diff options
Diffstat (limited to 'llvm/lib')
-rw-r--r-- | llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp | 74 | ||||
-rw-r--r-- | llvm/lib/CodeGen/GlobalISel/LegalizerInfo.cpp | 381 | ||||
-rw-r--r-- | llvm/lib/Support/LowLevelType.cpp | 2 | ||||
-rw-r--r-- | llvm/lib/Target/AArch64/AArch64LegalizerInfo.cpp | 169 | ||||
-rw-r--r-- | llvm/lib/Target/ARM/ARMLegalizerInfo.cpp | 71 | ||||
-rw-r--r-- | llvm/lib/Target/X86/X86LegalizerInfo.cpp | 66 |
6 files changed, 554 insertions, 209 deletions
diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp index 99f605abe06..a8cfe0b89a0 100644 --- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp +++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp @@ -173,12 +173,18 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, MIRBuilder.setInstr(MI); + int64_t SizeOp0 = MRI.getType(MI.getOperand(0).getReg()).getSizeInBits(); + int64_t NarrowSize = NarrowTy.getSizeInBits(); + switch (MI.getOpcode()) { default: return UnableToLegalize; case TargetOpcode::G_IMPLICIT_DEF: { - int NumParts = MRI.getType(MI.getOperand(0).getReg()).getSizeInBits() / - NarrowTy.getSizeInBits(); + // FIXME: add support for when SizeOp0 isn't an exact multiple of + // NarrowSize. + if (SizeOp0 % NarrowSize != 0) + return UnableToLegalize; + int NumParts = SizeOp0 / NarrowSize; SmallVector<unsigned, 2> DstRegs; for (int i = 0; i < NumParts; ++i) { @@ -191,9 +197,12 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, return Legalized; } case TargetOpcode::G_ADD: { + // FIXME: add support for when SizeOp0 isn't an exact multiple of + // NarrowSize. + if (SizeOp0 % NarrowSize != 0) + return UnableToLegalize; // Expand in terms of carry-setting/consuming G_ADDE instructions. - int NumParts = MRI.getType(MI.getOperand(0).getReg()).getSizeInBits() / - NarrowTy.getSizeInBits(); + int NumParts = SizeOp0 / NarrowTy.getSizeInBits(); SmallVector<unsigned, 2> Src1Regs, Src2Regs, DstRegs; extractParts(MI.getOperand(1).getReg(), NarrowTy, NumParts, Src1Regs); @@ -221,9 +230,12 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, if (TypeIdx != 1) return UnableToLegalize; - int64_t NarrowSize = NarrowTy.getSizeInBits(); - int NumParts = - MRI.getType(MI.getOperand(1).getReg()).getSizeInBits() / NarrowSize; + int64_t SizeOp1 = MRI.getType(MI.getOperand(1).getReg()).getSizeInBits(); + // FIXME: add support for when SizeOp1 isn't an exact multiple of + // NarrowSize. + if (SizeOp1 % NarrowSize != 0) + return UnableToLegalize; + int NumParts = SizeOp1 / NarrowSize; SmallVector<unsigned, 2> SrcRegs, DstRegs; SmallVector<uint64_t, 2> Indexes; @@ -270,12 +282,12 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, return Legalized; } case TargetOpcode::G_INSERT: { - if (TypeIdx != 0) + // FIXME: add support for when SizeOp0 isn't an exact multiple of + // NarrowSize. + if (SizeOp0 % NarrowSize != 0) return UnableToLegalize; - int64_t NarrowSize = NarrowTy.getSizeInBits(); - int NumParts = - MRI.getType(MI.getOperand(0).getReg()).getSizeInBits() / NarrowSize; + int NumParts = SizeOp0 / NarrowSize; SmallVector<unsigned, 2> SrcRegs, DstRegs; SmallVector<uint64_t, 2> Indexes; @@ -330,9 +342,11 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, return Legalized; } case TargetOpcode::G_LOAD: { - unsigned NarrowSize = NarrowTy.getSizeInBits(); - int NumParts = - MRI.getType(MI.getOperand(0).getReg()).getSizeInBits() / NarrowSize; + // FIXME: add support for when SizeOp0 isn't an exact multiple of + // NarrowSize. + if (SizeOp0 % NarrowSize != 0) + return UnableToLegalize; + int NumParts = SizeOp0 / NarrowSize; LLT OffsetTy = LLT::scalar( MRI.getType(MI.getOperand(1).getReg()).getScalarSizeInBits()); @@ -357,9 +371,11 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, return Legalized; } case TargetOpcode::G_STORE: { - unsigned NarrowSize = NarrowTy.getSizeInBits(); - int NumParts = - MRI.getType(MI.getOperand(0).getReg()).getSizeInBits() / NarrowSize; + // FIXME: add support for when SizeOp0 isn't an exact multiple of + // NarrowSize. + if (SizeOp0 % NarrowSize != 0) + return UnableToLegalize; + int NumParts = SizeOp0 / NarrowSize; LLT OffsetTy = LLT::scalar( MRI.getType(MI.getOperand(1).getReg()).getScalarSizeInBits()); @@ -381,9 +397,11 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, return Legalized; } case TargetOpcode::G_CONSTANT: { - unsigned NarrowSize = NarrowTy.getSizeInBits(); - int NumParts = - MRI.getType(MI.getOperand(0).getReg()).getSizeInBits() / NarrowSize; + // FIXME: add support for when SizeOp0 isn't an exact multiple of + // NarrowSize. + if (SizeOp0 % NarrowSize != 0) + return UnableToLegalize; + int NumParts = SizeOp0 / NarrowSize; const APInt &Cst = MI.getOperand(1).getCImm()->getValue(); LLVMContext &Ctx = MIRBuilder.getMF().getFunction()->getContext(); @@ -410,9 +428,12 @@ LegalizerHelper::LegalizeResult LegalizerHelper::narrowScalar(MachineInstr &MI, // ... // AN = BinOp<Ty/N> BN, CN // A = G_MERGE_VALUES A1, ..., AN - unsigned NarrowSize = NarrowTy.getSizeInBits(); - int NumParts = - MRI.getType(MI.getOperand(0).getReg()).getSizeInBits() / NarrowSize; + + // FIXME: add support for when SizeOp0 isn't an exact multiple of + // NarrowSize. + if (SizeOp0 % NarrowSize != 0) + return UnableToLegalize; + int NumParts = SizeOp0 / NarrowSize; // List the registers where the destination will be scattered. SmallVector<unsigned, 2> DstRegs; @@ -854,7 +875,12 @@ LegalizerHelper::fewerElementsVector(MachineInstr &MI, unsigned TypeIdx, case TargetOpcode::G_ADD: { unsigned NarrowSize = NarrowTy.getSizeInBits(); unsigned DstReg = MI.getOperand(0).getReg(); - int NumParts = MRI.getType(DstReg).getSizeInBits() / NarrowSize; + unsigned Size = MRI.getType(DstReg).getSizeInBits(); + int NumParts = Size / NarrowSize; + // FIXME: Don't know how to handle the situation where the small vectors + // aren't all the same size yet. + if (Size % NarrowSize != 0) + return UnableToLegalize; MIRBuilder.setInstr(MI); diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerInfo.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerInfo.cpp index e7a46eadb44..2bd8da3d83b 100644 --- a/llvm/lib/CodeGen/GlobalISel/LegalizerInfo.cpp +++ b/llvm/lib/CodeGen/GlobalISel/LegalizerInfo.cpp @@ -28,46 +28,130 @@ #include "llvm/Support/MathExtras.h" #include "llvm/Target/TargetOpcodes.h" #include <algorithm> -#include <cassert> -#include <tuple> -#include <utility> - +#include <map> using namespace llvm; -LegalizerInfo::LegalizerInfo() { - DefaultActions[TargetOpcode::G_IMPLICIT_DEF] = NarrowScalar; - - // FIXME: these two can be legalized to the fundamental load/store Jakob - // proposed. Once loads & stores are supported. - DefaultActions[TargetOpcode::G_ANYEXT] = Legal; - DefaultActions[TargetOpcode::G_TRUNC] = Legal; +LegalizerInfo::LegalizerInfo() : TablesInitialized(false) { + // Set defaults. + // FIXME: these two (G_ANYEXT and G_TRUNC?) can be legalized to the + // fundamental load/store Jakob proposed. Once loads & stores are supported. + setScalarAction(TargetOpcode::G_ANYEXT, 1, {{1, Legal}}); + setScalarAction(TargetOpcode::G_ZEXT, 1, {{1, Legal}}); + setScalarAction(TargetOpcode::G_SEXT, 1, {{1, Legal}}); + setScalarAction(TargetOpcode::G_TRUNC, 0, {{1, Legal}}); + setScalarAction(TargetOpcode::G_TRUNC, 1, {{1, Legal}}); - DefaultActions[TargetOpcode::G_INTRINSIC] = Legal; - DefaultActions[TargetOpcode::G_INTRINSIC_W_SIDE_EFFECTS] = Legal; + setScalarAction(TargetOpcode::G_INTRINSIC, 0, {{1, Legal}}); + setScalarAction(TargetOpcode::G_INTRINSIC_W_SIDE_EFFECTS, 0, {{1, Legal}}); - DefaultActions[TargetOpcode::G_ADD] = NarrowScalar; - DefaultActions[TargetOpcode::G_LOAD] = NarrowScalar; - DefaultActions[TargetOpcode::G_STORE] = NarrowScalar; - DefaultActions[TargetOpcode::G_OR] = NarrowScalar; + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_IMPLICIT_DEF, 0, narrowToSmallerAndUnsupportedIfTooSmall); + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_ADD, 0, widenToLargerTypesAndNarrowToLargest); + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_OR, 0, widenToLargerTypesAndNarrowToLargest); + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_LOAD, 0, narrowToSmallerAndUnsupportedIfTooSmall); + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_STORE, 0, narrowToSmallerAndUnsupportedIfTooSmall); - DefaultActions[TargetOpcode::G_BRCOND] = WidenScalar; - DefaultActions[TargetOpcode::G_INSERT] = NarrowScalar; - DefaultActions[TargetOpcode::G_EXTRACT] = NarrowScalar; - DefaultActions[TargetOpcode::G_FNEG] = Lower; + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_BRCOND, 0, widenToLargerTypesUnsupportedOtherwise); + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_INSERT, 0, narrowToSmallerAndUnsupportedIfTooSmall); + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_EXTRACT, 0, narrowToSmallerAndUnsupportedIfTooSmall); + setLegalizeScalarToDifferentSizeStrategy( + TargetOpcode::G_EXTRACT, 1, narrowToSmallerAndUnsupportedIfTooSmall); + setScalarAction(TargetOpcode::G_FNEG, 0, {{1, Lower}}); } void LegalizerInfo::computeTables() { - for (unsigned Opcode = 0; Opcode <= LastOp - FirstOp; ++Opcode) { - for (unsigned Idx = 0, End = Actions[Opcode].size(); Idx != End; ++Idx) { - for (auto &Action : Actions[Opcode][Idx]) { - LLT Ty = Action.first; - if (!Ty.isVector()) - continue; - - auto &Entry = MaxLegalVectorElts[std::make_pair(Opcode + FirstOp, - Ty.getElementType())]; - Entry = std::max(Entry, Ty.getNumElements()); + assert(TablesInitialized == false); + + for (unsigned OpcodeIdx = 0; OpcodeIdx <= LastOp - FirstOp; ++OpcodeIdx) { + const unsigned Opcode = FirstOp + OpcodeIdx; + for (unsigned TypeIdx = 0; TypeIdx != SpecifiedActions[OpcodeIdx].size(); + ++TypeIdx) { + // 0. Collect information specified through the setAction API, i.e. + // for specific bit sizes. + // For scalar types: + SizeAndActionsVec ScalarSpecifiedActions; + // For pointer types: + std::map<uint16_t, SizeAndActionsVec> AddressSpace2SpecifiedActions; + // For vector types: + std::map<uint16_t, SizeAndActionsVec> ElemSize2SpecifiedActions; + for (auto LLT2Action : SpecifiedActions[OpcodeIdx][TypeIdx]) { + const LLT Type = LLT2Action.first; + const LegalizeAction Action = LLT2Action.second; + + auto SizeAction = std::make_pair(Type.getSizeInBits(), Action); + if (Type.isPointer()) + AddressSpace2SpecifiedActions[Type.getAddressSpace()].push_back( + SizeAction); + else if (Type.isVector()) + ElemSize2SpecifiedActions[Type.getElementType().getSizeInBits()] + .push_back(SizeAction); + else + ScalarSpecifiedActions.push_back(SizeAction); + } + + // 1. Handle scalar types + { + // Decide how to handle bit sizes for which no explicit specification + // was given. + SizeChangeStrategy S = &unsupportedForDifferentSizes; + if (TypeIdx < ScalarSizeChangeStrategies[OpcodeIdx].size() && + ScalarSizeChangeStrategies[OpcodeIdx][TypeIdx] != nullptr) + S = ScalarSizeChangeStrategies[OpcodeIdx][TypeIdx]; + std::sort(ScalarSpecifiedActions.begin(), ScalarSpecifiedActions.end()); + checkPartialSizeAndActionsVector(ScalarSpecifiedActions); + setScalarAction(Opcode, TypeIdx, S(ScalarSpecifiedActions)); } + + // 2. Handle pointer types + for (auto PointerSpecifiedActions : AddressSpace2SpecifiedActions) { + std::sort(PointerSpecifiedActions.second.begin(), + PointerSpecifiedActions.second.end()); + checkPartialSizeAndActionsVector(PointerSpecifiedActions.second); + // For pointer types, we assume that there isn't a meaningfull way + // to change the number of bits used in the pointer. + setPointerAction( + Opcode, TypeIdx, PointerSpecifiedActions.first, + unsupportedForDifferentSizes(PointerSpecifiedActions.second)); + } + + // 3. Handle vector types + SizeAndActionsVec ElementSizesSeen; + for (auto VectorSpecifiedActions : ElemSize2SpecifiedActions) { + std::sort(VectorSpecifiedActions.second.begin(), + VectorSpecifiedActions.second.end()); + const uint16_t ElementSize = VectorSpecifiedActions.first; + ElementSizesSeen.push_back({ElementSize, Legal}); + checkPartialSizeAndActionsVector(VectorSpecifiedActions.second); + // For vector types, we assume that the best way to adapt the number + // of elements is to the next larger number of elements type for which + // the vector type is legal, unless there is no such type. In that case, + // legalize towards a vector type with a smaller number of elements. + SizeAndActionsVec NumElementsActions; + for (SizeAndAction BitsizeAndAction : VectorSpecifiedActions.second) { + assert(BitsizeAndAction.first % ElementSize == 0); + const uint16_t NumElements = BitsizeAndAction.first / ElementSize; + NumElementsActions.push_back({NumElements, BitsizeAndAction.second}); + } + setVectorNumElementAction( + Opcode, TypeIdx, ElementSize, + moreToWiderTypesAndLessToWidest(NumElementsActions)); + } + std::sort(ElementSizesSeen.begin(), ElementSizesSeen.end()); + SizeChangeStrategy VectorElementSizeChangeStrategy = + &unsupportedForDifferentSizes; + if (TypeIdx < VectorElementSizeChangeStrategies[OpcodeIdx].size() && + VectorElementSizeChangeStrategies[OpcodeIdx][TypeIdx] != nullptr) + VectorElementSizeChangeStrategy = + VectorElementSizeChangeStrategies[OpcodeIdx][TypeIdx]; + setScalarInVectorAction( + Opcode, TypeIdx, VectorElementSizeChangeStrategy(ElementSizesSeen)); } } @@ -90,69 +174,24 @@ LegalizerInfo::getAction(const InstrAspect &Aspect) const { Aspect.Opcode == TargetOpcode::G_UNMERGE_VALUES) return std::make_pair(Legal, Aspect.Type); - LLT Ty = Aspect.Type; - LegalizeAction Action = findInActions(Aspect); - // LegalizerHelper is not able to handle non-power-of-2 types right now, so do - // not try to legalize them unless they are marked as Legal or Custom. - // FIXME: This is a temporary hack until the general non-power-of-2 - // legalization works. - if (!isPowerOf2_64(Ty.getSizeInBits()) && - !(Action == Legal || Action == Custom)) - return std::make_pair(Unsupported, LLT()); - - if (Action != NotFound) - return findLegalAction(Aspect, Action); - - unsigned Opcode = Aspect.Opcode; - if (!Ty.isVector()) { - auto DefaultAction = DefaultActions.find(Aspect.Opcode); - if (DefaultAction != DefaultActions.end() && DefaultAction->second == Legal) - return std::make_pair(Legal, Ty); - - if (DefaultAction != DefaultActions.end() && DefaultAction->second == Lower) - return std::make_pair(Lower, Ty); - - if (DefaultAction == DefaultActions.end() || - DefaultAction->second != NarrowScalar) - return std::make_pair(Unsupported, LLT()); - return findLegalAction(Aspect, NarrowScalar); - } - - LLT EltTy = Ty.getElementType(); - int NumElts = Ty.getNumElements(); - - auto ScalarAction = ScalarInVectorActions.find(std::make_pair(Opcode, EltTy)); - if (ScalarAction != ScalarInVectorActions.end() && - ScalarAction->second != Legal) - return findLegalAction(Aspect, ScalarAction->second); - - // The element type is legal in principle, but the number of elements is - // wrong. - auto MaxLegalElts = MaxLegalVectorElts.lookup(std::make_pair(Opcode, EltTy)); - if (MaxLegalElts > NumElts) - return findLegalAction(Aspect, MoreElements); - - if (MaxLegalElts == 0) { - // Scalarize if there's no legal vector type, which is just a special case - // of FewerElements. - return std::make_pair(FewerElements, EltTy); - } - - return findLegalAction(Aspect, FewerElements); + if (Aspect.Type.isScalar() || Aspect.Type.isPointer()) + return findScalarLegalAction(Aspect); + assert(Aspect.Type.isVector()); + return findVectorLegalAction(Aspect); } std::tuple<LegalizerInfo::LegalizeAction, unsigned, LLT> LegalizerInfo::getAction(const MachineInstr &MI, const MachineRegisterInfo &MRI) const { SmallBitVector SeenTypes(8); - const MCInstrDesc &MCID = MI.getDesc(); - const MCOperandInfo *OpInfo = MCID.OpInfo; - for (unsigned i = 0, e = MCID.getNumOperands(); i != e; ++i) { + const MCOperandInfo *OpInfo = MI.getDesc().OpInfo; + // FIXME: probably we'll need to cache the results here somehow? + for (unsigned i = 0; i < MI.getDesc().getNumOperands(); ++i) { if (!OpInfo[i].isGenericType()) continue; - // We don't want to repeatedly check the same operand index, that - // could get expensive. + // We must only record actions once for each TypeIdx; otherwise we'd + // try to legalize operands multiple times down the line. unsigned TypeIdx = OpInfo[i].getGenericTypeIndex(); if (SeenTypes[TypeIdx]) continue; @@ -172,38 +211,164 @@ bool LegalizerInfo::isLegal(const MachineInstr &MI, return std::get<0>(getAction(MI, MRI)) == Legal; } -Optional<LLT> LegalizerInfo::findLegalType(const InstrAspect &Aspect, - LegalizeAction Action) const { - switch(Action) { - default: - llvm_unreachable("Cannot find legal type"); +bool LegalizerInfo::legalizeCustom(MachineInstr &MI, MachineRegisterInfo &MRI, + MachineIRBuilder &MIRBuilder) const { + return false; +} + +LegalizerInfo::SizeAndActionsVec +LegalizerInfo::increaseToLargerTypesAndDecreaseToLargest( + const SizeAndActionsVec &v, LegalizeAction IncreaseAction, + LegalizeAction DecreaseAction) { + SizeAndActionsVec result; + unsigned LargestSizeSoFar = 0; + if (v.size() >= 1 && v[0].first != 1) + result.push_back({1, IncreaseAction}); + for (size_t i = 0; i < v.size(); ++i) { + result.push_back(v[i]); + LargestSizeSoFar = v[i].first; + if (i + 1 < v.size() && v[i + 1].first != v[i].first + 1) { + result.push_back({LargestSizeSoFar + 1, IncreaseAction}); + LargestSizeSoFar = v[i].first + 1; + } + } + result.push_back({LargestSizeSoFar + 1, DecreaseAction}); + return result; +} + +LegalizerInfo::SizeAndActionsVec +LegalizerInfo::decreaseToSmallerTypesAndIncreaseToSmallest( + const SizeAndActionsVec &v, LegalizeAction DecreaseAction, + LegalizeAction IncreaseAction) { + SizeAndActionsVec result; + if (v.size() == 0 || v[0].first != 1) + result.push_back({1, IncreaseAction}); + for (size_t i = 0; i < v.size(); ++i) { + result.push_back(v[i]); + if (i + 1 == v.size() || v[i + 1].first != v[i].first + 1) { + result.push_back({v[i].first + 1, DecreaseAction}); + } + } + return result; +} + +LegalizerInfo::SizeAndAction +LegalizerInfo::findAction(const SizeAndActionsVec &Vec, const uint32_t Size) { + assert(Size >= 1); + // Find the last element in Vec that has a bitsize equal to or smaller than + // the requested bit size. + // That is the element just before the first element that is bigger than Size. + auto VecIt = std::upper_bound( + Vec.begin(), Vec.end(), Size, + [](const uint32_t Size, const SizeAndAction lhs) -> bool { + return Size < lhs.first; + }); + assert(VecIt != Vec.begin() && "Does Vec not start with size 1?"); + --VecIt; + int VecIdx = VecIt - Vec.begin(); + + LegalizeAction Action = Vec[VecIdx].second; + switch (Action) { case Legal: case Lower: case Libcall: case Custom: - return Aspect.Type; + return {Size, Action}; + case FewerElements: + // FIXME: is this special case still needed and correct? + // Special case for scalarization: + if (Vec == SizeAndActionsVec({{1, FewerElements}})) + return {1, FewerElements}; case NarrowScalar: { - return findLegalizableSize( - Aspect, [&](LLT Ty) -> LLT { return Ty.halfScalarSize(); }); - } - case WidenScalar: { - return findLegalizableSize(Aspect, [&](LLT Ty) -> LLT { - return Ty.getSizeInBits() < 8 ? LLT::scalar(8) : Ty.doubleScalarSize(); - }); - } - case FewerElements: { - return findLegalizableSize( - Aspect, [&](LLT Ty) -> LLT { return Ty.halfElements(); }); + // The following needs to be a loop, as for now, we do allow needing to + // go over "Unsupported" bit sizes before finding a legalizable bit size. + // e.g. (s8, WidenScalar), (s9, Unsupported), (s32, Legal). if Size==8, + // we need to iterate over s9, and then to s32 to return (s32, Legal). + // If we want to get rid of the below loop, we should have stronger asserts + // when building the SizeAndActionsVecs, probably not allowing + // "Unsupported" unless at the ends of the vector. + for (int i = VecIdx - 1; i >= 0; --i) + if (!needsLegalizingToDifferentSize(Vec[i].second) && + Vec[i].second != Unsupported) + return {Vec[i].first, Action}; + llvm_unreachable(""); } + case WidenScalar: case MoreElements: { - return findLegalizableSize( - Aspect, [&](LLT Ty) -> LLT { return Ty.doubleElements(); }); + // See above, the following needs to be a loop, at least for now. + for (std::size_t i = VecIdx + 1; i < Vec.size(); ++i) + if (!needsLegalizingToDifferentSize(Vec[i].second) && + Vec[i].second != Unsupported) + return {Vec[i].first, Action}; + llvm_unreachable(""); } + case Unsupported: + return {Size, Unsupported}; + case NotFound: + llvm_unreachable("NotFound"); } } -bool LegalizerInfo::legalizeCustom(MachineInstr &MI, - MachineRegisterInfo &MRI, - MachineIRBuilder &MIRBuilder) const { - return false; +std::pair<LegalizerInfo::LegalizeAction, LLT> +LegalizerInfo::findScalarLegalAction(const InstrAspect &Aspect) const { + assert(Aspect.Type.isScalar() || Aspect.Type.isPointer()); + if (Aspect.Opcode < FirstOp || Aspect.Opcode > LastOp) + return {NotFound, LLT()}; + const unsigned OpcodeIdx = Aspect.Opcode - FirstOp; + if (Aspect.Type.isPointer() && + AddrSpace2PointerActions[OpcodeIdx].find(Aspect.Type.getAddressSpace()) == + AddrSpace2PointerActions[OpcodeIdx].end()) { + return {NotFound, LLT()}; + } + const SmallVector<SizeAndActionsVec, 1> &Actions = + Aspect.Type.isPointer() + ? AddrSpace2PointerActions[OpcodeIdx] + .find(Aspect.Type.getAddressSpace()) + ->second + : ScalarActions[OpcodeIdx]; + if (Aspect.Idx >= Actions.size()) + return {NotFound, LLT()}; + const SizeAndActionsVec &Vec = Actions[Aspect.Idx]; + // FIXME: speed up this search, e.g. by using a results cache for repeated + // queries? + auto SizeAndAction = findAction(Vec, Aspect.Type.getSizeInBits()); + return {SizeAndAction.second, + Aspect.Type.isScalar() ? LLT::scalar(SizeAndAction.first) + : LLT::pointer(Aspect.Type.getAddressSpace(), + SizeAndAction.first)}; +} + +std::pair<LegalizerInfo::LegalizeAction, LLT> +LegalizerInfo::findVectorLegalAction(const InstrAspect &Aspect) const { + assert(Aspect.Type.isVector()); + // First legalize the vector element size, then legalize the number of + // lanes in the vector. + if (Aspect.Opcode < FirstOp || Aspect.Opcode > LastOp) + return {NotFound, Aspect.Type}; + const unsigned OpcodeIdx = Aspect.Opcode - FirstOp; + const unsigned TypeIdx = Aspect.Idx; + if (TypeIdx >= ScalarInVectorActions[OpcodeIdx].size()) + return {NotFound, Aspect.Type}; + const SizeAndActionsVec &ElemSizeVec = + ScalarInVectorActions[OpcodeIdx][TypeIdx]; + + LLT IntermediateType; + auto ElementSizeAndAction = + findAction(ElemSizeVec, Aspect.Type.getScalarSizeInBits()); + IntermediateType = + LLT::vector(Aspect.Type.getNumElements(), ElementSizeAndAction.first); + if (ElementSizeAndAction.second != Legal) + return {ElementSizeAndAction.second, IntermediateType}; + + auto i = NumElements2Actions[OpcodeIdx].find( + IntermediateType.getScalarSizeInBits()); + if (i == NumElements2Actions[OpcodeIdx].end()) { + return {NotFound, IntermediateType}; + } + const SizeAndActionsVec &NumElementsVec = (*i).second[TypeIdx]; + auto NumElementsAndAction = + findAction(NumElementsVec, IntermediateType.getNumElements()); + return {NumElementsAndAction.second, + LLT::vector(NumElementsAndAction.first, + IntermediateType.getScalarSizeInBits())}; } diff --git a/llvm/lib/Support/LowLevelType.cpp b/llvm/lib/Support/LowLevelType.cpp index 0ee3f1d0119..cb2187405d6 100644 --- a/llvm/lib/Support/LowLevelType.cpp +++ b/llvm/lib/Support/LowLevelType.cpp @@ -43,7 +43,7 @@ void LLT::print(raw_ostream &OS) const { assert(isScalar() && "unexpected type"); OS << "s" << getScalarSizeInBits(); } else - llvm_unreachable("trying to print an invalid type"); + OS << "LLT_invalid"; } const constexpr LLT::BitFieldInfo LLT::ScalarSizeFieldInfo; diff --git a/llvm/lib/Target/AArch64/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/AArch64LegalizerInfo.cpp index 2d45be37ca7..3a456255224 100644 --- a/llvm/lib/Target/AArch64/AArch64LegalizerInfo.cpp +++ b/llvm/lib/Target/AArch64/AArch64LegalizerInfo.cpp @@ -23,6 +23,110 @@ using namespace llvm; +/// FIXME: The following static functions are SizeChangeStrategy functions +/// that are meant to temporarily mimic the behaviour of the old legalization +/// based on doubling/halving non-legal types as closely as possible. This is +/// not entirly possible as only legalizing the types that are exactly a power +/// of 2 times the size of the legal types would require specifying all those +/// sizes explicitly. +/// In practice, not specifying those isn't a problem, and the below functions +/// should disappear quickly as we add support for legalizing non-power-of-2 +/// sized types further. +static void +addAndInterleaveWithUnsupported(LegalizerInfo::SizeAndActionsVec &result, + const LegalizerInfo::SizeAndActionsVec &v) { + for (unsigned i = 0; i < v.size(); ++i) { + result.push_back(v[i]); + if (i + 1 < v[i].first && i + 1 < v.size() && + v[i + 1].first != v[i].first + 1) + result.push_back({v[i].first + 1, LegalizerInfo::Unsupported}); + } +} + +static LegalizerInfo::SizeAndActionsVec +widen_1_narrow_128_ToLargest(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 2); + LegalizerInfo::SizeAndActionsVec result = {{1, LegalizerInfo::WidenScalar}, + {2, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + assert(Largest + 1 < 128); + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + result.push_back({128, LegalizerInfo::NarrowScalar}); + result.push_back({129, LegalizerInfo::Unsupported}); + return result; +} + +static LegalizerInfo::SizeAndActionsVec +widen_16(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 17); + LegalizerInfo::SizeAndActionsVec result = {{1, LegalizerInfo::Unsupported}, + {16, LegalizerInfo::WidenScalar}, + {17, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + return result; +} + +static LegalizerInfo::SizeAndActionsVec +widen_1_8(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 9); + LegalizerInfo::SizeAndActionsVec result = { + {1, LegalizerInfo::WidenScalar}, {2, LegalizerInfo::Unsupported}, + {8, LegalizerInfo::WidenScalar}, {9, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + return result; +} + +static LegalizerInfo::SizeAndActionsVec +widen_1_8_16(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 17); + LegalizerInfo::SizeAndActionsVec result = { + {1, LegalizerInfo::WidenScalar}, {2, LegalizerInfo::Unsupported}, + {8, LegalizerInfo::WidenScalar}, {9, LegalizerInfo::Unsupported}, + {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + return result; +} + +static LegalizerInfo::SizeAndActionsVec +widen_1_8_16_narrowToLargest(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 17); + LegalizerInfo::SizeAndActionsVec result = { + {1, LegalizerInfo::WidenScalar}, {2, LegalizerInfo::Unsupported}, + {8, LegalizerInfo::WidenScalar}, {9, LegalizerInfo::Unsupported}, + {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::NarrowScalar}); + return result; +} + +static LegalizerInfo::SizeAndActionsVec +widen_1_8_16_32(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 33); + LegalizerInfo::SizeAndActionsVec result = { + {1, LegalizerInfo::WidenScalar}, {2, LegalizerInfo::Unsupported}, + {8, LegalizerInfo::WidenScalar}, {9, LegalizerInfo::Unsupported}, + {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported}, + {32, LegalizerInfo::WidenScalar}, {33, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + return result; +} + AArch64LegalizerInfo::AArch64LegalizerInfo() { using namespace TargetOpcode; const LLT p0 = LLT::pointer(0, 64); @@ -42,8 +146,7 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { for (auto Ty : {s16, s32, s64, p0}) setAction({G_PHI, Ty}, Legal); - for (auto Ty : {s1, s8}) - setAction({G_PHI, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(G_PHI, 0, widen_1_8); for (auto Ty : { s32, s64 }) setAction({G_BSWAP, Ty}, Legal); @@ -54,15 +157,15 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { for (auto Ty : {s32, s64, v2s32, v4s32, v2s64}) setAction({BinOp, Ty}, Legal); - for (auto Ty : {s1, s8, s16}) - setAction({BinOp, Ty}, WidenScalar); + if (BinOp != G_ADD) + setLegalizeScalarToDifferentSizeStrategy(BinOp, 0, + widen_1_8_16_narrowToLargest); } setAction({G_GEP, p0}, Legal); setAction({G_GEP, 1, s64}, Legal); - for (auto Ty : {s1, s8, s16, s32}) - setAction({G_GEP, 1, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(G_GEP, 1, widen_1_8_16_32); setAction({G_PTR_MASK, p0}, Legal); @@ -70,16 +173,17 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { for (auto Ty : {s32, s64}) setAction({BinOp, Ty}, Legal); - for (auto Ty : {s1, s8, s16}) - setAction({BinOp, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(BinOp, 0, widen_1_8_16); } for (unsigned BinOp : {G_SREM, G_UREM}) for (auto Ty : { s1, s8, s16, s32, s64 }) setAction({BinOp, Ty}, Lower); - for (unsigned Op : {G_SMULO, G_UMULO}) - setAction({Op, s64}, Lower); + for (unsigned Op : {G_SMULO, G_UMULO}) { + setAction({Op, 0, s64}, Lower); + setAction({Op, 1, s1}, Legal); + } for (unsigned Op : {G_UADDE, G_USUBE, G_SADDO, G_SSUBO, G_SMULH, G_UMULH}) { for (auto Ty : { s32, s64 }) @@ -101,8 +205,9 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { setAction({G_INSERT, Ty}, Legal); setAction({G_INSERT, 1, Ty}, Legal); } + setLegalizeScalarToDifferentSizeStrategy(G_INSERT, 0, + widen_1_8_16_narrowToLargest); for (auto Ty : {s1, s8, s16}) { - setAction({G_INSERT, Ty}, WidenScalar); setAction({G_INSERT, 1, Ty}, Legal); // FIXME: Can't widen the sources because that violates the constraints on // G_INSERT (It seems entirely reasonable that inputs shouldn't overlap). @@ -118,7 +223,8 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { for (auto Ty : {s8, s16, s32, s64, p0, v2s32}) setAction({MemOp, Ty}, Legal); - setAction({MemOp, s1}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(MemOp, 0, + widen_1_narrow_128_ToLargest); // And everything's fine in addrspace 0. setAction({MemOp, 1, p0}, Legal); @@ -132,20 +238,16 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { setAction({G_CONSTANT, p0}, Legal); - for (auto Ty : {s1, s8, s16}) - setAction({TargetOpcode::G_CONSTANT, Ty}, WidenScalar); - - setAction({TargetOpcode::G_FCONSTANT, s16}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(G_CONSTANT, 0, widen_1_8_16); + setLegalizeScalarToDifferentSizeStrategy(G_FCONSTANT, 0, widen_16); setAction({G_ICMP, 1, s32}, Legal); setAction({G_ICMP, 1, s64}, Legal); setAction({G_ICMP, 1, p0}, Legal); - for (auto Ty : {s1, s8, s16}) { - setAction({G_ICMP, Ty}, WidenScalar); - setAction({G_FCMP, Ty}, WidenScalar); - setAction({G_ICMP, 1, Ty}, WidenScalar); - } + setLegalizeScalarToDifferentSizeStrategy(G_ICMP, 0, widen_1_8_16); + setLegalizeScalarToDifferentSizeStrategy(G_FCMP, 0, widen_1_8_16); + setLegalizeScalarToDifferentSizeStrategy(G_ICMP, 1, widen_1_8_16); setAction({G_ICMP, s32}, Legal); setAction({G_FCMP, s32}, Legal); @@ -159,12 +261,6 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { setAction({G_ANYEXT, Ty}, Legal); } - for (auto Ty : { s1, s8, s16, s32 }) { - setAction({G_ZEXT, 1, Ty}, Legal); - setAction({G_SEXT, 1, Ty}, Legal); - setAction({G_ANYEXT, 1, Ty}, Legal); - } - // FP conversions for (auto Ty : { s16, s32 }) { setAction({G_FPTRUNC, Ty}, Legal); @@ -176,12 +272,6 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { setAction({G_FPEXT, Ty}, Legal); } - for (auto Ty : { s1, s8, s16, s32 }) - setAction({G_TRUNC, Ty}, Legal); - - for (auto Ty : { s8, s16, s32, s64 }) - setAction({G_TRUNC, 1, Ty}, Legal); - // Conversions for (auto Ty : { s32, s64 }) { setAction({G_FPTOSI, 0, Ty}, Legal); @@ -189,12 +279,10 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { setAction({G_SITOFP, 1, Ty}, Legal); setAction({G_UITOFP, 1, Ty}, Legal); } - for (auto Ty : { s1, s8, s16 }) { - setAction({G_FPTOSI, 0, Ty}, WidenScalar); - setAction({G_FPTOUI, 0, Ty}, WidenScalar); - setAction({G_SITOFP, 1, Ty}, WidenScalar); - setAction({G_UITOFP, 1, Ty}, WidenScalar); - } + setLegalizeScalarToDifferentSizeStrategy(G_FPTOSI, 0, widen_1_8_16); + setLegalizeScalarToDifferentSizeStrategy(G_FPTOUI, 0, widen_1_8_16); + setLegalizeScalarToDifferentSizeStrategy(G_SITOFP, 1, widen_1_8_16); + setLegalizeScalarToDifferentSizeStrategy(G_UITOFP, 1, widen_1_8_16); for (auto Ty : { s32, s64 }) { setAction({G_FPTOSI, 1, Ty}, Legal); @@ -209,8 +297,7 @@ AArch64LegalizerInfo::AArch64LegalizerInfo() { setAction({G_BRINDIRECT, p0}, Legal); // Select - for (auto Ty : {s1, s8, s16}) - setAction({G_SELECT, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(G_SELECT, 0, widen_1_8_16); for (auto Ty : {s32, s64, p0}) setAction({G_SELECT, Ty}, Legal); diff --git a/llvm/lib/Target/ARM/ARMLegalizerInfo.cpp b/llvm/lib/Target/ARM/ARMLegalizerInfo.cpp index 309430b0e9c..34186dede0d 100644 --- a/llvm/lib/Target/ARM/ARMLegalizerInfo.cpp +++ b/llvm/lib/Target/ARM/ARMLegalizerInfo.cpp @@ -24,6 +24,54 @@ using namespace llvm; +/// FIXME: The following static functions are SizeChangeStrategy functions +/// that are meant to temporarily mimic the behaviour of the old legalization +/// based on doubling/halving non-legal types as closely as possible. This is +/// not entirly possible as only legalizing the types that are exactly a power +/// of 2 times the size of the legal types would require specifying all those +/// sizes explicitly. +/// In practice, not specifying those isn't a problem, and the below functions +/// should disappear quickly as we add support for legalizing non-power-of-2 +/// sized types further. +static void +addAndInterleaveWithUnsupported(LegalizerInfo::SizeAndActionsVec &result, + const LegalizerInfo::SizeAndActionsVec &v) { + for (unsigned i = 0; i < v.size(); ++i) { + result.push_back(v[i]); + if (i + 1 < v[i].first && i + 1 < v.size() && + v[i + 1].first != v[i].first + 1) + result.push_back({v[i].first + 1, LegalizerInfo::Unsupported}); + } +} + +static LegalizerInfo::SizeAndActionsVec +widen_8_16(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 17); + LegalizerInfo::SizeAndActionsVec result = { + {1, LegalizerInfo::Unsupported}, + {8, LegalizerInfo::WidenScalar}, {9, LegalizerInfo::Unsupported}, + {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + return result; +} + +static LegalizerInfo::SizeAndActionsVec +widen_1_8_16(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 17); + LegalizerInfo::SizeAndActionsVec result = { + {1, LegalizerInfo::WidenScalar}, {2, LegalizerInfo::Unsupported}, + {8, LegalizerInfo::WidenScalar}, {9, LegalizerInfo::Unsupported}, + {16, LegalizerInfo::WidenScalar}, {17, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + return result; +} + static bool AEABI(const ARMSubtarget &ST) { return ST.isTargetAEABI() || ST.isTargetGNUAEABI() || ST.isTargetMuslAEABI(); } @@ -49,14 +97,15 @@ ARMLegalizerInfo::ARMLegalizerInfo(const ARMSubtarget &ST) { } for (unsigned Op : {G_ADD, G_SUB, G_MUL, G_AND, G_OR, G_XOR}) { - for (auto Ty : {s1, s8, s16}) - setAction({Op, Ty}, WidenScalar); + if (Op != G_ADD) + setLegalizeScalarToDifferentSizeStrategy( + Op, 0, widenToLargerTypesUnsupportedOtherwise); setAction({Op, s32}, Legal); } for (unsigned Op : {G_SDIV, G_UDIV}) { - for (auto Ty : {s8, s16}) - setAction({Op, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(Op, 0, + widenToLargerTypesUnsupportedOtherwise); if (ST.hasDivideInARMMode()) setAction({Op, s32}, Legal); else @@ -64,8 +113,7 @@ ARMLegalizerInfo::ARMLegalizerInfo(const ARMSubtarget &ST) { } for (unsigned Op : {G_SREM, G_UREM}) { - for (auto Ty : {s8, s16}) - setAction({Op, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(Op, 0, widen_8_16); if (ST.hasDivideInARMMode()) setAction({Op, s32}, Lower); else if (AEABI(ST)) @@ -74,10 +122,8 @@ ARMLegalizerInfo::ARMLegalizerInfo(const ARMSubtarget &ST) { setAction({Op, s32}, Libcall); } - for (unsigned Op : {G_SEXT, G_ZEXT}) { + for (unsigned Op : {G_SEXT, G_ZEXT, G_ANYEXT}) { setAction({Op, s32}, Legal); - for (auto Ty : {s1, s8, s16}) - setAction({Op, 1, Ty}, Legal); } for (unsigned Op : {G_ASHR, G_LSHR, G_SHL}) @@ -93,12 +139,11 @@ ARMLegalizerInfo::ARMLegalizerInfo(const ARMSubtarget &ST) { setAction({G_BRCOND, s1}, Legal); setAction({G_CONSTANT, s32}, Legal); - for (auto Ty : {s1, s8, s16}) - setAction({G_CONSTANT, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(G_CONSTANT, 0, widen_1_8_16); setAction({G_ICMP, s1}, Legal); - for (auto Ty : {s8, s16}) - setAction({G_ICMP, 1, Ty}, WidenScalar); + setLegalizeScalarToDifferentSizeStrategy(G_ICMP, 1, + widenToLargerTypesUnsupportedOtherwise); for (auto Ty : {s32, p0}) setAction({G_ICMP, 1, Ty}, Legal); diff --git a/llvm/lib/Target/X86/X86LegalizerInfo.cpp b/llvm/lib/Target/X86/X86LegalizerInfo.cpp index 98b4863134e..b1438bf7bc0 100644 --- a/llvm/lib/Target/X86/X86LegalizerInfo.cpp +++ b/llvm/lib/Target/X86/X86LegalizerInfo.cpp @@ -22,6 +22,38 @@ using namespace llvm; using namespace TargetOpcode; +/// FIXME: The following static functions are SizeChangeStrategy functions +/// that are meant to temporarily mimic the behaviour of the old legalization +/// based on doubling/halving non-legal types as closely as possible. This is +/// not entirly possible as only legalizing the types that are exactly a power +/// of 2 times the size of the legal types would require specifying all those +/// sizes explicitly. +/// In practice, not specifying those isn't a problem, and the below functions +/// should disappear quickly as we add support for legalizing non-power-of-2 +/// sized types further. +static void +addAndInterleaveWithUnsupported(LegalizerInfo::SizeAndActionsVec &result, + const LegalizerInfo::SizeAndActionsVec &v) { + for (unsigned i = 0; i < v.size(); ++i) { + result.push_back(v[i]); + if (i + 1 < v[i].first && i + 1 < v.size() && + v[i + 1].first != v[i].first + 1) + result.push_back({v[i].first + 1, LegalizerInfo::Unsupported}); + } +} + +static LegalizerInfo::SizeAndActionsVec +widen_1(const LegalizerInfo::SizeAndActionsVec &v) { + assert(v.size() >= 1); + assert(v[0].first > 1); + LegalizerInfo::SizeAndActionsVec result = {{1, LegalizerInfo::WidenScalar}, + {2, LegalizerInfo::Unsupported}}; + addAndInterleaveWithUnsupported(result, v); + auto Largest = result.back().first; + result.push_back({Largest + 1, LegalizerInfo::Unsupported}); + return result; +} + X86LegalizerInfo::X86LegalizerInfo(const X86Subtarget &STI, const X86TargetMachine &TM) : Subtarget(STI), TM(TM) { @@ -37,6 +69,17 @@ X86LegalizerInfo::X86LegalizerInfo(const X86Subtarget &STI, setLegalizerInfoAVX512DQ(); setLegalizerInfoAVX512BW(); + setLegalizeScalarToDifferentSizeStrategy(G_PHI, 0, widen_1); + for (unsigned BinOp : {G_SUB, G_MUL, G_AND, G_OR, G_XOR}) + setLegalizeScalarToDifferentSizeStrategy(BinOp, 0, widen_1); + for (unsigned MemOp : {G_LOAD, G_STORE}) + setLegalizeScalarToDifferentSizeStrategy(MemOp, 0, + narrowToSmallerAndWidenToSmallest); + setLegalizeScalarToDifferentSizeStrategy( + G_GEP, 1, widenToLargerTypesUnsupportedOtherwise); + setLegalizeScalarToDifferentSizeStrategy( + G_CONSTANT, 0, widenToLargerTypesAndNarrowToLargest); + computeTables(); } @@ -47,7 +90,6 @@ void X86LegalizerInfo::setLegalizerInfo32bit() { const LLT s8 = LLT::scalar(8); const LLT s16 = LLT::scalar(16); const LLT s32 = LLT::scalar(32); - const LLT s64 = LLT::scalar(64); for (auto Ty : {p0, s1, s8, s16, s32}) setAction({G_IMPLICIT_DEF, Ty}, Legal); @@ -55,15 +97,10 @@ void X86LegalizerInfo::setLegalizerInfo32bit() { for (auto Ty : {s8, s16, s32, p0}) setAction({G_PHI, Ty}, Legal); - setAction({G_PHI, s1}, WidenScalar); - - for (unsigned BinOp : {G_ADD, G_SUB, G_MUL, G_AND, G_OR, G_XOR}) { + for (unsigned BinOp : {G_ADD, G_SUB, G_MUL, G_AND, G_OR, G_XOR}) for (auto Ty : {s8, s16, s32}) setAction({BinOp, Ty}, Legal); - setAction({BinOp, s1}, WidenScalar); - } - for (unsigned Op : {G_UADDE}) { setAction({Op, s32}, Legal); setAction({Op, 1, s1}, Legal); @@ -73,7 +110,6 @@ void X86LegalizerInfo::setLegalizerInfo32bit() { for (auto Ty : {s8, s16, s32, p0}) setAction({MemOp, Ty}, Legal); - setAction({MemOp, s1}, WidenScalar); // And everything's fine in addrspace 0. setAction({MemOp, 1, p0}, Legal); } @@ -85,9 +121,6 @@ void X86LegalizerInfo::setLegalizerInfo32bit() { setAction({G_GEP, p0}, Legal); setAction({G_GEP, 1, s32}, Legal); - for (auto Ty : {s1, s8, s16}) - setAction({G_GEP, 1, Ty}, WidenScalar); - // Control-flow setAction({G_BRCOND, s1}, Legal); @@ -95,9 +128,6 @@ void X86LegalizerInfo::setLegalizerInfo32bit() { for (auto Ty : {s8, s16, s32, p0}) setAction({TargetOpcode::G_CONSTANT, Ty}, Legal); - setAction({TargetOpcode::G_CONSTANT, s1}, WidenScalar); - setAction({TargetOpcode::G_CONSTANT, s64}, NarrowScalar); - // Extensions for (auto Ty : {s8, s16, s32}) { setAction({G_ZEXT, Ty}, Legal); @@ -105,12 +135,6 @@ void X86LegalizerInfo::setLegalizerInfo32bit() { setAction({G_ANYEXT, Ty}, Legal); } - for (auto Ty : {s1, s8, s16}) { - setAction({G_ZEXT, 1, Ty}, Legal); - setAction({G_SEXT, 1, Ty}, Legal); - setAction({G_ANYEXT, 1, Ty}, Legal); - } - // Comparison setAction({G_ICMP, s1}, Legal); @@ -123,7 +147,6 @@ void X86LegalizerInfo::setLegalizerInfo64bit() { if (!Subtarget.is64Bit()) return; - const LLT s32 = LLT::scalar(32); const LLT s64 = LLT::scalar(64); setAction({G_IMPLICIT_DEF, s64}, Legal); @@ -145,7 +168,6 @@ void X86LegalizerInfo::setLegalizerInfo64bit() { // Extensions for (unsigned extOp : {G_ZEXT, G_SEXT, G_ANYEXT}) { setAction({extOp, s64}, Legal); - setAction({extOp, 1, s32}, Legal); } // Comparison |