (v16i32 VR512:$src0))),
+         (VMOVDQU32Zrmk VR512:$src0, VK16WM:$mask, addr:$ptr)>;
+
+def: Pat<(v8i64 (masked_load addr:$ptr, VK8WM:$mask,
+                             (bc_v8i64 (v16i32 immAllZerosV)))),
+         (VMOVDQU64Zrmkz VK8WM:$mask, addr:$ptr)>;
+
+def: Pat<(v8i64 (masked_load addr:$ptr, VK8WM:$mask, undef)),
+         (VMOVDQU64Zrmkz VK8WM:$mask, addr:$ptr)>;
+
+def: Pat<(v8i64 (masked_load addr:$ptr, VK8WM:$mask, (v8i64 VR512:$src0))),
+         (VMOVDQU64Zrmk VR512:$src0, VK8WM:$mask, addr:$ptr)>;
+
+def: Pat<(masked_store addr:$ptr, VK16WM:$mask, (v16i32 VR512:$src)),
+         (VMOVDQU32Zmrk addr:$ptr, VK16WM:$mask, VR512:$src)>;
+
+def: Pat<(masked_store addr:$ptr, VK8WM:$mask, (v8i64 VR512:$src)),
+         (VMOVDQU64Zmrk addr:$ptr, VK8WM:$mask, VR512:$src)>;
+
+// SKX replacement
+def: Pat<(masked_store addr:$ptr, VK8WM:$mask, (v8i32 VR256:$src)),
+         (VMOVDQU32Z256mrk addr:$ptr, VK8WM:$mask, VR256:$src)>;
+
+// KNL replacement
+def: Pat<(masked_store addr:$ptr, VK8WM:$mask, (v8i32 VR256:$src)),
+         (VMOVDQU32Zmrk addr:$ptr,
+         (v16i1 (COPY_TO_REGCLASS VK8WM:$mask, VK16WM)),
+         (INSERT_SUBREG (v16i32 (IMPLICIT_DEF)), VR256:$src, sub_ymm))>;
+
+def: Pat<(v8i32 (masked_load addr:$ptr, VK8WM:$mask, undef)),
+         (v8i32 (EXTRACT_SUBREG (v16i32 (VMOVDQU32Zrmkz 
+          (v16i1 (COPY_TO_REGCLASS VK8WM:$mask, VK16WM)), addr:$ptr)), sub_ymm))>;
+
+
 // Move Int Doubleword to Packed Double Int
 //
 def VMOVDI2PDIZrr : AVX512BI<0x6E, MRMSrcReg, (outs VR128X:$dst), (ins GR32:$src),
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index 18ba3b45197..547e3835a72 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -9260,6 +9260,61 @@ defm VPMASKMOVQ : avx2_pmovmask<"vpmaskmovq",
                                 int_x86_avx2_maskstore_q,
                                 int_x86_avx2_maskstore_q_256>, VEX_W;
 
+def: Pat<(masked_store addr:$ptr, (v8i32 VR256:$mask), (v8f32 VR256:$src)),
+         (VPMASKMOVDYmr addr:$ptr, VR256:$mask, VR256:$src)>;
+
+def: Pat<(masked_store addr:$ptr, (v8i32 VR256:$mask), (v8i32 VR256:$src)),
+         (VPMASKMOVDYmr addr:$ptr, VR256:$mask, VR256:$src)>;
+
+def: Pat<(v8f32 (masked_load addr:$ptr, (v8i32 VR256:$mask), undef)),
+         (VPMASKMOVDYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v8f32 (masked_load addr:$ptr, (v8i32 VR256:$mask),
+                             (bc_v8f32 (v8i32 immAllZerosV)))),
+         (VPMASKMOVDYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v8f32 (masked_load addr:$ptr, (v8i32 VR256:$mask), (v8f32 VR256:$src0))),
+         (VBLENDVPSYrr VR256:$src0, (VPMASKMOVDYrm VR256:$mask, addr:$ptr),
+                       VR256:$mask)>;
+
+def: Pat<(v8i32 (masked_load addr:$ptr, (v8i32 VR256:$mask), undef)),
+         (VPMASKMOVDYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v8i32 (masked_load addr:$ptr, (v8i32 VR256:$mask), (v8i32 immAllZerosV))),
+         (VPMASKMOVDYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v8i32 (masked_load addr:$ptr, (v8i32 VR256:$mask), (v8i32 VR256:$src0))),
+         (VBLENDVPSYrr VR256:$src0, (VPMASKMOVDYrm VR256:$mask, addr:$ptr),
+                       VR256:$mask)>;
+
+def: Pat<(masked_store addr:$ptr, (v4i64 VR256:$mask), (v4f64 VR256:$src)),
+         (VPMASKMOVQYmr addr:$ptr, VR256:$mask, VR256:$src)>;
+
+def: Pat<(masked_store addr:$ptr, (v4i64 VR256:$mask), (v4i64 VR256:$src)),
+         (VPMASKMOVQYmr addr:$ptr, VR256:$mask, VR256:$src)>;
+
+def: Pat<(v4f64 (masked_load addr:$ptr, (v4i64 VR256:$mask), undef)),
+         (VPMASKMOVQYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v4f64 (masked_load addr:$ptr, (v4i64 VR256:$mask),
+                             (v4f64 immAllZerosV))),
+         (VPMASKMOVQYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v4f64 (masked_load addr:$ptr, (v4i64 VR256:$mask), (v4f64 VR256:$src0))),
+         (VBLENDVPDYrr VR256:$src0, (VPMASKMOVQYrm VR256:$mask, addr:$ptr),
+                       VR256:$mask)>;
+
+def: Pat<(v4i64 (masked_load addr:$ptr, (v4i64 VR256:$mask), undef)),
+         (VPMASKMOVQYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v4i64 (masked_load addr:$ptr, (v4i64 VR256:$mask),
+                             (bc_v4i64 (v8i32 immAllZerosV)))),
+         (VPMASKMOVQYrm VR256:$mask, addr:$ptr)>;
+
+def: Pat<(v4i64 (masked_load addr:$ptr, (v4i64 VR256:$mask), (v4i64 VR256:$src0))),
+         (VBLENDVPDYrr VR256:$src0, (VPMASKMOVQYrm VR256:$mask, addr:$ptr),
+                       VR256:$mask)>;
+
 
 //===----------------------------------------------------------------------===//
 // Variable Bit Shifts
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 9f9fb350bdc..bed78ac8ab9 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -111,6 +111,8 @@ public:
                          Type *Ty) const override;
   unsigned getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
                          Type *Ty) const override;
+  bool isLegalPredicatedLoad (Type *DataType, int Consecutive) const override;
+  bool isLegalPredicatedStore(Type *DataType, int Consecutive) const override;
 
   /// @}
 };
@@ -1156,3 +1158,19 @@ unsigned X86TTI::getIntImmCost(Intrinsic::ID IID, unsigned Idx,
   }
   return X86TTI::getIntImmCost(Imm, Ty);
 }
+
+bool X86TTI::isLegalPredicatedLoad(Type *DataType, int Consecutive) const {
+  int ScalarWidth = DataType->getScalarSizeInBits();
+  
+  // Todo: AVX512 allows gather/scatter, works with strided and random as well
+  if ((ScalarWidth < 32) || (Consecutive == 0))
+    return false;
+  if (ST->hasAVX512() || ST->hasAVX2()) 
+    return true;
+  return false;
+}
+
+bool X86TTI::isLegalPredicatedStore(Type *DataType, int Consecutive) const {
+  return isLegalPredicatedLoad(DataType, Consecutive);
+}
+