From e1eda8a9e6064f8bf76ef618b6a1e33d61822a3b Mon Sep 17 00:00:00 2001 From: Elena Demikhovsky Date: Thu, 30 Apr 2015 08:38:48 +0000 Subject: [PATCH] Masked gather and scatter - added DAGCombine visitors and AVX-512 instruction selection patterns. All other patches, including tests will follow. http://reviews.llvm.org/D7665 llvm-svn: 236211 --- llvm/include/llvm/Target/TargetSelectionDAG.td | 14 ++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp | 142 +++++++++++++++++++++ .../CodeGen/SelectionDAG/SelectionDAGDumper.cpp | 2 + llvm/lib/Target/X86/X86ISelDAGToDAG.cpp | 38 ++++++ llvm/lib/Target/X86/X86InstrAVX512.td | 96 +++++++------- llvm/lib/Target/X86/X86InstrFragmentsSIMD.td | 46 +++++++ llvm/lib/Target/X86/X86InstrInfo.td | 2 + 7 files changed, 295 insertions(+), 45 deletions(-) diff --git a/llvm/include/llvm/Target/TargetSelectionDAG.td b/llvm/include/llvm/Target/TargetSelectionDAG.td index 5388962..ac71122 100644 --- a/llvm/include/llvm/Target/TargetSelectionDAG.td +++ b/llvm/include/llvm/Target/TargetSelectionDAG.td @@ -208,6 +208,16 @@ def SDTMaskedLoad: SDTypeProfile<1, 3, [ // masked load SDTCisVec<0>, SDTCisPtrTy<1>, SDTCisVec<2>, SDTCisSameAs<0, 3> ]>; +def SDTMaskedGather: SDTypeProfile<2, 3, [ // masked gather + SDTCisVec<0>, SDTCisVec<1>, SDTCisSameAs<0, 2>, SDTCisSameAs<1, 3>, + SDTCisPtrTy<4>, SDTCVecEltisVT<1, i1>, SDTCisSameNumEltsAs<0, 1> +]>; + +def SDTMaskedScatter: SDTypeProfile<1, 3, [ // masked scatter + SDTCisVec<0>, SDTCisVec<1>, SDTCisSameAs<0, 2>, SDTCisSameNumEltsAs<0, 1>, + SDTCVecEltisVT<0, i1>, SDTCisPtrTy<3> +]>; + def SDTVecShuffle : SDTypeProfile<1, 2, [ SDTCisSameAs<0, 1>, SDTCisSameAs<1, 2> ]>; @@ -480,6 +490,10 @@ def masked_store : SDNode<"ISD::MSTORE", SDTMaskedStore, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>; def masked_load : SDNode<"ISD::MLOAD", SDTMaskedLoad, [SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>; +def masked_scatter : SDNode<"ISD::MSCATTER", SDTMaskedScatter, + [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>; +def masked_gather : SDNode<"ISD::MGATHER", SDTMaskedGather, + [SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>; // Do not use ld, st directly. Use load, extload, sextload, zextload, store, // and truncst (see below). diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp index a5f558f..81e4a81 100644 --- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp @@ -307,6 +307,8 @@ namespace { SDValue visitINSERT_SUBVECTOR(SDNode *N); SDValue visitMLOAD(SDNode *N); SDValue visitMSTORE(SDNode *N); + SDValue visitMGATHER(SDNode *N); + SDValue visitMSCATTER(SDNode *N); SDValue visitFP_TO_FP16(SDNode *N); SDValue visitFADDForFMACombine(SDNode *N); @@ -1382,7 +1384,9 @@ SDValue DAGCombiner::visit(SDNode *N) { case ISD::VECTOR_SHUFFLE: return visitVECTOR_SHUFFLE(N); case ISD::SCALAR_TO_VECTOR: return visitSCALAR_TO_VECTOR(N); case ISD::INSERT_SUBVECTOR: return visitINSERT_SUBVECTOR(N); + case ISD::MGATHER: return visitMGATHER(N); case ISD::MLOAD: return visitMLOAD(N); + case ISD::MSCATTER: return visitMSCATTER(N); case ISD::MSTORE: return visitMSTORE(N); case ISD::FP_TO_FP16: return visitFP_TO_FP16(N); } @@ -5073,6 +5077,67 @@ static SDValue ConvertSelectToConcatVector(SDNode *N, SelectionDAG &DAG) { TopHalf->isNullValue() ? RHS->getOperand(1) : LHS->getOperand(1)); } +SDValue DAGCombiner::visitMSCATTER(SDNode *N) { + + if (Level >= AfterLegalizeTypes) + return SDValue(); + + MaskedScatterSDNode *MSC = cast(N); + SDValue Mask = MSC->getMask(); + SDValue Data = MSC->getValue(); + SDLoc DL(N); + + // If the MSCATTER 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) + return SDValue(); + + // 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(MSC->getValueType(0)); + + SDValue Chain = MSC->getChain(); + + EVT MemoryVT = MSC->getMemoryVT(); + unsigned Alignment = MSC->getOriginalAlignment(); + + EVT LoMemVT, HiMemVT; + std::tie(LoMemVT, HiMemVT) = DAG.GetSplitDestVTs(MemoryVT); + + SDValue DataLo, DataHi; + std::tie(DataLo, DataHi) = DAG.SplitVector(Data, DL); + + SDValue BasePtr = MSC->getBasePtr(); + SDValue IndexLo, IndexHi; + std::tie(IndexLo, IndexHi) = DAG.SplitVector(MSC->getIndex(), DL); + + MachineMemOperand *MMO = DAG.getMachineFunction(). + getMachineMemOperand(MSC->getPointerInfo(), + MachineMemOperand::MOStore, LoMemVT.getStoreSize(), + Alignment, MSC->getAAInfo(), MSC->getRanges()); + + SDValue OpsLo[] = { Chain, DataLo, MaskLo, BasePtr, IndexLo }; + Lo = DAG.getMaskedScatter(DAG.getVTList(MVT::Other), DataLo.getValueType(), + DL, OpsLo, MMO); + + SDValue OpsHi[] = {Chain, DataHi, MaskHi, BasePtr, IndexHi}; + Hi = DAG.getMaskedScatter(DAG.getVTList(MVT::Other), DataHi.getValueType(), + DL, OpsHi, MMO); + + AddToWorklist(Lo.getNode()); + AddToWorklist(Hi.getNode()); + + return DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Lo, Hi); +} + SDValue DAGCombiner::visitMSTORE(SDNode *N) { if (Level >= AfterLegalizeTypes) @@ -5147,6 +5212,83 @@ SDValue DAGCombiner::visitMSTORE(SDNode *N) { return SDValue(); } +SDValue DAGCombiner::visitMGATHER(SDNode *N) { + + if (Level >= AfterLegalizeTypes) + return SDValue(); + + MaskedGatherSDNode *MGT = dyn_cast(N); + SDValue Mask = MGT->getMask(); + SDLoc DL(N); + + // If the MGATHER 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) + return SDValue(); + + 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 = MGT->getValue(); + SDValue Src0Lo, Src0Hi; + std::tie(Src0Lo, Src0Hi) = DAG.SplitVector(Src0, DL); + + EVT LoVT, HiVT; + std::tie(LoVT, HiVT) = DAG.GetSplitDestVTs(VT); + + SDValue Chain = MGT->getChain(); + EVT MemoryVT = MGT->getMemoryVT(); + unsigned Alignment = MGT->getOriginalAlignment(); + + EVT LoMemVT, HiMemVT; + std::tie(LoMemVT, HiMemVT) = DAG.GetSplitDestVTs(MemoryVT); + + SDValue BasePtr = MGT->getBasePtr(); + SDValue Index = MGT->getIndex(); + SDValue IndexLo, IndexHi; + std::tie(IndexLo, IndexHi) = DAG.SplitVector(Index, DL); + + MachineMemOperand *MMO = DAG.getMachineFunction(). + getMachineMemOperand(MGT->getPointerInfo(), + MachineMemOperand::MOLoad, LoMemVT.getStoreSize(), + Alignment, MGT->getAAInfo(), MGT->getRanges()); + + SDValue OpsLo[] = { Chain, Src0Lo, MaskLo, BasePtr, IndexLo }; + Lo = DAG.getMaskedGather(DAG.getVTList(LoVT, MVT::Other), LoVT, DL, OpsLo, + MMO); + + SDValue OpsHi[] = {Chain, Src0Hi, MaskHi, BasePtr, IndexHi}; + Hi = DAG.getMaskedGather(DAG.getVTList(HiVT, MVT::Other), HiVT, DL, OpsHi, + 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(MGT, 1), Chain); + + SDValue GatherRes = DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, Lo, Hi); + + SDValue RetOps[] = { GatherRes, Chain }; + return DAG.getMergeValues(RetOps, DL); +} + SDValue DAGCombiner::visitMLOAD(SDNode *N) { if (Level >= AfterLegalizeTypes) diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp index b728833..8415102 100644 --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp @@ -273,6 +273,8 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const { case ISD::STORE: return "store"; case ISD::MLOAD: return "masked_load"; case ISD::MSTORE: return "masked_store"; + case ISD::MGATHER: return "masked_gather"; + case ISD::MSCATTER: return "masked_scatter"; case ISD::VAARG: return "vaarg"; case ISD::VACOPY: return "vacopy"; case ISD::VAEND: return "vaend"; diff --git a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp index fa71e3a..5bbe18e 100644 --- a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp +++ b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp @@ -204,6 +204,9 @@ namespace { bool SelectAddr(SDNode *Parent, SDValue N, SDValue &Base, SDValue &Scale, SDValue &Index, SDValue &Disp, SDValue &Segment); + bool SelectVectorAddr(SDNode *Parent, SDValue N, SDValue &Base, + SDValue &Scale, SDValue &Index, SDValue &Disp, + SDValue &Segment); bool SelectMOV64Imm32(SDValue N, SDValue &Imm); bool SelectLEAAddr(SDValue N, SDValue &Base, SDValue &Scale, SDValue &Index, SDValue &Disp, @@ -1319,6 +1322,41 @@ bool X86DAGToDAGISel::MatchAddressBase(SDValue N, X86ISelAddressMode &AM) { return false; } +bool X86DAGToDAGISel::SelectVectorAddr(SDNode *Parent, SDValue N, SDValue &Base, + SDValue &Scale, SDValue &Index, + SDValue &Disp, SDValue &Segment) { + + MaskedGatherScatterSDNode *Mgs = dyn_cast(Parent); + if (!Mgs) + return false; + X86ISelAddressMode AM; + unsigned AddrSpace = Mgs->getPointerInfo().getAddrSpace(); + // AddrSpace 256 -> GS, 257 -> FS. + if (AddrSpace == 256) + AM.Segment = CurDAG->getRegister(X86::GS, MVT::i16); + if (AddrSpace == 257) + AM.Segment = CurDAG->getRegister(X86::FS, MVT::i16); + + SDLoc DL(N); + Base = Mgs->getBasePtr(); + Index = Mgs->getIndex(); + unsigned ScalarSize = Mgs->getValue().getValueType().getScalarSizeInBits(); + Scale = getI8Imm(ScalarSize/8, DL); + + // If Base is 0, the whole address is in index and the Scale is 1 + if (ConstantSDNode *C = dyn_cast(Base)) { + assert(C->isNullValue() && "Unexpected base in gather/scatter"); + Scale = getI8Imm(1, DL); + Base = CurDAG->getRegister(0, MVT::i32); + } + if (AM.Segment.getNode()) + Segment = AM.Segment; + else + Segment = CurDAG->getRegister(0, MVT::i32); + Disp = CurDAG->getTargetConstant(0, DL, MVT::i32); + return true; +} + /// SelectAddr - returns true if it is able pattern match an addressing mode. /// It returns the operands which make up the maximal addressing mode it can /// match by reference. diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td index db15dfa..85bdfa7 100644 --- a/llvm/lib/Target/X86/X86InstrAVX512.td +++ b/llvm/lib/Target/X86/X86InstrAVX512.td @@ -5177,74 +5177,80 @@ defm VPMOVSXDQZ: avx512_extend<0x25, "vpmovsxdq", VK8WM, VR512, VR256X, X86vsext //===----------------------------------------------------------------------===// // GATHER - SCATTER Operations -multiclass avx512_gather opc, string OpcodeStr, RegisterClass KRC, - RegisterClass RC, X86MemOperand memop> { -let mayLoad = 1, - Constraints = "@earlyclobber $dst, $src1 = $dst, $mask = $mask_wb" in - def rm : AVX5128I opc, string OpcodeStr, X86VectorVTInfo _, + X86MemOperand memop, PatFrag GatherNode> { + let Constraints = "@earlyclobber $dst, $src1 = $dst, $mask = $mask_wb" in + def rm : AVX5128I, EVEX, EVEX_K; + [(set _.RC:$dst, _.KRCWM:$mask_wb, + (GatherNode (_.VT _.RC:$src1), _.KRCWM:$mask, + vectoraddr:$src2))]>, EVEX, EVEX_K, + EVEX_CD8<_.EltSize, CD8VT1>; } let ExeDomain = SSEPackedDouble in { -defm VGATHERDPDZ : avx512_gather<0x92, "vgatherdpd", VK8WM, VR512, vy64xmem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; -defm VGATHERQPDZ : avx512_gather<0x93, "vgatherqpd", VK8WM, VR512, vz64mem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; +defm VGATHERDPDZ : avx512_gather<0x92, "vgatherdpd", v8f64_info, vy64xmem, + mgatherv8i32>, EVEX_V512, VEX_W; +defm VGATHERQPDZ : avx512_gather<0x93, "vgatherqpd", v8f64_info, vz64mem, + mgatherv8i64>, EVEX_V512, VEX_W; } let ExeDomain = SSEPackedSingle in { -defm VGATHERDPSZ : avx512_gather<0x92, "vgatherdps", VK16WM, VR512, vz32mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; -defm VGATHERQPSZ : avx512_gather<0x93, "vgatherqps", VK8WM, VR256X, vz64mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; +defm VGATHERDPSZ : avx512_gather<0x92, "vgatherdps", v16f32_info, vz32mem, + mgatherv16i32>, EVEX_V512; +defm VGATHERQPSZ : avx512_gather<0x93, "vgatherqps", v8f32x_info, vz64mem, + mgatherv8i64>, EVEX_V512; } -defm VPGATHERDQZ : avx512_gather<0x90, "vpgatherdq", VK8WM, VR512, vy64xmem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; -defm VPGATHERDDZ : avx512_gather<0x90, "vpgatherdd", VK16WM, VR512, vz32mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; +defm VPGATHERDQZ : avx512_gather<0x90, "vpgatherdq", v8i64_info, vy64xmem, + mgatherv8i32>, EVEX_V512, VEX_W; +defm VPGATHERDDZ : avx512_gather<0x90, "vpgatherdd", v16i32_info, vz32mem, + mgatherv16i32>, EVEX_V512; + +defm VPGATHERQQZ : avx512_gather<0x91, "vpgatherqq", v8i64_info, vz64mem, + mgatherv8i64>, EVEX_V512, VEX_W; +defm VPGATHERQDZ : avx512_gather<0x91, "vpgatherqd", v8i32x_info, vz64mem, + mgatherv8i64>, EVEX_V512; -defm VPGATHERQQZ : avx512_gather<0x91, "vpgatherqq", VK8WM, VR512, vz64mem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; -defm VPGATHERQDZ : avx512_gather<0x91, "vpgatherqd", VK8WM, VR256X, vz64mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; +multiclass avx512_scatter opc, string OpcodeStr, X86VectorVTInfo _, + X86MemOperand memop, PatFrag ScatterNode> { -multiclass avx512_scatter opc, string OpcodeStr, RegisterClass KRC, - RegisterClass RC, X86MemOperand memop> { let mayStore = 1, Constraints = "$mask = $mask_wb" in - def mr : AVX5128I, EVEX, EVEX_K; + "\t{$src, ${dst} {${mask}}|${dst} {${mask}}, $src}"), + [(set _.KRCWM:$mask_wb, (ScatterNode (_.VT _.RC:$src), + _.KRCWM:$mask, vectoraddr:$dst))]>, + EVEX, EVEX_K, EVEX_CD8<_.EltSize, CD8VT1>; } let ExeDomain = SSEPackedDouble in { -defm VSCATTERDPDZ : avx512_scatter<0xA2, "vscatterdpd", VK8WM, VR512, vy64xmem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; -defm VSCATTERQPDZ : avx512_scatter<0xA3, "vscatterqpd", VK8WM, VR512, vz64mem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; +defm VSCATTERDPDZ : avx512_scatter<0xA2, "vscatterdpd", v8f64_info, vy64xmem, + mscatterv8i32>, EVEX_V512, VEX_W; +defm VSCATTERQPDZ : avx512_scatter<0xA3, "vscatterqpd", v8f64_info, vz64mem, + mscatterv8i64>, EVEX_V512, VEX_W; } let ExeDomain = SSEPackedSingle in { -defm VSCATTERDPSZ : avx512_scatter<0xA2, "vscatterdps", VK16WM, VR512, vz32mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; -defm VSCATTERQPSZ : avx512_scatter<0xA3, "vscatterqps", VK8WM, VR256X, vz64mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; +defm VSCATTERDPSZ : avx512_scatter<0xA2, "vscatterdps", v16f32_info, vz32mem, + mscatterv16i32>, EVEX_V512; +defm VSCATTERQPSZ : avx512_scatter<0xA3, "vscatterqps", v8f32x_info, vz64mem, + mscatterv8i64>, EVEX_V512; } -defm VPSCATTERDQZ : avx512_scatter<0xA0, "vpscatterdq", VK8WM, VR512, vy64xmem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; -defm VPSCATTERDDZ : avx512_scatter<0xA0, "vpscatterdd", VK16WM, VR512, vz32mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; +defm VPSCATTERDQZ : avx512_scatter<0xA0, "vpscatterdq", v8i64_info, vy64xmem, + mscatterv8i32>, EVEX_V512, VEX_W; +defm VPSCATTERDDZ : avx512_scatter<0xA0, "vpscatterdd", v16i32_info, vz32mem, + mscatterv16i32>, EVEX_V512; -defm VPSCATTERQQZ : avx512_scatter<0xA1, "vpscatterqq", VK8WM, VR512, vz64mem>, - EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>; -defm VPSCATTERQDZ : avx512_scatter<0xA1, "vpscatterqd", VK8WM, VR256X, vz64mem>, - EVEX_V512, EVEX_CD8<32, CD8VT1>; +defm VPSCATTERQQZ : avx512_scatter<0xA1, "vpscatterqq", v8i64_info, vz64mem, + mscatterv8i64>, EVEX_V512, VEX_W; +defm VPSCATTERQDZ : avx512_scatter<0xA1, "vpscatterqd", v8i32x_info, vz64mem, + mscatterv8i64>, EVEX_V512; // prefetch multiclass avx512_gather_scatter_prefetch opc, Format F, string OpcodeStr, diff --git a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td index b53a8f8..b5f56eb3 100644 --- a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td +++ b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td @@ -528,6 +528,52 @@ def unalignednontemporalstore : PatFrag<(ops node:$val, node:$ptr), return false; }]>; +def mgatherv8i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3), + (masked_gather node:$src1, node:$src2, node:$src3) , [{ + if (MaskedGatherSDNode *Mgt = dyn_cast(N)) + return (Mgt->getIndex().getValueType() == MVT::v8i32 || + Mgt->getBasePtr().getValueType() == MVT::v8i32); + return false; +}]>; + +def mgatherv8i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3), + (masked_gather node:$src1, node:$src2, node:$src3) , [{ + if (MaskedGatherSDNode *Mgt = dyn_cast(N)) + return (Mgt->getIndex().getValueType() == MVT::v8i64 || + Mgt->getBasePtr().getValueType() == MVT::v8i64); + return false; +}]>; +def mgatherv16i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3), + (masked_gather node:$src1, node:$src2, node:$src3) , [{ + if (MaskedGatherSDNode *Mgt = dyn_cast(N)) + return (Mgt->getIndex().getValueType() == MVT::v16i32 || + Mgt->getBasePtr().getValueType() == MVT::v16i32); + return false; +}]>; + +def mscatterv8i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3), + (masked_scatter node:$src1, node:$src2, node:$src3) , [{ + if (MaskedScatterSDNode *Sc = dyn_cast(N)) + return (Sc->getIndex().getValueType() == MVT::v8i32 || + Sc->getBasePtr().getValueType() == MVT::v8i32); + return false; +}]>; + +def mscatterv8i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3), + (masked_scatter node:$src1, node:$src2, node:$src3) , [{ + if (MaskedScatterSDNode *Sc = dyn_cast(N)) + return (Sc->getIndex().getValueType() == MVT::v8i64 || + Sc->getBasePtr().getValueType() == MVT::v8i64); + return false; +}]>; +def mscatterv16i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3), + (masked_scatter node:$src1, node:$src2, node:$src3) , [{ + if (MaskedScatterSDNode *Sc = dyn_cast(N)) + return (Sc->getIndex().getValueType() == MVT::v16i32 || + Sc->getBasePtr().getValueType() == MVT::v16i32); + return false; +}]>; + // 128-bit bitconvert pattern fragments def bc_v4f32 : PatFrag<(ops node:$in), (v4f32 (bitconvert node:$in))>; def bc_v2f64 : PatFrag<(ops node:$in), (v2f64 (bitconvert node:$in))>; diff --git a/llvm/lib/Target/X86/X86InstrInfo.td b/llvm/lib/Target/X86/X86InstrInfo.td index 8e270bf..70c2027 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.td +++ b/llvm/lib/Target/X86/X86InstrInfo.td @@ -716,6 +716,8 @@ def tls64addr : ComplexPattern; +def vectoraddr : ComplexPattern; + //===----------------------------------------------------------------------===// // X86 Instruction Predicate Definitions. def HasCMov : Predicate<"Subtarget->hasCMov()">; -- 2.7.4