llvm/lib/Target/AArch64/AArch64InstructionSelector.cpp

//===- AArch64InstructionSelector.cpp ----------------------------*- C++ -*-==//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
/// \file
/// This file implements the targeting of the InstructionSelector class for
/// AArch64.
/// \todo This should be generated by TableGen.
//===----------------------------------------------------------------------===//

#include "AArch64InstrInfo.h"
#include "AArch64MachineFunctionInfo.h"
#include "AArch64RegisterBankInfo.h"
#include "AArch64RegisterInfo.h"
#include "AArch64Subtarget.h"
#include "AArch64TargetMachine.h"
#include "MCTargetDesc/AArch64AddressingModes.h"
#include "llvm/ADT/Optional.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelectorImpl.h"
#include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
#include "llvm/CodeGen/GlobalISel/MIPatternMatch.h"
#include "llvm/CodeGen/GlobalISel/Utils.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineConstantPool.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/IR/Type.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"

#define DEBUG_TYPE "aarch64-isel"

using namespace llvm;

namespace {

#define GET_GLOBALISEL_PREDICATE_BITSET
#include "AArch64GenGlobalISel.inc"
#undef GET_GLOBALISEL_PREDICATE_BITSET

class AArch64InstructionSelector : public InstructionSelector {
public:
  AArch64InstructionSelector(const AArch64TargetMachine &TM,
                             const AArch64Subtarget &STI,
                             const AArch64RegisterBankInfo &RBI);

  bool select(MachineInstr &I, CodeGenCoverage &CoverageInfo) const override;
  static const char *getName() { return DEBUG_TYPE; }

private:
  /// tblgen-erated 'select' implementation, used as the initial selector for
  /// the patterns that don't require complex C++.
  bool selectImpl(MachineInstr &I, CodeGenCoverage &CoverageInfo) const;

  // A lowering phase that runs before any selection attempts.

  void preISelLower(MachineInstr &I) const;

  // An early selection function that runs before the selectImpl() call.
  bool earlySelect(MachineInstr &I) const;

  bool earlySelectSHL(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool earlySelectLoad(MachineInstr &I, MachineRegisterInfo &MRI) const;

  /// Eliminate same-sized cross-bank copies into stores before selectImpl().
  void contractCrossBankCopyIntoStore(MachineInstr &I,
                                      MachineRegisterInfo &MRI) const;

  bool selectVaStartAAPCS(MachineInstr &I, MachineFunction &MF,
                          MachineRegisterInfo &MRI) const;
  bool selectVaStartDarwin(MachineInstr &I, MachineFunction &MF,
                           MachineRegisterInfo &MRI) const;

  bool selectCompareBranch(MachineInstr &I, MachineFunction &MF,
                           MachineRegisterInfo &MRI) const;

  bool selectVectorASHR(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectVectorSHL(MachineInstr &I, MachineRegisterInfo &MRI) const;

  // Helper to generate an equivalent of scalar_to_vector into a new register,
  // returned via 'Dst'.
  MachineInstr *emitScalarToVector(unsigned EltSize,
                                   const TargetRegisterClass *DstRC,
                                   Register Scalar,
                                   MachineIRBuilder &MIRBuilder) const;

  /// Emit a lane insert into \p DstReg, or a new vector register if None is
  /// provided.
  ///
  /// The lane inserted into is defined by \p LaneIdx. The vector source
  /// register is given by \p SrcReg. The register containing the element is
  /// given by \p EltReg.
  MachineInstr *emitLaneInsert(Optional<Register> DstReg, Register SrcReg,
                               Register EltReg, unsigned LaneIdx,
                               const RegisterBank &RB,
                               MachineIRBuilder &MIRBuilder) const;
  bool selectInsertElt(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectBuildVector(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectMergeValues(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectUnmergeValues(MachineInstr &I, MachineRegisterInfo &MRI) const;

  void collectShuffleMaskIndices(MachineInstr &I, MachineRegisterInfo &MRI,
                                 SmallVectorImpl<Optional<int>> &Idxs) const;
  bool selectShuffleVector(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectExtractElt(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectConcatVectors(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectSplitVectorUnmerge(MachineInstr &I,
                                MachineRegisterInfo &MRI) const;
  bool selectIntrinsicWithSideEffects(MachineInstr &I,
                                      MachineRegisterInfo &MRI) const;
  bool selectIntrinsic(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectVectorICmp(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectIntrinsicTrunc(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectIntrinsicRound(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectJumpTable(MachineInstr &I, MachineRegisterInfo &MRI) const;
  bool selectBrJT(MachineInstr &I, MachineRegisterInfo &MRI) const;

  unsigned emitConstantPoolEntry(Constant *CPVal, MachineFunction &MF) const;
  MachineInstr *emitLoadFromConstantPool(Constant *CPVal,
                                         MachineIRBuilder &MIRBuilder) const;

  // Emit a vector concat operation.
  MachineInstr *emitVectorConcat(Optional<Register> Dst, Register Op1,
                                 Register Op2,
                                 MachineIRBuilder &MIRBuilder) const;
  MachineInstr *emitIntegerCompare(MachineOperand &LHS, MachineOperand &RHS,
                                   MachineOperand &Predicate,
                                   MachineIRBuilder &MIRBuilder) const;
  MachineInstr *emitADD(Register DefReg, MachineOperand &LHS, MachineOperand &RHS,
                        MachineIRBuilder &MIRBuilder) const;
  MachineInstr *emitCMN(MachineOperand &LHS, MachineOperand &RHS,
                        MachineIRBuilder &MIRBuilder) const;
  MachineInstr *emitTST(const Register &LHS, const Register &RHS,
                        MachineIRBuilder &MIRBuilder) const;
  MachineInstr *emitExtractVectorElt(Optional<Register> DstReg,
                                     const RegisterBank &DstRB, LLT ScalarTy,
                                     Register VecReg, unsigned LaneIdx,
                                     MachineIRBuilder &MIRBuilder) const;

  /// Helper function for selecting G_FCONSTANT. If the G_FCONSTANT can be
  /// materialized using a FMOV instruction, then update MI and return it.
  /// Otherwise, do nothing and return a nullptr.
  MachineInstr *emitFMovForFConstant(MachineInstr &MI,
                                     MachineRegisterInfo &MRI) const;

  /// Emit a CSet for a compare.
  MachineInstr *emitCSetForICMP(Register DefReg, unsigned Pred,
                                MachineIRBuilder &MIRBuilder) const;

  // Equivalent to the i32shift_a and friends from AArch64InstrInfo.td.
  // We use these manually instead of using the importer since it doesn't
  // support SDNodeXForm.
  ComplexRendererFns selectShiftA_32(const MachineOperand &Root) const;
  ComplexRendererFns selectShiftB_32(const MachineOperand &Root) const;
  ComplexRendererFns selectShiftA_64(const MachineOperand &Root) const;
  ComplexRendererFns selectShiftB_64(const MachineOperand &Root) const;

  ComplexRendererFns select12BitValueWithLeftShift(uint64_t Immed) const;
  ComplexRendererFns selectArithImmed(MachineOperand &Root) const;
  ComplexRendererFns selectNegArithImmed(MachineOperand &Root) const;

  ComplexRendererFns selectAddrModeUnscaled(MachineOperand &Root,
                                            unsigned Size) const;

  ComplexRendererFns selectAddrModeUnscaled8(MachineOperand &Root) const {
    return selectAddrModeUnscaled(Root, 1);
  }
  ComplexRendererFns selectAddrModeUnscaled16(MachineOperand &Root) const {
    return selectAddrModeUnscaled(Root, 2);
  }
  ComplexRendererFns selectAddrModeUnscaled32(MachineOperand &Root) const {
    return selectAddrModeUnscaled(Root, 4);
  }
  ComplexRendererFns selectAddrModeUnscaled64(MachineOperand &Root) const {
    return selectAddrModeUnscaled(Root, 8);
  }
  ComplexRendererFns selectAddrModeUnscaled128(MachineOperand &Root) const {
    return selectAddrModeUnscaled(Root, 16);
  }

  ComplexRendererFns selectAddrModeIndexed(MachineOperand &Root,
                                           unsigned Size) const;
  template <int Width>
  ComplexRendererFns selectAddrModeIndexed(MachineOperand &Root) const {
    return selectAddrModeIndexed(Root, Width / 8);
  }

  bool isWorthFoldingIntoExtendedReg(MachineInstr &MI,
                                     const MachineRegisterInfo &MRI) const;
  ComplexRendererFns
  selectAddrModeShiftedExtendXReg(MachineOperand &Root,
                                  unsigned SizeInBytes) const;
  ComplexRendererFns selectAddrModeRegisterOffset(MachineOperand &Root) const;
  ComplexRendererFns selectAddrModeXRO(MachineOperand &Root,
                                       unsigned SizeInBytes) const;

  void renderTruncImm(MachineInstrBuilder &MIB, const MachineInstr &MI) const;

  // Materialize a GlobalValue or BlockAddress using a movz+movk sequence.
  void materializeLargeCMVal(MachineInstr &I, const Value *V,
                             unsigned OpFlags) const;

  // Optimization methods.
  bool tryOptVectorShuffle(MachineInstr &I) const;
  bool tryOptVectorDup(MachineInstr &MI) const;
  bool tryOptSelect(MachineInstr &MI) const;
  MachineInstr *tryFoldIntegerCompare(MachineOperand &LHS, MachineOperand &RHS,
                                      MachineOperand &Predicate,
                                      MachineIRBuilder &MIRBuilder) const;

  const AArch64TargetMachine &TM;
  const AArch64Subtarget &STI;
  const AArch64InstrInfo &TII;
  const AArch64RegisterInfo &TRI;
  const AArch64RegisterBankInfo &RBI;

#define GET_GLOBALISEL_PREDICATES_DECL
#include "AArch64GenGlobalISel.inc"
#undef GET_GLOBALISEL_PREDICATES_DECL

// We declare the temporaries used by selectImpl() in the class to minimize the
// cost of constructing placeholder values.
#define GET_GLOBALISEL_TEMPORARIES_DECL
#include "AArch64GenGlobalISel.inc"
#undef GET_GLOBALISEL_TEMPORARIES_DECL
};

} // end anonymous namespace

#define GET_GLOBALISEL_IMPL
#include "AArch64GenGlobalISel.inc"
#undef GET_GLOBALISEL_IMPL

AArch64InstructionSelector::AArch64InstructionSelector(
    const AArch64TargetMachine &TM, const AArch64Subtarget &STI,
    const AArch64RegisterBankInfo &RBI)
    : InstructionSelector(), TM(TM), STI(STI), TII(*STI.getInstrInfo()),
      TRI(*STI.getRegisterInfo()), RBI(RBI),
#define GET_GLOBALISEL_PREDICATES_INIT
#include "AArch64GenGlobalISel.inc"
#undef GET_GLOBALISEL_PREDICATES_INIT
#define GET_GLOBALISEL_TEMPORARIES_INIT
#include "AArch64GenGlobalISel.inc"
#undef GET_GLOBALISEL_TEMPORARIES_INIT
{
}

// FIXME: This should be target-independent, inferred from the types declared
// for each class in the bank.
static const TargetRegisterClass *
getRegClassForTypeOnBank(LLT Ty, const RegisterBank &RB,
                         const RegisterBankInfo &RBI,
                         bool GetAllRegSet = false) {
  if (RB.getID() == AArch64::GPRRegBankID) {
    if (Ty.getSizeInBits() <= 32)
      return GetAllRegSet ? &AArch64::GPR32allRegClass
                          : &AArch64::GPR32RegClass;
    if (Ty.getSizeInBits() == 64)
      return GetAllRegSet ? &AArch64::GPR64allRegClass
                          : &AArch64::GPR64RegClass;
    return nullptr;
  }

  if (RB.getID() == AArch64::FPRRegBankID) {
    if (Ty.getSizeInBits() <= 16)
      return &AArch64::FPR16RegClass;
    if (Ty.getSizeInBits() == 32)
      return &AArch64::FPR32RegClass;
    if (Ty.getSizeInBits() == 64)
      return &AArch64::FPR64RegClass;
    if (Ty.getSizeInBits() == 128)
      return &AArch64::FPR128RegClass;
    return nullptr;
  }

  return nullptr;
}

/// Given a register bank, and size in bits, return the smallest register class
/// that can represent that combination.
static const TargetRegisterClass *
getMinClassForRegBank(const RegisterBank &RB, unsigned SizeInBits,
                      bool GetAllRegSet = false) {
  unsigned RegBankID = RB.getID();

  if (RegBankID == AArch64::GPRRegBankID) {
    if (SizeInBits <= 32)
      return GetAllRegSet ? &AArch64::GPR32allRegClass
                          : &AArch64::GPR32RegClass;
    if (SizeInBits == 64)
      return GetAllRegSet ? &AArch64::GPR64allRegClass
                          : &AArch64::GPR64RegClass;
  }

  if (RegBankID == AArch64::FPRRegBankID) {
    switch (SizeInBits) {
    default:
      return nullptr;
    case 8:
      return &AArch64::FPR8RegClass;
    case 16:
      return &AArch64::FPR16RegClass;
    case 32:
      return &AArch64::FPR32RegClass;
    case 64:
      return &AArch64::FPR64RegClass;
    case 128:
      return &AArch64::FPR128RegClass;
    }
  }

  return nullptr;
}

/// Returns the correct subregister to use for a given register class.
static bool getSubRegForClass(const TargetRegisterClass *RC,
                              const TargetRegisterInfo &TRI, unsigned &SubReg) {
  switch (TRI.getRegSizeInBits(*RC)) {
  case 8:
    SubReg = AArch64::bsub;
    break;
  case 16:
    SubReg = AArch64::hsub;
    break;
  case 32:
    if (RC == &AArch64::GPR32RegClass)
      SubReg = AArch64::sub_32;
    else
      SubReg = AArch64::ssub;
    break;
  case 64:
    SubReg = AArch64::dsub;
    break;
  default:
    LLVM_DEBUG(
        dbgs() << "Couldn't find appropriate subregister for register class.");
    return false;
  }

  return true;
}

/// Check whether \p I is a currently unsupported binary operation:
/// - it has an unsized type
/// - an operand is not a vreg
/// - all operands are not in the same bank
/// These are checks that should someday live in the verifier, but right now,
/// these are mostly limitations of the aarch64 selector.
static bool unsupportedBinOp(const MachineInstr &I,
                             const AArch64RegisterBankInfo &RBI,
                             const MachineRegisterInfo &MRI,
                             const AArch64RegisterInfo &TRI) {
  LLT Ty = MRI.getType(I.getOperand(0).getReg());
  if (!Ty.isValid()) {
    LLVM_DEBUG(dbgs() << "Generic binop register should be typed\n");
    return true;
  }

  const RegisterBank *PrevOpBank = nullptr;
  for (auto &MO : I.operands()) {
    // FIXME: Support non-register operands.
    if (!MO.isReg()) {
      LLVM_DEBUG(dbgs() << "Generic inst non-reg operands are unsupported\n");
      return true;
    }

    // FIXME: Can generic operations have physical registers operands? If
    // so, this will need to be taught about that, and we'll need to get the
    // bank out of the minimal class for the register.
    // Either way, this needs to be documented (and possibly verified).
    if (!Register::isVirtualRegister(MO.getReg())) {
      LLVM_DEBUG(dbgs() << "Generic inst has physical register operand\n");
      return true;
    }

    const RegisterBank *OpBank = RBI.getRegBank(MO.getReg(), MRI, TRI);
    if (!OpBank) {
      LLVM_DEBUG(dbgs() << "Generic register has no bank or class\n");
      return true;
    }

    if (PrevOpBank && OpBank != PrevOpBank) {
      LLVM_DEBUG(dbgs() << "Generic inst operands have different banks\n");
      return true;
    }
    PrevOpBank = OpBank;
  }
  return false;
}

/// Select the AArch64 opcode for the basic binary operation \p GenericOpc
/// (such as G_OR or G_SDIV), appropriate for the register bank \p RegBankID
/// and of size \p OpSize.
/// \returns \p GenericOpc if the combination is unsupported.
static unsigned selectBinaryOp(unsigned GenericOpc, unsigned RegBankID,
                               unsigned OpSize) {
  switch (RegBankID) {
  case AArch64::GPRRegBankID:
    if (OpSize == 32) {
      switch (GenericOpc) {
      case TargetOpcode::G_SHL:
        return AArch64::LSLVWr;
      case TargetOpcode::G_LSHR:
        return AArch64::LSRVWr;
      case TargetOpcode::G_ASHR:
        return AArch64::ASRVWr;
      default:
        return GenericOpc;
      }
    } else if (OpSize == 64) {
      switch (GenericOpc) {
      case TargetOpcode::G_GEP:
        return AArch64::ADDXrr;
      case TargetOpcode::G_SHL:
        return AArch64::LSLVXr;
      case TargetOpcode::G_LSHR:
        return AArch64::LSRVXr;
      case TargetOpcode::G_ASHR:
        return AArch64::ASRVXr;
      default:
        return GenericOpc;
      }
    }
    break;
  case AArch64::FPRRegBankID:
    switch (OpSize) {
    case 32:
      switch (GenericOpc) {
      case TargetOpcode::G_FADD:
        return AArch64::FADDSrr;
      case TargetOpcode::G_FSUB:
        return AArch64::FSUBSrr;
      case TargetOpcode::G_FMUL:
        return AArch64::FMULSrr;
      case TargetOpcode::G_FDIV:
        return AArch64::FDIVSrr;
      default:
        return GenericOpc;
      }
    case 64:
      switch (GenericOpc) {
      case TargetOpcode::G_FADD:
        return AArch64::FADDDrr;
      case TargetOpcode::G_FSUB:
        return AArch64::FSUBDrr;
      case TargetOpcode::G_FMUL:
        return AArch64::FMULDrr;
      case TargetOpcode::G_FDIV:
        return AArch64::FDIVDrr;
      case TargetOpcode::G_OR:
        return AArch64::ORRv8i8;
      default:
        return GenericOpc;
      }
    }
    break;
  }
  return GenericOpc;
}

/// Select the AArch64 opcode for the G_LOAD or G_STORE operation \p GenericOpc,
/// appropriate for the (value) register bank \p RegBankID and of memory access
/// size \p OpSize.  This returns the variant with the base+unsigned-immediate
/// addressing mode (e.g., LDRXui).
/// \returns \p GenericOpc if the combination is unsupported.
static unsigned selectLoadStoreUIOp(unsigned GenericOpc, unsigned RegBankID,
                                    unsigned OpSize) {
  const bool isStore = GenericOpc == TargetOpcode::G_STORE;
  switch (RegBankID) {
  case AArch64::GPRRegBankID:
    switch (OpSize) {
    case 8:
      return isStore ? AArch64::STRBBui : AArch64::LDRBBui;
    case 16:
      return isStore ? AArch64::STRHHui : AArch64::LDRHHui;
    case 32:
      return isStore ? AArch64::STRWui : AArch64::LDRWui;
    case 64:
      return isStore ? AArch64::STRXui : AArch64::LDRXui;
    }
    break;
  case AArch64::FPRRegBankID:
    switch (OpSize) {
    case 8:
      return isStore ? AArch64::STRBui : AArch64::LDRBui;
    case 16:
      return isStore ? AArch64::STRHui : AArch64::LDRHui;
    case 32:
      return isStore ? AArch64::STRSui : AArch64::LDRSui;
    case 64:
      return isStore ? AArch64::STRDui : AArch64::LDRDui;
    }
    break;
  }
  return GenericOpc;
}

#ifndef NDEBUG
/// Helper function that verifies that we have a valid copy at the end of
/// selectCopy. Verifies that the source and dest have the expected sizes and
/// then returns true.
static bool isValidCopy(const MachineInstr &I, const RegisterBank &DstBank,
                        const MachineRegisterInfo &MRI,
                        const TargetRegisterInfo &TRI,
                        const RegisterBankInfo &RBI) {
  const unsigned DstReg = I.getOperand(0).getReg();
  const unsigned SrcReg = I.getOperand(1).getReg();
  const unsigned DstSize = RBI.getSizeInBits(DstReg, MRI, TRI);
  const unsigned SrcSize = RBI.getSizeInBits(SrcReg, MRI, TRI);

  // Make sure the size of the source and dest line up.
  assert(
      (DstSize == SrcSize ||
       // Copies are a mean to setup initial types, the number of
       // bits may not exactly match.
       (Register::isPhysicalRegister(SrcReg) && DstSize <= SrcSize) ||
       // Copies are a mean to copy bits around, as long as we are
       // on the same register class, that's fine. Otherwise, that
       // means we need some SUBREG_TO_REG or AND & co.
       (((DstSize + 31) / 32 == (SrcSize + 31) / 32) && DstSize > SrcSize)) &&
      "Copy with different width?!");

  // Check the size of the destination.
  assert((DstSize <= 64 || DstBank.getID() == AArch64::FPRRegBankID) &&
         "GPRs cannot get more than 64-bit width values");

  return true;
}
#endif

/// Helper function for selectCopy. Inserts a subregister copy from
/// \p *From to \p *To, linking it up to \p I.
///
/// e.g, given I = "Dst = COPY SrcReg", we'll transform that into
///
/// CopyReg (From class) = COPY SrcReg
/// SubRegCopy (To class) = COPY CopyReg:SubReg
/// Dst = COPY SubRegCopy
static bool selectSubregisterCopy(MachineInstr &I, MachineRegisterInfo &MRI,
                                  const RegisterBankInfo &RBI, unsigned SrcReg,
                                  const TargetRegisterClass *From,
                                  const TargetRegisterClass *To,
                                  unsigned SubReg) {
  MachineIRBuilder MIB(I);
  auto Copy = MIB.buildCopy({From}, {SrcReg});
  auto SubRegCopy = MIB.buildInstr(TargetOpcode::COPY, {To}, {})
                        .addReg(Copy.getReg(0), 0, SubReg);
  MachineOperand &RegOp = I.getOperand(1);
  RegOp.setReg(SubRegCopy.getReg(0));

  // It's possible that the destination register won't be constrained. Make
  // sure that happens.
  if (!Register::isPhysicalRegister(I.getOperand(0).getReg()))
    RBI.constrainGenericRegister(I.getOperand(0).getReg(), *To, MRI);

  return true;
}

/// Helper function to get the source and destination register classes for a
/// copy. Returns a std::pair containing the source register class for the
/// copy, and the destination register class for the copy. If a register class
/// cannot be determined, then it will be nullptr.
static std::pair<const TargetRegisterClass *, const TargetRegisterClass *>
getRegClassesForCopy(MachineInstr &I, const TargetInstrInfo &TII,
                     MachineRegisterInfo &MRI, const TargetRegisterInfo &TRI,
                     const RegisterBankInfo &RBI) {
  unsigned DstReg = I.getOperand(0).getReg();
  unsigned SrcReg = I.getOperand(1).getReg();
  const RegisterBank &DstRegBank = *RBI.getRegBank(DstReg, MRI, TRI);
  const RegisterBank &SrcRegBank = *RBI.getRegBank(SrcReg, MRI, TRI);
  unsigned DstSize = RBI.getSizeInBits(DstReg, MRI, TRI);
  unsigned SrcSize = RBI.getSizeInBits(SrcReg, MRI, TRI);

  // Special casing for cross-bank copies of s1s. We can technically represent
  // a 1-bit value with any size of register. The minimum size for a GPR is 32
  // bits. So, we need to put the FPR on 32 bits as well.
  //
  // FIXME: I'm not sure if this case holds true outside of copies. If it does,
  // then we can pull it into the helpers that get the appropriate class for a
  // register bank. Or make a new helper that carries along some constraint
  // information.
  if (SrcRegBank != DstRegBank && (DstSize == 1 && SrcSize == 1))
    SrcSize = DstSize = 32;

  return {getMinClassForRegBank(SrcRegBank, SrcSize, true),
          getMinClassForRegBank(DstRegBank, DstSize, true)};
}

static bool selectCopy(MachineInstr &I, const TargetInstrInfo &TII,
                       MachineRegisterInfo &MRI, const TargetRegisterInfo &TRI,
                       const RegisterBankInfo &RBI) {

  unsigned DstReg = I.getOperand(0).getReg();
  unsigned SrcReg = I.getOperand(1).getReg();
  const RegisterBank &DstRegBank = *RBI.getRegBank(DstReg, MRI, TRI);
  const RegisterBank &SrcRegBank = *RBI.getRegBank(SrcReg, MRI, TRI);

  // Find the correct register classes for the source and destination registers.
  const TargetRegisterClass *SrcRC;
  const TargetRegisterClass *DstRC;
  std::tie(SrcRC, DstRC) = getRegClassesForCopy(I, TII, MRI, TRI, RBI);

  if (!DstRC) {
    LLVM_DEBUG(dbgs() << "Unexpected dest size "
                      << RBI.getSizeInBits(DstReg, MRI, TRI) << '\n');
    return false;
  }

  // A couple helpers below, for making sure that the copy we produce is valid.

  // Set to true if we insert a SUBREG_TO_REG. If we do this, then we don't want
  // to verify that the src and dst are the same size, since that's handled by
  // the SUBREG_TO_REG.
  bool KnownValid = false;

  // Returns true, or asserts if something we don't expect happens. Instead of
  // returning true, we return isValidCopy() to ensure that we verify the
  // result.
  auto CheckCopy = [&]() {
    // If we have a bitcast or something, we can't have physical registers.
    assert((I.isCopy() ||
            (!Register::isPhysicalRegister(I.getOperand(0).getReg()) &&
             !Register::isPhysicalRegister(I.getOperand(1).getReg()))) &&
           "No phys reg on generic operator!");
    assert(KnownValid || isValidCopy(I, DstRegBank, MRI, TRI, RBI));
    (void)KnownValid;
    return true;
  };

  // Is this a copy? If so, then we may need to insert a subregister copy, or
  // a SUBREG_TO_REG.
  if (I.isCopy()) {
    // Yes. Check if there's anything to fix up.
    if (!SrcRC) {
      LLVM_DEBUG(dbgs() << "Couldn't determine source register class\n");
      return false;
    }

    // Is this a cross-bank copy?
    if (DstRegBank.getID() != SrcRegBank.getID()) {
      // If we're doing a cross-bank copy on different-sized registers, we need
      // to do a bit more work.
      unsigned SrcSize = TRI.getRegSizeInBits(*SrcRC);
      unsigned DstSize = TRI.getRegSizeInBits(*DstRC);

      if (SrcSize > DstSize) {
        // We're doing a cross-bank copy into a smaller register. We need a
        // subregister copy. First, get a register class that's on the same bank
        // as the destination, but the same size as the source.
        const TargetRegisterClass *SubregRC =
            getMinClassForRegBank(DstRegBank, SrcSize, true);
        assert(SubregRC && "Didn't get a register class for subreg?");

        // Get the appropriate subregister for the destination.
        unsigned SubReg = 0;
        if (!getSubRegForClass(DstRC, TRI, SubReg)) {
          LLVM_DEBUG(dbgs() << "Couldn't determine subregister for copy.\n");
          return false;
        }

        // Now, insert a subregister copy using the new register class.
        selectSubregisterCopy(I, MRI, RBI, SrcReg, SubregRC, DstRC, SubReg);
        return CheckCopy();
      }

      else if (DstRegBank.getID() == AArch64::GPRRegBankID && DstSize == 32 &&
               SrcSize == 16) {
        // Special case for FPR16 to GPR32.
        // FIXME: This can probably be generalized like the above case.
        unsigned PromoteReg =
            MRI.createVirtualRegister(&AArch64::FPR32RegClass);
        BuildMI(*I.getParent(), I, I.getDebugLoc(),
                TII.get(AArch64::SUBREG_TO_REG), PromoteReg)
            .addImm(0)
            .addUse(SrcReg)
            .addImm(AArch64::hsub);
        MachineOperand &RegOp = I.getOperand(1);
        RegOp.setReg(PromoteReg);

        // Promise that the copy is implicitly validated by the SUBREG_TO_REG.
        KnownValid = true;
      }
    }

    // If the destination is a physical register, then there's nothing to
    // change, so we're done.
    if (Register::isPhysicalRegister(DstReg))
      return CheckCopy();
  }

  // No need to constrain SrcReg. It will get constrained when we hit another
  // of its use or its defs. Copies do not have constraints.
  if (!RBI.constrainGenericRegister(DstReg, *DstRC, MRI)) {
    LLVM_DEBUG(dbgs() << "Failed to constrain " << TII.getName(I.getOpcode())
                      << " operand\n");
    return false;
  }
  I.setDesc(TII.get(AArch64::COPY));
  return CheckCopy();
}

static unsigned selectFPConvOpc(unsigned GenericOpc, LLT DstTy, LLT SrcTy) {
  if (!DstTy.isScalar() || !SrcTy.isScalar())
    return GenericOpc;

  const unsigned DstSize = DstTy.getSizeInBits();
  const unsigned SrcSize = SrcTy.getSizeInBits();

  switch (DstSize) {
  case 32:
    switch (SrcSize) {
    case 32:
      switch (GenericOpc) {
      case TargetOpcode::G_SITOFP:
        return AArch64::SCVTFUWSri;
      case TargetOpcode::G_UITOFP:
        return AArch64::UCVTFUWSri;
      case TargetOpcode::G_FPTOSI:
        return AArch64::FCVTZSUWSr;
      case TargetOpcode::G_FPTOUI:
        return AArch64::FCVTZUUWSr;
      default:
        return GenericOpc;
      }
    case 64:
      switch (GenericOpc) {
      case TargetOpcode::G_SITOFP:
        return AArch64::SCVTFUXSri;
      case TargetOpcode::G_UITOFP:
        return AArch64::UCVTFUXSri;
      case TargetOpcode::G_FPTOSI:
        return AArch64::FCVTZSUWDr;
      case TargetOpcode::G_FPTOUI:
        return AArch64::FCVTZUUWDr;
      default:
        return GenericOpc;
      }
    default:
      return GenericOpc;
    }
  case 64:
    switch (SrcSize) {
    case 32:
      switch (GenericOpc) {
      case TargetOpcode::G_SITOFP:
        return AArch64::SCVTFUWDri;
      case TargetOpcode::G_UITOFP:
        return AArch64::UCVTFUWDri;
      case TargetOpcode::G_FPTOSI:
        return AArch64::FCVTZSUXSr;
      case TargetOpcode::G_FPTOUI:
        return AArch64::FCVTZUUXSr;
      default:
        return GenericOpc;
      }
    case 64:
      switch (GenericOpc) {
      case TargetOpcode::G_SITOFP:
        return AArch64::SCVTFUXDri;
      case TargetOpcode::G_UITOFP:
        return AArch64::UCVTFUXDri;
      case TargetOpcode::G_FPTOSI:
        return AArch64::FCVTZSUXDr;
      case TargetOpcode::G_FPTOUI:
        return AArch64::FCVTZUUXDr;
      default:
        return GenericOpc;
      }
    default:
      return GenericOpc;
    }
  default:
    return GenericOpc;
  };
  return GenericOpc;
}

static unsigned selectSelectOpc(MachineInstr &I, MachineRegisterInfo &MRI,
                                const RegisterBankInfo &RBI) {
  const TargetRegisterInfo &TRI = *MRI.getTargetRegisterInfo();
  bool IsFP = (RBI.getRegBank(I.getOperand(0).getReg(), MRI, TRI)->getID() !=
               AArch64::GPRRegBankID);
  LLT Ty = MRI.getType(I.getOperand(0).getReg());
  if (Ty == LLT::scalar(32))
    return IsFP ? AArch64::FCSELSrrr : AArch64::CSELWr;
  else if (Ty == LLT::scalar(64) || Ty == LLT::pointer(0, 64))
    return IsFP ? AArch64::FCSELDrrr : AArch64::CSELXr;
  return 0;
}

/// Helper function to select the opcode for a G_FCMP.
static unsigned selectFCMPOpc(MachineInstr &I, MachineRegisterInfo &MRI) {
  // If this is a compare against +0.0, then we don't have to explicitly
  // materialize a constant.
  const ConstantFP *FPImm = getConstantFPVRegVal(I.getOperand(3).getReg(), MRI);
  bool ShouldUseImm = FPImm && (FPImm->isZero() && !FPImm->isNegative());
  unsigned OpSize = MRI.getType(I.getOperand(2).getReg()).getSizeInBits();
  if (OpSize != 32 && OpSize != 64)
    return 0;
  unsigned CmpOpcTbl[2][2] = {{AArch64::FCMPSrr, AArch64::FCMPDrr},
                              {AArch64::FCMPSri, AArch64::FCMPDri}};
  return CmpOpcTbl[ShouldUseImm][OpSize == 64];
}

/// Returns true if \p P is an unsigned integer comparison predicate.
static bool isUnsignedICMPPred(const CmpInst::Predicate P) {
  switch (P) {
  default:
    return false;
  case CmpInst::ICMP_UGT:
  case CmpInst::ICMP_UGE:
  case CmpInst::ICMP_ULT:
  case CmpInst::ICMP_ULE:
    return true;
  }
}

static AArch64CC::CondCode changeICMPPredToAArch64CC(CmpInst::Predicate P) {
  switch (P) {
  default:
    llvm_unreachable("Unknown condition code!");
  case CmpInst::ICMP_NE:
    return AArch64CC::NE;
  case CmpInst::ICMP_EQ:
    return AArch64CC::EQ;
  case CmpInst::ICMP_SGT:
    return AArch64CC::GT;
  case CmpInst::ICMP_SGE:
    return AArch64CC::GE;
  case CmpInst::ICMP_SLT:
    return AArch64CC::LT;
  case CmpInst::ICMP_SLE:
    return AArch64CC::LE;
  case CmpInst::ICMP_UGT:
    return AArch64CC::HI;
  case CmpInst::ICMP_UGE:
    return AArch64CC::HS;
  case CmpInst::ICMP_ULT:
    return AArch64CC::LO;
  case CmpInst::ICMP_ULE:
    return AArch64CC::LS;
  }
}

static void changeFCMPPredToAArch64CC(CmpInst::Predicate P,
                                      AArch64CC::CondCode &CondCode,
                                      AArch64CC::CondCode &CondCode2) {
  CondCode2 = AArch64CC::AL;
  switch (P) {
  default:
    llvm_unreachable("Unknown FP condition!");
  case CmpInst::FCMP_OEQ:
    CondCode = AArch64CC::EQ;
    break;
  case CmpInst::FCMP_OGT:
    CondCode = AArch64CC::GT;
    break;
  case CmpInst::FCMP_OGE:
    CondCode = AArch64CC::GE;
    break;
  case CmpInst::FCMP_OLT:
    CondCode = AArch64CC::MI;
    break;
  case CmpInst::FCMP_OLE:
    CondCode = AArch64CC::LS;
    break;
  case CmpInst::FCMP_ONE:
    CondCode = AArch64CC::MI;
    CondCode2 = AArch64CC::GT;
    break;
  case CmpInst::FCMP_ORD:
    CondCode = AArch64CC::VC;
    break;
  case CmpInst::FCMP_UNO:
    CondCode = AArch64CC::VS;
    break;
  case CmpInst::FCMP_UEQ:
    CondCode = AArch64CC::EQ;
    CondCode2 = AArch64CC::VS;
    break;
  case CmpInst::FCMP_UGT:
    CondCode = AArch64CC::HI;
    break;
  case CmpInst::FCMP_UGE:
    CondCode = AArch64CC::PL;
    break;
  case CmpInst::FCMP_ULT:
    CondCode = AArch64CC::LT;
    break;
  case CmpInst::FCMP_ULE:
    CondCode = AArch64CC::LE;
    break;
  case CmpInst::FCMP_UNE:
    CondCode = AArch64CC::NE;
    break;
  }
}

bool AArch64InstructionSelector::selectCompareBranch(
    MachineInstr &I, MachineFunction &MF, MachineRegisterInfo &MRI) const {

  const Register CondReg = I.getOperand(0).getReg();
  MachineBasicBlock *DestMBB = I.getOperand(1).getMBB();
  MachineInstr *CCMI = MRI.getVRegDef(CondReg);
  if (CCMI->getOpcode() == TargetOpcode::G_TRUNC)
    CCMI = MRI.getVRegDef(CCMI->getOperand(1).getReg());
  if (CCMI->getOpcode() != TargetOpcode::G_ICMP)
    return false;

  Register LHS = CCMI->getOperand(2).getReg();
  Register RHS = CCMI->getOperand(3).getReg();
  auto VRegAndVal = getConstantVRegValWithLookThrough(RHS, MRI);
  if (!VRegAndVal)
    std::swap(RHS, LHS);

  VRegAndVal = getConstantVRegValWithLookThrough(RHS, MRI);
  if (!VRegAndVal || VRegAndVal->Value != 0) {
    MachineIRBuilder MIB(I);
    // If we can't select a CBZ then emit a cmp + Bcc.
    if (!emitIntegerCompare(CCMI->getOperand(2), CCMI->getOperand(3),
                            CCMI->getOperand(1), MIB))
      return false;
    const AArch64CC::CondCode CC = changeICMPPredToAArch64CC(
        (CmpInst::Predicate)CCMI->getOperand(1).getPredicate());
    MIB.buildInstr(AArch64::Bcc, {}, {}).addImm(CC).addMBB(DestMBB);
    I.eraseFromParent();
    return true;
  }

  const RegisterBank &RB = *RBI.getRegBank(LHS, MRI, TRI);
  if (RB.getID() != AArch64::GPRRegBankID)
    return false;

  const auto Pred = (CmpInst::Predicate)CCMI->getOperand(1).getPredicate();
  if (Pred != CmpInst::ICMP_NE && Pred != CmpInst::ICMP_EQ)
    return false;

  const unsigned CmpWidth = MRI.getType(LHS).getSizeInBits();
  unsigned CBOpc = 0;
  if (CmpWidth <= 32)
    CBOpc = (Pred == CmpInst::ICMP_EQ ? AArch64::CBZW : AArch64::CBNZW);
  else if (CmpWidth == 64)
    CBOpc = (Pred == CmpInst::ICMP_EQ ? AArch64::CBZX : AArch64::CBNZX);
  else
    return false;

  BuildMI(*I.getParent(), I, I.getDebugLoc(), TII.get(CBOpc))
      .addUse(LHS)
      .addMBB(DestMBB)
      .constrainAllUses(TII, TRI, RBI);

  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectVectorSHL(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_SHL);
  Register DstReg = I.getOperand(0).getReg();
  const LLT Ty = MRI.getType(DstReg);
  Register Src1Reg = I.getOperand(1).getReg();
  Register Src2Reg = I.getOperand(2).getReg();

  if (!Ty.isVector())
    return false;

  unsigned Opc = 0;
  if (Ty == LLT::vector(4, 32)) {
    Opc = AArch64::USHLv4i32;
  } else if (Ty == LLT::vector(2, 32)) {
    Opc = AArch64::USHLv2i32;
  } else {
    LLVM_DEBUG(dbgs() << "Unhandled G_SHL type");
    return false;
  }

  MachineIRBuilder MIB(I);
  auto UShl = MIB.buildInstr(Opc, {DstReg}, {Src1Reg, Src2Reg});
  constrainSelectedInstRegOperands(*UShl, TII, TRI, RBI);
  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectVectorASHR(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_ASHR);
  Register DstReg = I.getOperand(0).getReg();
  const LLT Ty = MRI.getType(DstReg);
  Register Src1Reg = I.getOperand(1).getReg();
  Register Src2Reg = I.getOperand(2).getReg();

  if (!Ty.isVector())
    return false;

  // There is not a shift right register instruction, but the shift left
  // register instruction takes a signed value, where negative numbers specify a
  // right shift.

  unsigned Opc = 0;
  unsigned NegOpc = 0;
  const TargetRegisterClass *RC = nullptr;
  if (Ty == LLT::vector(4, 32)) {
    Opc = AArch64::SSHLv4i32;
    NegOpc = AArch64::NEGv4i32;
    RC = &AArch64::FPR128RegClass;
  } else if (Ty == LLT::vector(2, 32)) {
    Opc = AArch64::SSHLv2i32;
    NegOpc = AArch64::NEGv2i32;
    RC = &AArch64::FPR64RegClass;
  } else {
    LLVM_DEBUG(dbgs() << "Unhandled G_ASHR type");
    return false;
  }

  MachineIRBuilder MIB(I);
  auto Neg = MIB.buildInstr(NegOpc, {RC}, {Src2Reg});
  constrainSelectedInstRegOperands(*Neg, TII, TRI, RBI);
  auto SShl = MIB.buildInstr(Opc, {DstReg}, {Src1Reg, Neg});
  constrainSelectedInstRegOperands(*SShl, TII, TRI, RBI);
  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectVaStartAAPCS(
    MachineInstr &I, MachineFunction &MF, MachineRegisterInfo &MRI) const {
  return false;
}

bool AArch64InstructionSelector::selectVaStartDarwin(
    MachineInstr &I, MachineFunction &MF, MachineRegisterInfo &MRI) const {
  AArch64FunctionInfo *FuncInfo = MF.getInfo<AArch64FunctionInfo>();
  Register ListReg = I.getOperand(0).getReg();

  Register ArgsAddrReg = MRI.createVirtualRegister(&AArch64::GPR64RegClass);

  auto MIB =
      BuildMI(*I.getParent(), I, I.getDebugLoc(), TII.get(AArch64::ADDXri))
          .addDef(ArgsAddrReg)
          .addFrameIndex(FuncInfo->getVarArgsStackIndex())
          .addImm(0)
          .addImm(0);

  constrainSelectedInstRegOperands(*MIB, TII, TRI, RBI);

  MIB = BuildMI(*I.getParent(), I, I.getDebugLoc(), TII.get(AArch64::STRXui))
            .addUse(ArgsAddrReg)
            .addUse(ListReg)
            .addImm(0)
            .addMemOperand(*I.memoperands_begin());

  constrainSelectedInstRegOperands(*MIB, TII, TRI, RBI);
  I.eraseFromParent();
  return true;
}

void AArch64InstructionSelector::materializeLargeCMVal(
    MachineInstr &I, const Value *V, unsigned OpFlags) const {
  MachineBasicBlock &MBB = *I.getParent();
  MachineFunction &MF = *MBB.getParent();
  MachineRegisterInfo &MRI = MF.getRegInfo();
  MachineIRBuilder MIB(I);

  auto MovZ = MIB.buildInstr(AArch64::MOVZXi, {&AArch64::GPR64RegClass}, {});
  MovZ->addOperand(MF, I.getOperand(1));
  MovZ->getOperand(1).setTargetFlags(OpFlags | AArch64II::MO_G0 |
                                     AArch64II::MO_NC);
  MovZ->addOperand(MF, MachineOperand::CreateImm(0));
  constrainSelectedInstRegOperands(*MovZ, TII, TRI, RBI);

  auto BuildMovK = [&](Register SrcReg, unsigned char Flags, unsigned Offset,
                       Register ForceDstReg) {
    Register DstReg = ForceDstReg
                          ? ForceDstReg
                          : MRI.createVirtualRegister(&AArch64::GPR64RegClass);
    auto MovI = MIB.buildInstr(AArch64::MOVKXi).addDef(DstReg).addUse(SrcReg);
    if (auto *GV = dyn_cast<GlobalValue>(V)) {
      MovI->addOperand(MF, MachineOperand::CreateGA(
                               GV, MovZ->getOperand(1).getOffset(), Flags));
    } else {
      MovI->addOperand(
          MF, MachineOperand::CreateBA(cast<BlockAddress>(V),
                                       MovZ->getOperand(1).getOffset(), Flags));
    }
    MovI->addOperand(MF, MachineOperand::CreateImm(Offset));
    constrainSelectedInstRegOperands(*MovI, TII, TRI, RBI);
    return DstReg;
  };
  Register DstReg = BuildMovK(MovZ.getReg(0),
                              AArch64II::MO_G1 | AArch64II::MO_NC, 16, 0);
  DstReg = BuildMovK(DstReg, AArch64II::MO_G2 | AArch64II::MO_NC, 32, 0);
  BuildMovK(DstReg, AArch64II::MO_G3, 48, I.getOperand(0).getReg());
  return;
}

void AArch64InstructionSelector::preISelLower(MachineInstr &I) const {
  MachineBasicBlock &MBB = *I.getParent();
  MachineFunction &MF = *MBB.getParent();
  MachineRegisterInfo &MRI = MF.getRegInfo();

  switch (I.getOpcode()) {
  case TargetOpcode::G_SHL:
  case TargetOpcode::G_ASHR:
  case TargetOpcode::G_LSHR: {
    // These shifts are legalized to have 64 bit shift amounts because we want
    // to take advantage of the existing imported selection patterns that assume
    // the immediates are s64s. However, if the shifted type is 32 bits and for
    // some reason we receive input GMIR that has an s64 shift amount that's not
    // a G_CONSTANT, insert a truncate so that we can still select the s32
    // register-register variant.
    unsigned SrcReg = I.getOperand(1).getReg();
    unsigned ShiftReg = I.getOperand(2).getReg();
    const LLT ShiftTy = MRI.getType(ShiftReg);
    const LLT SrcTy = MRI.getType(SrcReg);
    if (SrcTy.isVector())
      return;
    assert(!ShiftTy.isVector() && "unexpected vector shift ty");
    if (SrcTy.getSizeInBits() != 32 || ShiftTy.getSizeInBits() != 64)
      return;
    auto *AmtMI = MRI.getVRegDef(ShiftReg);
    assert(AmtMI && "could not find a vreg definition for shift amount");
    if (AmtMI->getOpcode() != TargetOpcode::G_CONSTANT) {
      // Insert a subregister copy to implement a 64->32 trunc
      MachineIRBuilder MIB(I);
      auto Trunc = MIB.buildInstr(TargetOpcode::COPY, {SrcTy}, {})
                       .addReg(ShiftReg, 0, AArch64::sub_32);
      MRI.setRegBank(Trunc.getReg(0), RBI.getRegBank(AArch64::GPRRegBankID));
      I.getOperand(2).setReg(Trunc.getReg(0));
    }
    return;
  }
  case TargetOpcode::G_STORE:
    contractCrossBankCopyIntoStore(I, MRI);
    return;
  default:
    return;
  }
}

bool AArch64InstructionSelector::earlySelectSHL(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  // We try to match the immediate variant of LSL, which is actually an alias
  // for a special case of UBFM. Otherwise, we fall back to the imported
  // selector which will match the register variant.
  assert(I.getOpcode() == TargetOpcode::G_SHL && "unexpected op");
  const auto &MO = I.getOperand(2);
  auto VRegAndVal = getConstantVRegVal(MO.getReg(), MRI);
  if (!VRegAndVal)
    return false;

  const LLT DstTy = MRI.getType(I.getOperand(0).getReg());
  if (DstTy.isVector())
    return false;
  bool Is64Bit = DstTy.getSizeInBits() == 64;
  auto Imm1Fn = Is64Bit ? selectShiftA_64(MO) : selectShiftA_32(MO);
  auto Imm2Fn = Is64Bit ? selectShiftB_64(MO) : selectShiftB_32(MO);
  MachineIRBuilder MIB(I);

  if (!Imm1Fn || !Imm2Fn)
    return false;

  auto NewI =
      MIB.buildInstr(Is64Bit ? AArch64::UBFMXri : AArch64::UBFMWri,
                     {I.getOperand(0).getReg()}, {I.getOperand(1).getReg()});

  for (auto &RenderFn : *Imm1Fn)
    RenderFn(NewI);
  for (auto &RenderFn : *Imm2Fn)
    RenderFn(NewI);

  I.eraseFromParent();
  return constrainSelectedInstRegOperands(*NewI, TII, TRI, RBI);
}

void AArch64InstructionSelector::contractCrossBankCopyIntoStore(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_STORE && "Expected G_STORE");
  // If we're storing a scalar, it doesn't matter what register bank that
  // scalar is on. All that matters is the size.
  //
  // So, if we see something like this (with a 32-bit scalar as an example):
  //
  // %x:gpr(s32) = ... something ...
  // %y:fpr(s32) = COPY %x:gpr(s32)
  // G_STORE %y:fpr(s32)
  //
  // We can fix this up into something like this:
  //
  // G_STORE %x:gpr(s32)
  //
  // And then continue the selection process normally.
  MachineInstr *Def = getDefIgnoringCopies(I.getOperand(0).getReg(), MRI);
  if (!Def)
    return;
  Register DefDstReg = Def->getOperand(0).getReg();
  LLT DefDstTy = MRI.getType(DefDstReg);
  Register StoreSrcReg = I.getOperand(0).getReg();
  LLT StoreSrcTy = MRI.getType(StoreSrcReg);

  // If we get something strange like a physical register, then we shouldn't
  // go any further.
  if (!DefDstTy.isValid())
    return;

  // Are the source and dst types the same size?
  if (DefDstTy.getSizeInBits() != StoreSrcTy.getSizeInBits())
    return;

  if (RBI.getRegBank(StoreSrcReg, MRI, TRI) ==
      RBI.getRegBank(DefDstReg, MRI, TRI))
    return;

  // We have a cross-bank copy, which is entering a store. Let's fold it.
  I.getOperand(0).setReg(DefDstReg);
}

bool AArch64InstructionSelector::earlySelectLoad(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  // Try to fold in shifts, etc into the addressing mode of a load.
  assert(I.getOpcode() == TargetOpcode::G_LOAD && "unexpected op");

  // Don't handle atomic loads/stores yet.
  auto &MemOp = **I.memoperands_begin();
  if (MemOp.getOrdering() != AtomicOrdering::NotAtomic) {
    LLVM_DEBUG(dbgs() << "Atomic load/store not supported yet\n");
    return false;
  }

  unsigned MemBytes = MemOp.getSize();

  // Only support 64-bit loads for now.
  if (MemBytes != 8)
    return false;

  Register DstReg = I.getOperand(0).getReg();
  const LLT DstTy = MRI.getType(DstReg);
  // Don't handle vectors.
  if (DstTy.isVector())
    return false;

  unsigned DstSize = DstTy.getSizeInBits();
  // TODO: 32-bit destinations.
  if (DstSize != 64)
    return false;

  // Check if we can do any folding from GEPs/shifts etc. into the load.
  auto ImmFn = selectAddrModeXRO(I.getOperand(1), MemBytes);
  if (!ImmFn)
    return false;

  // We can fold something. Emit the load here.
  MachineIRBuilder MIB(I);

  // Choose the instruction based off the size of the element being loaded, and
  // whether or not we're loading into a FPR.
  const RegisterBank &RB = *RBI.getRegBank(DstReg, MRI, TRI);
  unsigned Opc =
      RB.getID() == AArch64::GPRRegBankID ? AArch64::LDRXroX : AArch64::LDRDroX;
  // Construct the load.
  auto LoadMI = MIB.buildInstr(Opc, {DstReg}, {});
  for (auto &RenderFn : *ImmFn)
    RenderFn(LoadMI);
  LoadMI.addMemOperand(*I.memoperands_begin());
  I.eraseFromParent();
  return constrainSelectedInstRegOperands(*LoadMI, TII, TRI, RBI);
}

bool AArch64InstructionSelector::earlySelect(MachineInstr &I) const {
  assert(I.getParent() && "Instruction should be in a basic block!");
  assert(I.getParent()->getParent() && "Instruction should be in a function!");

  MachineBasicBlock &MBB = *I.getParent();
  MachineFunction &MF = *MBB.getParent();
  MachineRegisterInfo &MRI = MF.getRegInfo();

  switch (I.getOpcode()) {
  case TargetOpcode::G_SHL:
    return earlySelectSHL(I, MRI);
  case TargetOpcode::G_LOAD:
    return earlySelectLoad(I, MRI);
  case TargetOpcode::G_CONSTANT: {
    bool IsZero = false;
    if (I.getOperand(1).isCImm())
      IsZero = I.getOperand(1).getCImm()->getZExtValue() == 0;
    else if (I.getOperand(1).isImm())
      IsZero = I.getOperand(1).getImm() == 0;

    if (!IsZero)
      return false;

    Register DefReg = I.getOperand(0).getReg();
    LLT Ty = MRI.getType(DefReg);
    if (Ty != LLT::scalar(64) && Ty != LLT::scalar(32))
      return false;

    if (Ty == LLT::scalar(64)) {
      I.getOperand(1).ChangeToRegister(AArch64::XZR, false);
      RBI.constrainGenericRegister(DefReg, AArch64::GPR64RegClass, MRI);
    } else {
      I.getOperand(1).ChangeToRegister(AArch64::WZR, false);
      RBI.constrainGenericRegister(DefReg, AArch64::GPR32RegClass, MRI);
    }
    I.setDesc(TII.get(TargetOpcode::COPY));
    return true;
  }
  default:
    return false;
  }
}

bool AArch64InstructionSelector::select(MachineInstr &I,
                                        CodeGenCoverage &CoverageInfo) const {
  assert(I.getParent() && "Instruction should be in a basic block!");
  assert(I.getParent()->getParent() && "Instruction should be in a function!");

  MachineBasicBlock &MBB = *I.getParent();
  MachineFunction &MF = *MBB.getParent();
  MachineRegisterInfo &MRI = MF.getRegInfo();

  unsigned Opcode = I.getOpcode();
  // G_PHI requires same handling as PHI
  if (!isPreISelGenericOpcode(Opcode) || Opcode == TargetOpcode::G_PHI) {
    // Certain non-generic instructions also need some special handling.

    if (Opcode ==  TargetOpcode::LOAD_STACK_GUARD)
      return constrainSelectedInstRegOperands(I, TII, TRI, RBI);

    if (Opcode == TargetOpcode::PHI || Opcode == TargetOpcode::G_PHI) {
      const Register DefReg = I.getOperand(0).getReg();
      const LLT DefTy = MRI.getType(DefReg);

      const RegClassOrRegBank &RegClassOrBank =
        MRI.getRegClassOrRegBank(DefReg);

      const TargetRegisterClass *DefRC
        = RegClassOrBank.dyn_cast<const TargetRegisterClass *>();
      if (!DefRC) {
        if (!DefTy.isValid()) {
          LLVM_DEBUG(dbgs() << "PHI operand has no type, not a gvreg?\n");
          return false;
        }
        const RegisterBank &RB = *RegClassOrBank.get<const RegisterBank *>();
        DefRC = getRegClassForTypeOnBank(DefTy, RB, RBI);
        if (!DefRC) {
          LLVM_DEBUG(dbgs() << "PHI operand has unexpected size/bank\n");
          return false;
        }
      }

      I.setDesc(TII.get(TargetOpcode::PHI));

      return RBI.constrainGenericRegister(DefReg, *DefRC, MRI);
    }

    if (I.isCopy())
      return selectCopy(I, TII, MRI, TRI, RBI);

    return true;
  }


  if (I.getNumOperands() != I.getNumExplicitOperands()) {
    LLVM_DEBUG(
        dbgs() << "Generic instruction has unexpected implicit operands\n");
    return false;
  }

  // Try to do some lowering before we start instruction selecting. These
  // lowerings are purely transformations on the input G_MIR and so selection
  // must continue after any modification of the instruction.
  preISelLower(I);

  // There may be patterns where the importer can't deal with them optimally,
  // but does select it to a suboptimal sequence so our custom C++ selection
  // code later never has a chance to work on it. Therefore, we have an early
  // selection attempt here to give priority to certain selection routines
  // over the imported ones.
  if (earlySelect(I))
    return true;

  if (selectImpl(I, CoverageInfo))
    return true;

  LLT Ty =
      I.getOperand(0).isReg() ? MRI.getType(I.getOperand(0).getReg()) : LLT{};

  MachineIRBuilder MIB(I);

  switch (Opcode) {
  case TargetOpcode::G_BRCOND: {
    if (Ty.getSizeInBits() > 32) {
      // We shouldn't need this on AArch64, but it would be implemented as an
      // EXTRACT_SUBREG followed by a TBNZW because TBNZX has no encoding if the
      // bit being tested is < 32.
      LLVM_DEBUG(dbgs() << "G_BRCOND has type: " << Ty
                        << ", expected at most 32-bits");
      return false;
    }

    const Register CondReg = I.getOperand(0).getReg();
    MachineBasicBlock *DestMBB = I.getOperand(1).getMBB();

    // Speculation tracking/SLH assumes that optimized TB(N)Z/CB(N)Z
    // instructions will not be produced, as they are conditional branch
    // instructions that do not set flags.
    bool ProduceNonFlagSettingCondBr =
        !MF.getFunction().hasFnAttribute(Attribute::SpeculativeLoadHardening);
    if (ProduceNonFlagSettingCondBr && selectCompareBranch(I, MF, MRI))
      return true;

    if (ProduceNonFlagSettingCondBr) {
      auto MIB = BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::TBNZW))
                     .addUse(CondReg)
                     .addImm(/*bit offset=*/0)
                     .addMBB(DestMBB);

      I.eraseFromParent();
      return constrainSelectedInstRegOperands(*MIB.getInstr(), TII, TRI, RBI);
    } else {
      auto CMP = BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::ANDSWri))
                     .addDef(AArch64::WZR)
                     .addUse(CondReg)
                     .addImm(1);
      constrainSelectedInstRegOperands(*CMP.getInstr(), TII, TRI, RBI);
      auto Bcc =
          BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::Bcc))
              .addImm(AArch64CC::EQ)
              .addMBB(DestMBB);

      I.eraseFromParent();
      return constrainSelectedInstRegOperands(*Bcc.getInstr(), TII, TRI, RBI);
    }
  }

  case TargetOpcode::G_BRINDIRECT: {
    I.setDesc(TII.get(AArch64::BR));
    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }

  case TargetOpcode::G_BRJT:
    return selectBrJT(I, MRI);

  case TargetOpcode::G_BSWAP: {
    // Handle vector types for G_BSWAP directly.
    Register DstReg = I.getOperand(0).getReg();
    LLT DstTy = MRI.getType(DstReg);

    // We should only get vector types here; everything else is handled by the
    // importer right now.
    if (!DstTy.isVector() || DstTy.getSizeInBits() > 128) {
      LLVM_DEBUG(dbgs() << "Dst type for G_BSWAP currently unsupported.\n");
      return false;
    }

    // Only handle 4 and 2 element vectors for now.
    // TODO: 16-bit elements.
    unsigned NumElts = DstTy.getNumElements();
    if (NumElts != 4 && NumElts != 2) {
      LLVM_DEBUG(dbgs() << "Unsupported number of elements for G_BSWAP.\n");
      return false;
    }

    // Choose the correct opcode for the supported types. Right now, that's
    // v2s32, v4s32, and v2s64.
    unsigned Opc = 0;
    unsigned EltSize = DstTy.getElementType().getSizeInBits();
    if (EltSize == 32)
      Opc = (DstTy.getNumElements() == 2) ? AArch64::REV32v8i8
                                          : AArch64::REV32v16i8;
    else if (EltSize == 64)
      Opc = AArch64::REV64v16i8;

    // We should always get something by the time we get here...
    assert(Opc != 0 && "Didn't get an opcode for G_BSWAP?");

    I.setDesc(TII.get(Opc));
    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }

  case TargetOpcode::G_FCONSTANT:
  case TargetOpcode::G_CONSTANT: {
    const bool isFP = Opcode == TargetOpcode::G_FCONSTANT;

    const LLT s8 = LLT::scalar(8);
    const LLT s16 = LLT::scalar(16);
    const LLT s32 = LLT::scalar(32);
    const LLT s64 = LLT::scalar(64);
    const LLT p0 = LLT::pointer(0, 64);

    const Register DefReg = I.getOperand(0).getReg();
    const LLT DefTy = MRI.getType(DefReg);
    const unsigned DefSize = DefTy.getSizeInBits();
    const RegisterBank &RB = *RBI.getRegBank(DefReg, MRI, TRI);

    // FIXME: Redundant check, but even less readable when factored out.
    if (isFP) {
      if (Ty != s32 && Ty != s64) {
        LLVM_DEBUG(dbgs() << "Unable to materialize FP " << Ty
                          << " constant, expected: " << s32 << " or " << s64
                          << '\n');
        return false;
      }

      if (RB.getID() != AArch64::FPRRegBankID) {
        LLVM_DEBUG(dbgs() << "Unable to materialize FP " << Ty
                          << " constant on bank: " << RB
                          << ", expected: FPR\n");
        return false;
      }

      // The case when we have 0.0 is covered by tablegen. Reject it here so we
      // can be sure tablegen works correctly and isn't rescued by this code.
      if (I.getOperand(1).getFPImm()->getValueAPF().isExactlyValue(0.0))
        return false;
    } else {
      // s32 and s64 are covered by tablegen.
      if (Ty != p0 && Ty != s8 && Ty != s16) {
        LLVM_DEBUG(dbgs() << "Unable to materialize integer " << Ty
                          << " constant, expected: " << s32 << ", " << s64
                          << ", or " << p0 << '\n');
        return false;
      }

      if (RB.getID() != AArch64::GPRRegBankID) {
        LLVM_DEBUG(dbgs() << "Unable to materialize integer " << Ty
                          << " constant on bank: " << RB
                          << ", expected: GPR\n");
        return false;
      }
    }

    // We allow G_CONSTANT of types < 32b.
    const unsigned MovOpc =
        DefSize == 64 ? AArch64::MOVi64imm : AArch64::MOVi32imm;

    if (isFP) {
      // Either emit a FMOV, or emit a copy to emit a normal mov.
      const TargetRegisterClass &GPRRC =
          DefSize == 32 ? AArch64::GPR32RegClass : AArch64::GPR64RegClass;
      const TargetRegisterClass &FPRRC =
          DefSize == 32 ? AArch64::FPR32RegClass : AArch64::FPR64RegClass;

      // Can we use a FMOV instruction to represent the immediate?
      if (emitFMovForFConstant(I, MRI))
        return true;

      // Nope. Emit a copy and use a normal mov instead.
      const Register DefGPRReg = MRI.createVirtualRegister(&GPRRC);
      MachineOperand &RegOp = I.getOperand(0);
      RegOp.setReg(DefGPRReg);
      MIB.setInsertPt(MIB.getMBB(), std::next(I.getIterator()));
      MIB.buildCopy({DefReg}, {DefGPRReg});

      if (!RBI.constrainGenericRegister(DefReg, FPRRC, MRI)) {
        LLVM_DEBUG(dbgs() << "Failed to constrain G_FCONSTANT def operand\n");
        return false;
      }

      MachineOperand &ImmOp = I.getOperand(1);
      // FIXME: Is going through int64_t always correct?
      ImmOp.ChangeToImmediate(
          ImmOp.getFPImm()->getValueAPF().bitcastToAPInt().getZExtValue());
    } else if (I.getOperand(1).isCImm()) {
      uint64_t Val = I.getOperand(1).getCImm()->getZExtValue();
      I.getOperand(1).ChangeToImmediate(Val);
    } else if (I.getOperand(1).isImm()) {
      uint64_t Val = I.getOperand(1).getImm();
      I.getOperand(1).ChangeToImmediate(Val);
    }

    I.setDesc(TII.get(MovOpc));
    constrainSelectedInstRegOperands(I, TII, TRI, RBI);
    return true;
  }
  case TargetOpcode::G_EXTRACT: {
    Register DstReg = I.getOperand(0).getReg();
    Register SrcReg = I.getOperand(1).getReg();
    LLT SrcTy = MRI.getType(SrcReg);
    LLT DstTy = MRI.getType(DstReg);
    (void)DstTy;
    unsigned SrcSize = SrcTy.getSizeInBits();

    if (SrcTy.getSizeInBits() > 64) {
      // This should be an extract of an s128, which is like a vector extract.
      if (SrcTy.getSizeInBits() != 128)
        return false;
      // Only support extracting 64 bits from an s128 at the moment.
      if (DstTy.getSizeInBits() != 64)
        return false;

      const RegisterBank &SrcRB = *RBI.getRegBank(SrcReg, MRI, TRI);
      const RegisterBank &DstRB = *RBI.getRegBank(DstReg, MRI, TRI);
      // Check we have the right regbank always.
      assert(SrcRB.getID() == AArch64::FPRRegBankID &&
             DstRB.getID() == AArch64::FPRRegBankID &&
             "Wrong extract regbank!");
      (void)SrcRB;

      // Emit the same code as a vector extract.
      // Offset must be a multiple of 64.
      unsigned Offset = I.getOperand(2).getImm();
      if (Offset % 64 != 0)
        return false;
      unsigned LaneIdx = Offset / 64;
      MachineIRBuilder MIB(I);
      MachineInstr *Extract = emitExtractVectorElt(
          DstReg, DstRB, LLT::scalar(64), SrcReg, LaneIdx, MIB);
      if (!Extract)
        return false;
      I.eraseFromParent();
      return true;
    }

    I.setDesc(TII.get(SrcSize == 64 ? AArch64::UBFMXri : AArch64::UBFMWri));
    MachineInstrBuilder(MF, I).addImm(I.getOperand(2).getImm() +
                                      Ty.getSizeInBits() - 1);

    if (SrcSize < 64) {
      assert(SrcSize == 32 && DstTy.getSizeInBits() == 16 &&
             "unexpected G_EXTRACT types");
      return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
    }

    DstReg = MRI.createGenericVirtualRegister(LLT::scalar(64));
    MIB.setInsertPt(MIB.getMBB(), std::next(I.getIterator()));
    MIB.buildInstr(TargetOpcode::COPY, {I.getOperand(0).getReg()}, {})
        .addReg(DstReg, 0, AArch64::sub_32);
    RBI.constrainGenericRegister(I.getOperand(0).getReg(),
                                 AArch64::GPR32RegClass, MRI);
    I.getOperand(0).setReg(DstReg);

    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }

  case TargetOpcode::G_INSERT: {
    LLT SrcTy = MRI.getType(I.getOperand(2).getReg());
    LLT DstTy = MRI.getType(I.getOperand(0).getReg());
    unsigned DstSize = DstTy.getSizeInBits();
    // Larger inserts are vectors, same-size ones should be something else by
    // now (split up or turned into COPYs).
    if (Ty.getSizeInBits() > 64 || SrcTy.getSizeInBits() > 32)
      return false;

    I.setDesc(TII.get(DstSize == 64 ? AArch64::BFMXri : AArch64::BFMWri));
    unsigned LSB = I.getOperand(3).getImm();
    unsigned Width = MRI.getType(I.getOperand(2).getReg()).getSizeInBits();
    I.getOperand(3).setImm((DstSize - LSB) % DstSize);
    MachineInstrBuilder(MF, I).addImm(Width - 1);

    if (DstSize < 64) {
      assert(DstSize == 32 && SrcTy.getSizeInBits() == 16 &&
             "unexpected G_INSERT types");
      return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
    }

    Register SrcReg = MRI.createGenericVirtualRegister(LLT::scalar(64));
    BuildMI(MBB, I.getIterator(), I.getDebugLoc(),
            TII.get(AArch64::SUBREG_TO_REG))
        .addDef(SrcReg)
        .addImm(0)
        .addUse(I.getOperand(2).getReg())
        .addImm(AArch64::sub_32);
    RBI.constrainGenericRegister(I.getOperand(2).getReg(),
                                 AArch64::GPR32RegClass, MRI);
    I.getOperand(2).setReg(SrcReg);

    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }
  case TargetOpcode::G_FRAME_INDEX: {
    // allocas and G_FRAME_INDEX are only supported in addrspace(0).
    if (Ty != LLT::pointer(0, 64)) {
      LLVM_DEBUG(dbgs() << "G_FRAME_INDEX pointer has type: " << Ty
                        << ", expected: " << LLT::pointer(0, 64) << '\n');
      return false;
    }
    I.setDesc(TII.get(AArch64::ADDXri));

    // MOs for a #0 shifted immediate.
    I.addOperand(MachineOperand::CreateImm(0));
    I.addOperand(MachineOperand::CreateImm(0));

    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }

  case TargetOpcode::G_GLOBAL_VALUE: {
    auto GV = I.getOperand(1).getGlobal();
    if (GV->isThreadLocal()) {
      // FIXME: we don't support TLS yet.
      return false;
    }
    unsigned OpFlags = STI.ClassifyGlobalReference(GV, TM);
    if (OpFlags & AArch64II::MO_GOT) {
      I.setDesc(TII.get(AArch64::LOADgot));
      I.getOperand(1).setTargetFlags(OpFlags);
    } else if (TM.getCodeModel() == CodeModel::Large) {
      // Materialize the global using movz/movk instructions.
      materializeLargeCMVal(I, GV, OpFlags);
      I.eraseFromParent();
      return true;
    } else if (TM.getCodeModel() == CodeModel::Tiny) {
      I.setDesc(TII.get(AArch64::ADR));
      I.getOperand(1).setTargetFlags(OpFlags);
    } else {
      I.setDesc(TII.get(AArch64::MOVaddr));
      I.getOperand(1).setTargetFlags(OpFlags | AArch64II::MO_PAGE);
      MachineInstrBuilder MIB(MF, I);
      MIB.addGlobalAddress(GV, I.getOperand(1).getOffset(),
                           OpFlags | AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
    }
    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }

  case TargetOpcode::G_ZEXTLOAD:
  case TargetOpcode::G_LOAD:
  case TargetOpcode::G_STORE: {
    bool IsZExtLoad = I.getOpcode() == TargetOpcode::G_ZEXTLOAD;
    MachineIRBuilder MIB(I);

    LLT PtrTy = MRI.getType(I.getOperand(1).getReg());

    if (PtrTy != LLT::pointer(0, 64)) {
      LLVM_DEBUG(dbgs() << "Load/Store pointer has type: " << PtrTy
                        << ", expected: " << LLT::pointer(0, 64) << '\n');
      return false;
    }

    auto &MemOp = **I.memoperands_begin();
    if (MemOp.getOrdering() != AtomicOrdering::NotAtomic) {
      LLVM_DEBUG(dbgs() << "Atomic load/store not supported yet\n");
      return false;
    }
    unsigned MemSizeInBits = MemOp.getSize() * 8;

    const Register PtrReg = I.getOperand(1).getReg();
#ifndef NDEBUG
    const RegisterBank &PtrRB = *RBI.getRegBank(PtrReg, MRI, TRI);
    // Sanity-check the pointer register.
    assert(PtrRB.getID() == AArch64::GPRRegBankID &&
           "Load/Store pointer operand isn't a GPR");
    assert(MRI.getType(PtrReg).isPointer() &&
           "Load/Store pointer operand isn't a pointer");
#endif

    const Register ValReg = I.getOperand(0).getReg();
    const RegisterBank &RB = *RBI.getRegBank(ValReg, MRI, TRI);

    const unsigned NewOpc =
        selectLoadStoreUIOp(I.getOpcode(), RB.getID(), MemSizeInBits);
    if (NewOpc == I.getOpcode())
      return false;

    I.setDesc(TII.get(NewOpc));

    uint64_t Offset = 0;
    auto *PtrMI = MRI.getVRegDef(PtrReg);

    // Try to fold a GEP into our unsigned immediate addressing mode.
    if (PtrMI->getOpcode() == TargetOpcode::G_GEP) {
      if (auto COff = getConstantVRegVal(PtrMI->getOperand(2).getReg(), MRI)) {
        int64_t Imm = *COff;
        const unsigned Size = MemSizeInBits / 8;
        const unsigned Scale = Log2_32(Size);
        if ((Imm & (Size - 1)) == 0 && Imm >= 0 && Imm < (0x1000 << Scale)) {
          unsigned Ptr2Reg = PtrMI->getOperand(1).getReg();
          I.getOperand(1).setReg(Ptr2Reg);
          PtrMI = MRI.getVRegDef(Ptr2Reg);
          Offset = Imm / Size;
        }
      }
    }

    // If we haven't folded anything into our addressing mode yet, try to fold
    // a frame index into the base+offset.
    if (!Offset && PtrMI->getOpcode() == TargetOpcode::G_FRAME_INDEX)
      I.getOperand(1).ChangeToFrameIndex(PtrMI->getOperand(1).getIndex());

    I.addOperand(MachineOperand::CreateImm(Offset));

    // If we're storing a 0, use WZR/XZR.
    if (auto CVal = getConstantVRegVal(ValReg, MRI)) {
      if (*CVal == 0 && Opcode == TargetOpcode::G_STORE) {
        if (I.getOpcode() == AArch64::STRWui)
          I.getOperand(0).setReg(AArch64::WZR);
        else if (I.getOpcode() == AArch64::STRXui)
          I.getOperand(0).setReg(AArch64::XZR);
      }
    }

    if (IsZExtLoad) {
      // The zextload from a smaller type to i32 should be handled by the importer.
      if (MRI.getType(ValReg).getSizeInBits() != 64)
        return false;
      // If we have a ZEXTLOAD then change the load's type to be a narrower reg
      //and zero_extend with SUBREG_TO_REG.
      Register LdReg = MRI.createVirtualRegister(&AArch64::GPR32RegClass);
      Register DstReg = I.getOperand(0).getReg();
      I.getOperand(0).setReg(LdReg);

      MIB.setInsertPt(MIB.getMBB(), std::next(I.getIterator()));
      MIB.buildInstr(AArch64::SUBREG_TO_REG, {DstReg}, {})
          .addImm(0)
          .addUse(LdReg)
          .addImm(AArch64::sub_32);
      constrainSelectedInstRegOperands(I, TII, TRI, RBI);
      return RBI.constrainGenericRegister(DstReg, AArch64::GPR64allRegClass,
                                          MRI);
    }
    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }

  case TargetOpcode::G_SMULH:
  case TargetOpcode::G_UMULH: {
    // Reject the various things we don't support yet.
    if (unsupportedBinOp(I, RBI, MRI, TRI))
      return false;

    const Register DefReg = I.getOperand(0).getReg();
    const RegisterBank &RB = *RBI.getRegBank(DefReg, MRI, TRI);

    if (RB.getID() != AArch64::GPRRegBankID) {
      LLVM_DEBUG(dbgs() << "G_[SU]MULH on bank: " << RB << ", expected: GPR\n");
      return false;
    }

    if (Ty != LLT::scalar(64)) {
      LLVM_DEBUG(dbgs() << "G_[SU]MULH has type: " << Ty
                        << ", expected: " << LLT::scalar(64) << '\n');
      return false;
    }

    unsigned NewOpc = I.getOpcode() == TargetOpcode::G_SMULH ? AArch64::SMULHrr
                                                             : AArch64::UMULHrr;
    I.setDesc(TII.get(NewOpc));

    // Now that we selected an opcode, we need to constrain the register
    // operands to use appropriate classes.
    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }
  case TargetOpcode::G_FADD:
  case TargetOpcode::G_FSUB:
  case TargetOpcode::G_FMUL:
  case TargetOpcode::G_FDIV:

  case TargetOpcode::G_ASHR:
    if (MRI.getType(I.getOperand(0).getReg()).isVector())
      return selectVectorASHR(I, MRI);
    LLVM_FALLTHROUGH;
  case TargetOpcode::G_SHL:
    if (Opcode == TargetOpcode::G_SHL &&
        MRI.getType(I.getOperand(0).getReg()).isVector())
      return selectVectorSHL(I, MRI);
    LLVM_FALLTHROUGH;
  case TargetOpcode::G_OR:
  case TargetOpcode::G_LSHR: {
    // Reject the various things we don't support yet.
    if (unsupportedBinOp(I, RBI, MRI, TRI))
      return false;

    const unsigned OpSize = Ty.getSizeInBits();

    const Register DefReg = I.getOperand(0).getReg();
    const RegisterBank &RB = *RBI.getRegBank(DefReg, MRI, TRI);

    const unsigned NewOpc = selectBinaryOp(I.getOpcode(), RB.getID(), OpSize);
    if (NewOpc == I.getOpcode())
      return false;

    I.setDesc(TII.get(NewOpc));
    // FIXME: Should the type be always reset in setDesc?

    // Now that we selected an opcode, we need to constrain the register
    // operands to use appropriate classes.
    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }

  case TargetOpcode::G_GEP: {
    MachineIRBuilder MIRBuilder(I);
    emitADD(I.getOperand(0).getReg(), I.getOperand(1), I.getOperand(2),
            MIRBuilder);
    I.eraseFromParent();
    return true;
  }
  case TargetOpcode::G_UADDO: {
    // TODO: Support other types.
    unsigned OpSize = Ty.getSizeInBits();
    if (OpSize != 32 && OpSize != 64) {
      LLVM_DEBUG(
          dbgs()
          << "G_UADDO currently only supported for 32 and 64 b types.\n");
      return false;
    }

    // TODO: Support vectors.
    if (Ty.isVector()) {
      LLVM_DEBUG(dbgs() << "G_UADDO currently only supported for scalars.\n");
      return false;
    }

    // Add and set the set condition flag.
    unsigned AddsOpc = OpSize == 32 ? AArch64::ADDSWrr : AArch64::ADDSXrr;
    MachineIRBuilder MIRBuilder(I);
    auto AddsMI = MIRBuilder.buildInstr(
        AddsOpc, {I.getOperand(0).getReg()},
        {I.getOperand(2).getReg(), I.getOperand(3).getReg()});
    constrainSelectedInstRegOperands(*AddsMI, TII, TRI, RBI);

    // Now, put the overflow result in the register given by the first operand
    // to the G_UADDO. CSINC increments the result when the predicate is false,
    // so to get the increment when it's true, we need to use the inverse. In
    // this case, we want to increment when carry is set.
    auto CsetMI = MIRBuilder
                      .buildInstr(AArch64::CSINCWr, {I.getOperand(1).getReg()},
                                  {Register(AArch64::WZR), Register(AArch64::WZR)})
                      .addImm(getInvertedCondCode(AArch64CC::HS));
    constrainSelectedInstRegOperands(*CsetMI, TII, TRI, RBI);
    I.eraseFromParent();
    return true;
  }

  case TargetOpcode::G_PTR_MASK: {
    uint64_t Align = I.getOperand(2).getImm();
    if (Align >= 64 || Align == 0)
      return false;

    uint64_t Mask = ~((1ULL << Align) - 1);
    I.setDesc(TII.get(AArch64::ANDXri));
    I.getOperand(2).setImm(AArch64_AM::encodeLogicalImmediate(Mask, 64));

    return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  }
  case TargetOpcode::G_PTRTOINT:
  case TargetOpcode::G_TRUNC: {
    const LLT DstTy = MRI.getType(I.getOperand(0).getReg());
    const LLT SrcTy = MRI.getType(I.getOperand(1).getReg());

    const Register DstReg = I.getOperand(0).getReg();
    const Register SrcReg = I.getOperand(1).getReg();

    const RegisterBank &DstRB = *RBI.getRegBank(DstReg, MRI, TRI);
    const RegisterBank &SrcRB = *RBI.getRegBank(SrcReg, MRI, TRI);

    if (DstRB.getID() != SrcRB.getID()) {
      LLVM_DEBUG(
          dbgs() << "G_TRUNC/G_PTRTOINT input/output on different banks\n");
      return false;
    }

    if (DstRB.getID() == AArch64::GPRRegBankID) {
      const TargetRegisterClass *DstRC =
          getRegClassForTypeOnBank(DstTy, DstRB, RBI);
      if (!DstRC)
        return false;

      const TargetRegisterClass *SrcRC =
          getRegClassForTypeOnBank(SrcTy, SrcRB, RBI);
      if (!SrcRC)
        return false;

      if (!RBI.constrainGenericRegister(SrcReg, *SrcRC, MRI) ||
          !RBI.constrainGenericRegister(DstReg, *DstRC, MRI)) {
        LLVM_DEBUG(dbgs() << "Failed to constrain G_TRUNC/G_PTRTOINT\n");
        return false;
      }

      if (DstRC == SrcRC) {
        // Nothing to be done
      } else if (Opcode == TargetOpcode::G_TRUNC && DstTy == LLT::scalar(32) &&
                 SrcTy == LLT::scalar(64)) {
        llvm_unreachable("TableGen can import this case");
        return false;
      } else if (DstRC == &AArch64::GPR32RegClass &&
                 SrcRC == &AArch64::GPR64RegClass) {
        I.getOperand(1).setSubReg(AArch64::sub_32);
      } else {
        LLVM_DEBUG(
            dbgs() << "Unhandled mismatched classes in G_TRUNC/G_PTRTOINT\n");
        return false;
      }

      I.setDesc(TII.get(TargetOpcode::COPY));
      return true;
    } else if (DstRB.getID() == AArch64::FPRRegBankID) {
      if (DstTy == LLT::vector(4, 16) && SrcTy == LLT::vector(4, 32)) {
        I.setDesc(TII.get(AArch64::XTNv4i16));
        constrainSelectedInstRegOperands(I, TII, TRI, RBI);
        return true;
      }

      if (!SrcTy.isVector() && SrcTy.getSizeInBits() == 128) {
        MachineIRBuilder MIB(I);
        MachineInstr *Extract = emitExtractVectorElt(
            DstReg, DstRB, LLT::scalar(DstTy.getSizeInBits()), SrcReg, 0, MIB);
        if (!Extract)
          return false;
        I.eraseFromParent();
        return true;
      }
    }

    return false;
  }

  case TargetOpcode::G_ANYEXT: {
    const Register DstReg = I.getOperand(0).getReg();
    const Register SrcReg = I.getOperand(1).getReg();

    const RegisterBank &RBDst = *RBI.getRegBank(DstReg, MRI, TRI);
    if (RBDst.getID() != AArch64::GPRRegBankID) {
      LLVM_DEBUG(dbgs() << "G_ANYEXT on bank: " << RBDst
                        << ", expected: GPR\n");
      return false;
    }

    const RegisterBank &RBSrc = *RBI.getRegBank(SrcReg, MRI, TRI);
    if (RBSrc.getID() != AArch64::GPRRegBankID) {
      LLVM_DEBUG(dbgs() << "G_ANYEXT on bank: " << RBSrc
                        << ", expected: GPR\n");
      return false;
    }

    const unsigned DstSize = MRI.getType(DstReg).getSizeInBits();

    if (DstSize == 0) {
      LLVM_DEBUG(dbgs() << "G_ANYEXT operand has no size, not a gvreg?\n");
      return false;
    }

    if (DstSize != 64 && DstSize > 32) {
      LLVM_DEBUG(dbgs() << "G_ANYEXT to size: " << DstSize
                        << ", expected: 32 or 64\n");
      return false;
    }
    // At this point G_ANYEXT is just like a plain COPY, but we need
    // to explicitly form the 64-bit value if any.
    if (DstSize > 32) {
      Register ExtSrc = MRI.createVirtualRegister(&AArch64::GPR64allRegClass);
      BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::SUBREG_TO_REG))
          .addDef(ExtSrc)
          .addImm(0)
          .addUse(SrcReg)
          .addImm(AArch64::sub_32);
      I.getOperand(1).setReg(ExtSrc);
    }
    return selectCopy(I, TII, MRI, TRI, RBI);
  }

  case TargetOpcode::G_ZEXT:
  case TargetOpcode::G_SEXT: {
    unsigned Opcode = I.getOpcode();
    const bool IsSigned = Opcode == TargetOpcode::G_SEXT;
    const Register DefReg = I.getOperand(0).getReg();
    const Register SrcReg = I.getOperand(1).getReg();
    const LLT DstTy = MRI.getType(DefReg);
    const LLT SrcTy = MRI.getType(SrcReg);
    unsigned DstSize = DstTy.getSizeInBits();
    unsigned SrcSize = SrcTy.getSizeInBits();

    assert((*RBI.getRegBank(DefReg, MRI, TRI)).getID() ==
               AArch64::GPRRegBankID &&
           "Unexpected ext regbank");

    MachineIRBuilder MIB(I);
    MachineInstr *ExtI;
    if (DstTy.isVector())
      return false; // Should be handled by imported patterns.

    // First check if we're extending the result of a load which has a dest type
    // smaller than 32 bits, then this zext is redundant. GPR32 is the smallest
    // GPR register on AArch64 and all loads which are smaller automatically
    // zero-extend the upper bits. E.g.
    // %v(s8) = G_LOAD %p, :: (load 1)
    // %v2(s32) = G_ZEXT %v(s8)
    if (!IsSigned) {
      auto *LoadMI = getOpcodeDef(TargetOpcode::G_LOAD, SrcReg, MRI);
      if (LoadMI &&
          RBI.getRegBank(SrcReg, MRI, TRI)->getID() == AArch64::GPRRegBankID) {
        const MachineMemOperand *MemOp = *LoadMI->memoperands_begin();
        unsigned BytesLoaded = MemOp->getSize();
        if (BytesLoaded < 4 && SrcTy.getSizeInBytes() == BytesLoaded)
          return selectCopy(I, TII, MRI, TRI, RBI);
      }
    }

    if (DstSize == 64) {
      // FIXME: Can we avoid manually doing this?
      if (!RBI.constrainGenericRegister(SrcReg, AArch64::GPR32RegClass, MRI)) {
        LLVM_DEBUG(dbgs() << "Failed to constrain " << TII.getName(Opcode)
                          << " operand\n");
        return false;
      }

      auto SubregToReg =
          MIB.buildInstr(AArch64::SUBREG_TO_REG, {&AArch64::GPR64RegClass}, {})
              .addImm(0)
              .addUse(SrcReg)
              .addImm(AArch64::sub_32);

      ExtI = MIB.buildInstr(IsSigned ? AArch64::SBFMXri : AArch64::UBFMXri,
                             {DefReg}, {SubregToReg})
                  .addImm(0)
                  .addImm(SrcSize - 1);
    } else if (DstSize <= 32) {
      ExtI = MIB.buildInstr(IsSigned ? AArch64::SBFMWri : AArch64::UBFMWri,
                             {DefReg}, {SrcReg})
                  .addImm(0)
                  .addImm(SrcSize - 1);
    } else {
      return false;
    }

    constrainSelectedInstRegOperands(*ExtI, TII, TRI, RBI);
    I.eraseFromParent();
    return true;
  }

  case TargetOpcode::G_SITOFP:
  case TargetOpcode::G_UITOFP:
  case TargetOpcode::G_FPTOSI:
  case TargetOpcode::G_FPTOUI: {
    const LLT DstTy = MRI.getType(I.getOperand(0).getReg()),
              SrcTy = MRI.getType(I.getOperand(1).getReg());
    const unsigned NewOpc = selectFPConvOpc(Opcode, DstTy, SrcTy);
    if (NewOpc == Opcode)
      return false;

    I.setDesc(TII.get(NewOpc));
    constrainSelectedInstRegOperands(I, TII, TRI, RBI);

    return true;
  }


  case TargetOpcode::G_INTTOPTR:
    // The importer is currently unable to import pointer types since they
    // didn't exist in SelectionDAG.
    return selectCopy(I, TII, MRI, TRI, RBI);

  case TargetOpcode::G_BITCAST:
    // Imported SelectionDAG rules can handle every bitcast except those that
    // bitcast from a type to the same type. Ideally, these shouldn't occur
    // but we might not run an optimizer that deletes them. The other exception
    // is bitcasts involving pointer types, as SelectionDAG has no knowledge
    // of them.
    return selectCopy(I, TII, MRI, TRI, RBI);

  case TargetOpcode::G_SELECT: {
    if (MRI.getType(I.getOperand(1).getReg()) != LLT::scalar(1)) {
      LLVM_DEBUG(dbgs() << "G_SELECT cond has type: " << Ty
                        << ", expected: " << LLT::scalar(1) << '\n');
      return false;
    }

    const Register CondReg = I.getOperand(1).getReg();
    const Register TReg = I.getOperand(2).getReg();
    const Register FReg = I.getOperand(3).getReg();

    if (tryOptSelect(I))
      return true;

    Register CSelOpc = selectSelectOpc(I, MRI, RBI);
    MachineInstr &TstMI =
        *BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::ANDSWri))
             .addDef(AArch64::WZR)
             .addUse(CondReg)
             .addImm(AArch64_AM::encodeLogicalImmediate(1, 32));

    MachineInstr &CSelMI = *BuildMI(MBB, I, I.getDebugLoc(), TII.get(CSelOpc))
                                .addDef(I.getOperand(0).getReg())
                                .addUse(TReg)
                                .addUse(FReg)
                                .addImm(AArch64CC::NE);

    constrainSelectedInstRegOperands(TstMI, TII, TRI, RBI);
    constrainSelectedInstRegOperands(CSelMI, TII, TRI, RBI);

    I.eraseFromParent();
    return true;
  }
  case TargetOpcode::G_ICMP: {
    if (Ty.isVector())
      return selectVectorICmp(I, MRI);

    if (Ty != LLT::scalar(32)) {
      LLVM_DEBUG(dbgs() << "G_ICMP result has type: " << Ty
                        << ", expected: " << LLT::scalar(32) << '\n');
      return false;
    }

    MachineIRBuilder MIRBuilder(I);
    if (!emitIntegerCompare(I.getOperand(2), I.getOperand(3), I.getOperand(1),
                            MIRBuilder))
      return false;
    emitCSetForICMP(I.getOperand(0).getReg(), I.getOperand(1).getPredicate(),
                    MIRBuilder);
    I.eraseFromParent();
    return true;
  }

  case TargetOpcode::G_FCMP: {
    if (Ty != LLT::scalar(32)) {
      LLVM_DEBUG(dbgs() << "G_FCMP result has type: " << Ty
                        << ", expected: " << LLT::scalar(32) << '\n');
      return false;
    }

    unsigned CmpOpc = selectFCMPOpc(I, MRI);
    if (!CmpOpc)
      return false;

    // FIXME: regbank

    AArch64CC::CondCode CC1, CC2;
    changeFCMPPredToAArch64CC(
        (CmpInst::Predicate)I.getOperand(1).getPredicate(), CC1, CC2);

    // Partially build the compare. Decide if we need to add a use for the
    // third operand based off whether or not we're comparing against 0.0.
    auto CmpMI = BuildMI(MBB, I, I.getDebugLoc(), TII.get(CmpOpc))
                     .addUse(I.getOperand(2).getReg());

    // If we don't have an immediate compare, then we need to add a use of the
    // register which wasn't used for the immediate.
    // Note that the immediate will always be the last operand.
    if (CmpOpc != AArch64::FCMPSri && CmpOpc != AArch64::FCMPDri)
      CmpMI = CmpMI.addUse(I.getOperand(3).getReg());

    const Register DefReg = I.getOperand(0).getReg();
    Register Def1Reg = DefReg;
    if (CC2 != AArch64CC::AL)
      Def1Reg = MRI.createVirtualRegister(&AArch64::GPR32RegClass);

    MachineInstr &CSetMI =
        *BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::CSINCWr))
             .addDef(Def1Reg)
             .addUse(AArch64::WZR)
             .addUse(AArch64::WZR)
             .addImm(getInvertedCondCode(CC1));

    if (CC2 != AArch64CC::AL) {
      Register Def2Reg = MRI.createVirtualRegister(&AArch64::GPR32RegClass);
      MachineInstr &CSet2MI =
          *BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::CSINCWr))
               .addDef(Def2Reg)
               .addUse(AArch64::WZR)
               .addUse(AArch64::WZR)
               .addImm(getInvertedCondCode(CC2));
      MachineInstr &OrMI =
          *BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::ORRWrr))
               .addDef(DefReg)
               .addUse(Def1Reg)
               .addUse(Def2Reg);
      constrainSelectedInstRegOperands(OrMI, TII, TRI, RBI);
      constrainSelectedInstRegOperands(CSet2MI, TII, TRI, RBI);
    }
    constrainSelectedInstRegOperands(*CmpMI, TII, TRI, RBI);
    constrainSelectedInstRegOperands(CSetMI, TII, TRI, RBI);

    I.eraseFromParent();
    return true;
  }
  case TargetOpcode::G_VASTART:
    return STI.isTargetDarwin() ? selectVaStartDarwin(I, MF, MRI)
                                : selectVaStartAAPCS(I, MF, MRI);
  case TargetOpcode::G_INTRINSIC:
    return selectIntrinsic(I, MRI);
  case TargetOpcode::G_INTRINSIC_W_SIDE_EFFECTS:
    return selectIntrinsicWithSideEffects(I, MRI);
  case TargetOpcode::G_IMPLICIT_DEF: {
    I.setDesc(TII.get(TargetOpcode::IMPLICIT_DEF));
    const LLT DstTy = MRI.getType(I.getOperand(0).getReg());
    const Register DstReg = I.getOperand(0).getReg();
    const RegisterBank &DstRB = *RBI.getRegBank(DstReg, MRI, TRI);
    const TargetRegisterClass *DstRC =
        getRegClassForTypeOnBank(DstTy, DstRB, RBI);
    RBI.constrainGenericRegister(DstReg, *DstRC, MRI);
    return true;
  }
  case TargetOpcode::G_BLOCK_ADDR: {
    if (TM.getCodeModel() == CodeModel::Large) {
      materializeLargeCMVal(I, I.getOperand(1).getBlockAddress(), 0);
      I.eraseFromParent();
      return true;
    } else {
      I.setDesc(TII.get(AArch64::MOVaddrBA));
      auto MovMI = BuildMI(MBB, I, I.getDebugLoc(), TII.get(AArch64::MOVaddrBA),
                           I.getOperand(0).getReg())
                       .addBlockAddress(I.getOperand(1).getBlockAddress(),
                                        /* Offset */ 0, AArch64II::MO_PAGE)
                       .addBlockAddress(
                           I.getOperand(1).getBlockAddress(), /* Offset */ 0,
                           AArch64II::MO_NC | AArch64II::MO_PAGEOFF);
      I.eraseFromParent();
      return constrainSelectedInstRegOperands(*MovMI, TII, TRI, RBI);
    }
  }
  case TargetOpcode::G_INTRINSIC_TRUNC:
    return selectIntrinsicTrunc(I, MRI);
  case TargetOpcode::G_INTRINSIC_ROUND:
    return selectIntrinsicRound(I, MRI);
  case TargetOpcode::G_BUILD_VECTOR:
    return selectBuildVector(I, MRI);
  case TargetOpcode::G_MERGE_VALUES:
    return selectMergeValues(I, MRI);
  case TargetOpcode::G_UNMERGE_VALUES:
    return selectUnmergeValues(I, MRI);
  case TargetOpcode::G_SHUFFLE_VECTOR:
    return selectShuffleVector(I, MRI);
  case TargetOpcode::G_EXTRACT_VECTOR_ELT:
    return selectExtractElt(I, MRI);
  case TargetOpcode::G_INSERT_VECTOR_ELT:
    return selectInsertElt(I, MRI);
  case TargetOpcode::G_CONCAT_VECTORS:
    return selectConcatVectors(I, MRI);
  case TargetOpcode::G_JUMP_TABLE:
    return selectJumpTable(I, MRI);
  }

  return false;
}

bool AArch64InstructionSelector::selectBrJT(MachineInstr &I,
                                            MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_BRJT && "Expected G_BRJT");
  Register JTAddr = I.getOperand(0).getReg();
  unsigned JTI = I.getOperand(1).getIndex();
  Register Index = I.getOperand(2).getReg();
  MachineIRBuilder MIB(I);

  Register TargetReg = MRI.createVirtualRegister(&AArch64::GPR64RegClass);
  Register ScratchReg = MRI.createVirtualRegister(&AArch64::GPR64spRegClass);
  MIB.buildInstr(AArch64::JumpTableDest32, {TargetReg, ScratchReg},
                 {JTAddr, Index})
      .addJumpTableIndex(JTI);

  // Build the indirect branch.
  MIB.buildInstr(AArch64::BR, {}, {TargetReg});
  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectJumpTable(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_JUMP_TABLE && "Expected jump table");
  assert(I.getOperand(1).isJTI() && "Jump table op should have a JTI!");

  Register DstReg = I.getOperand(0).getReg();
  unsigned JTI = I.getOperand(1).getIndex();
  // We generate a MOVaddrJT which will get expanded to an ADRP + ADD later.
  MachineIRBuilder MIB(I);
  auto MovMI =
    MIB.buildInstr(AArch64::MOVaddrJT, {DstReg}, {})
          .addJumpTableIndex(JTI, AArch64II::MO_PAGE)
          .addJumpTableIndex(JTI, AArch64II::MO_NC | AArch64II::MO_PAGEOFF);
  I.eraseFromParent();
  return constrainSelectedInstRegOperands(*MovMI, TII, TRI, RBI);
}

bool AArch64InstructionSelector::selectIntrinsicTrunc(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  const LLT SrcTy = MRI.getType(I.getOperand(0).getReg());

  // Select the correct opcode.
  unsigned Opc = 0;
  if (!SrcTy.isVector()) {
    switch (SrcTy.getSizeInBits()) {
    default:
    case 16:
      Opc = AArch64::FRINTZHr;
      break;
    case 32:
      Opc = AArch64::FRINTZSr;
      break;
    case 64:
      Opc = AArch64::FRINTZDr;
      break;
    }
  } else {
    unsigned NumElts = SrcTy.getNumElements();
    switch (SrcTy.getElementType().getSizeInBits()) {
    default:
      break;
    case 16:
      if (NumElts == 4)
        Opc = AArch64::FRINTZv4f16;
      else if (NumElts == 8)
        Opc = AArch64::FRINTZv8f16;
      break;
    case 32:
      if (NumElts == 2)
        Opc = AArch64::FRINTZv2f32;
      else if (NumElts == 4)
        Opc = AArch64::FRINTZv4f32;
      break;
    case 64:
      if (NumElts == 2)
        Opc = AArch64::FRINTZv2f64;
      break;
    }
  }

  if (!Opc) {
    // Didn't get an opcode above, bail.
    LLVM_DEBUG(dbgs() << "Unsupported type for G_INTRINSIC_TRUNC!\n");
    return false;
  }

  // Legalization would have set us up perfectly for this; we just need to
  // set the opcode and move on.
  I.setDesc(TII.get(Opc));
  return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
}

bool AArch64InstructionSelector::selectIntrinsicRound(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  const LLT SrcTy = MRI.getType(I.getOperand(0).getReg());

  // Select the correct opcode.
  unsigned Opc = 0;
  if (!SrcTy.isVector()) {
    switch (SrcTy.getSizeInBits()) {
    default:
    case 16:
      Opc = AArch64::FRINTAHr;
      break;
    case 32:
      Opc = AArch64::FRINTASr;
      break;
    case 64:
      Opc = AArch64::FRINTADr;
      break;
    }
  } else {
    unsigned NumElts = SrcTy.getNumElements();
    switch (SrcTy.getElementType().getSizeInBits()) {
    default:
      break;
    case 16:
      if (NumElts == 4)
        Opc = AArch64::FRINTAv4f16;
      else if (NumElts == 8)
        Opc = AArch64::FRINTAv8f16;
      break;
    case 32:
      if (NumElts == 2)
        Opc = AArch64::FRINTAv2f32;
      else if (NumElts == 4)
        Opc = AArch64::FRINTAv4f32;
      break;
    case 64:
      if (NumElts == 2)
        Opc = AArch64::FRINTAv2f64;
      break;
    }
  }

  if (!Opc) {
    // Didn't get an opcode above, bail.
    LLVM_DEBUG(dbgs() << "Unsupported type for G_INTRINSIC_ROUND!\n");
    return false;
  }

  // Legalization would have set us up perfectly for this; we just need to
  // set the opcode and move on.
  I.setDesc(TII.get(Opc));
  return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
}

bool AArch64InstructionSelector::selectVectorICmp(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  Register DstReg = I.getOperand(0).getReg();
  LLT DstTy = MRI.getType(DstReg);
  Register SrcReg = I.getOperand(2).getReg();
  Register Src2Reg = I.getOperand(3).getReg();
  LLT SrcTy = MRI.getType(SrcReg);

  unsigned SrcEltSize = SrcTy.getElementType().getSizeInBits();
  unsigned NumElts = DstTy.getNumElements();

  // First index is element size, 0 == 8b, 1 == 16b, 2 == 32b, 3 == 64b
  // Second index is num elts, 0 == v2, 1 == v4, 2 == v8, 3 == v16
  // Third index is cc opcode:
  // 0 == eq
  // 1 == ugt
  // 2 == uge
  // 3 == ult
  // 4 == ule
  // 5 == sgt
  // 6 == sge
  // 7 == slt
  // 8 == sle
  // ne is done by negating 'eq' result.

  // This table below assumes that for some comparisons the operands will be
  // commuted.
  // ult op == commute + ugt op
  // ule op == commute + uge op
  // slt op == commute + sgt op
  // sle op == commute + sge op
  unsigned PredIdx = 0;
  bool SwapOperands = false;
  CmpInst::Predicate Pred = (CmpInst::Predicate)I.getOperand(1).getPredicate();
  switch (Pred) {
  case CmpInst::ICMP_NE:
  case CmpInst::ICMP_EQ:
    PredIdx = 0;
    break;
  case CmpInst::ICMP_UGT:
    PredIdx = 1;
    break;
  case CmpInst::ICMP_UGE:
    PredIdx = 2;
    break;
  case CmpInst::ICMP_ULT:
    PredIdx = 3;
    SwapOperands = true;
    break;
  case CmpInst::ICMP_ULE:
    PredIdx = 4;
    SwapOperands = true;
    break;
  case CmpInst::ICMP_SGT:
    PredIdx = 5;
    break;
  case CmpInst::ICMP_SGE:
    PredIdx = 6;
    break;
  case CmpInst::ICMP_SLT:
    PredIdx = 7;
    SwapOperands = true;
    break;
  case CmpInst::ICMP_SLE:
    PredIdx = 8;
    SwapOperands = true;
    break;
  default:
    llvm_unreachable("Unhandled icmp predicate");
    return false;
  }

  // This table obviously should be tablegen'd when we have our GISel native
  // tablegen selector.

  static const unsigned OpcTable[4][4][9] = {
      {
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */},
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */},
          {AArch64::CMEQv8i8, AArch64::CMHIv8i8, AArch64::CMHSv8i8,
           AArch64::CMHIv8i8, AArch64::CMHSv8i8, AArch64::CMGTv8i8,
           AArch64::CMGEv8i8, AArch64::CMGTv8i8, AArch64::CMGEv8i8},
          {AArch64::CMEQv16i8, AArch64::CMHIv16i8, AArch64::CMHSv16i8,
           AArch64::CMHIv16i8, AArch64::CMHSv16i8, AArch64::CMGTv16i8,
           AArch64::CMGEv16i8, AArch64::CMGTv16i8, AArch64::CMGEv16i8}
      },
      {
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */},
          {AArch64::CMEQv4i16, AArch64::CMHIv4i16, AArch64::CMHSv4i16,
           AArch64::CMHIv4i16, AArch64::CMHSv4i16, AArch64::CMGTv4i16,
           AArch64::CMGEv4i16, AArch64::CMGTv4i16, AArch64::CMGEv4i16},
          {AArch64::CMEQv8i16, AArch64::CMHIv8i16, AArch64::CMHSv8i16,
           AArch64::CMHIv8i16, AArch64::CMHSv8i16, AArch64::CMGTv8i16,
           AArch64::CMGEv8i16, AArch64::CMGTv8i16, AArch64::CMGEv8i16},
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */}
      },
      {
          {AArch64::CMEQv2i32, AArch64::CMHIv2i32, AArch64::CMHSv2i32,
           AArch64::CMHIv2i32, AArch64::CMHSv2i32, AArch64::CMGTv2i32,
           AArch64::CMGEv2i32, AArch64::CMGTv2i32, AArch64::CMGEv2i32},
          {AArch64::CMEQv4i32, AArch64::CMHIv4i32, AArch64::CMHSv4i32,
           AArch64::CMHIv4i32, AArch64::CMHSv4i32, AArch64::CMGTv4i32,
           AArch64::CMGEv4i32, AArch64::CMGTv4i32, AArch64::CMGEv4i32},
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */},
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */}
      },
      {
          {AArch64::CMEQv2i64, AArch64::CMHIv2i64, AArch64::CMHSv2i64,
           AArch64::CMHIv2i64, AArch64::CMHSv2i64, AArch64::CMGTv2i64,
           AArch64::CMGEv2i64, AArch64::CMGTv2i64, AArch64::CMGEv2i64},
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */},
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */},
          {0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */, 0 /* invalid */, 0 /* invalid */, 0 /* invalid */,
           0 /* invalid */}
      },
  };
  unsigned EltIdx = Log2_32(SrcEltSize / 8);
  unsigned NumEltsIdx = Log2_32(NumElts / 2);
  unsigned Opc = OpcTable[EltIdx][NumEltsIdx][PredIdx];
  if (!Opc) {
    LLVM_DEBUG(dbgs() << "Could not map G_ICMP to cmp opcode");
    return false;
  }

  const RegisterBank &VecRB = *RBI.getRegBank(SrcReg, MRI, TRI);
  const TargetRegisterClass *SrcRC =
      getRegClassForTypeOnBank(SrcTy, VecRB, RBI, true);
  if (!SrcRC) {
    LLVM_DEBUG(dbgs() << "Could not determine source register class.\n");
    return false;
  }

  unsigned NotOpc = Pred == ICmpInst::ICMP_NE ? AArch64::NOTv8i8 : 0;
  if (SrcTy.getSizeInBits() == 128)
    NotOpc = NotOpc ? AArch64::NOTv16i8 : 0;

  if (SwapOperands)
    std::swap(SrcReg, Src2Reg);

  MachineIRBuilder MIB(I);
  auto Cmp = MIB.buildInstr(Opc, {SrcRC}, {SrcReg, Src2Reg});
  constrainSelectedInstRegOperands(*Cmp, TII, TRI, RBI);

  // Invert if we had a 'ne' cc.
  if (NotOpc) {
    Cmp = MIB.buildInstr(NotOpc, {DstReg}, {Cmp});
    constrainSelectedInstRegOperands(*Cmp, TII, TRI, RBI);
  } else {
    MIB.buildCopy(DstReg, Cmp.getReg(0));
  }
  RBI.constrainGenericRegister(DstReg, *SrcRC, MRI);
  I.eraseFromParent();
  return true;
}

MachineInstr *AArch64InstructionSelector::emitScalarToVector(
    unsigned EltSize, const TargetRegisterClass *DstRC, Register Scalar,
    MachineIRBuilder &MIRBuilder) const {
  auto Undef = MIRBuilder.buildInstr(TargetOpcode::IMPLICIT_DEF, {DstRC}, {});

  auto BuildFn = [&](unsigned SubregIndex) {
    auto Ins =
        MIRBuilder
            .buildInstr(TargetOpcode::INSERT_SUBREG, {DstRC}, {Undef, Scalar})
            .addImm(SubregIndex);
    constrainSelectedInstRegOperands(*Undef, TII, TRI, RBI);
    constrainSelectedInstRegOperands(*Ins, TII, TRI, RBI);
    return &*Ins;
  };

  switch (EltSize) {
  case 16:
    return BuildFn(AArch64::hsub);
  case 32:
    return BuildFn(AArch64::ssub);
  case 64:
    return BuildFn(AArch64::dsub);
  default:
    return nullptr;
  }
}

bool AArch64InstructionSelector::selectMergeValues(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_MERGE_VALUES && "unexpected opcode");
  const LLT DstTy = MRI.getType(I.getOperand(0).getReg());
  const LLT SrcTy = MRI.getType(I.getOperand(1).getReg());
  assert(!DstTy.isVector() && !SrcTy.isVector() && "invalid merge operation");
  const RegisterBank &RB = *RBI.getRegBank(I.getOperand(1).getReg(), MRI, TRI);

  if (I.getNumOperands() != 3)
    return false;

  // Merging 2 s64s into an s128.
  if (DstTy == LLT::scalar(128)) {
    if (SrcTy.getSizeInBits() != 64)
      return false;
    MachineIRBuilder MIB(I);
    Register DstReg = I.getOperand(0).getReg();
    Register Src1Reg = I.getOperand(1).getReg();
    Register Src2Reg = I.getOperand(2).getReg();
    auto Tmp = MIB.buildInstr(TargetOpcode::IMPLICIT_DEF, {DstTy}, {});
    MachineInstr *InsMI =
        emitLaneInsert(None, Tmp.getReg(0), Src1Reg, /* LaneIdx */ 0, RB, MIB);
    if (!InsMI)
      return false;
    MachineInstr *Ins2MI = emitLaneInsert(DstReg, InsMI->getOperand(0).getReg(),
                                          Src2Reg, /* LaneIdx */ 1, RB, MIB);
    if (!Ins2MI)
      return false;
    constrainSelectedInstRegOperands(*InsMI, TII, TRI, RBI);
    constrainSelectedInstRegOperands(*Ins2MI, TII, TRI, RBI);
    I.eraseFromParent();
    return true;
  }

  if (RB.getID() != AArch64::GPRRegBankID)
    return false;

  if (DstTy.getSizeInBits() != 64 || SrcTy.getSizeInBits() != 32)
    return false;

  auto *DstRC = &AArch64::GPR64RegClass;
  Register SubToRegDef = MRI.createVirtualRegister(DstRC);
  MachineInstr &SubRegMI = *BuildMI(*I.getParent(), I, I.getDebugLoc(),
                                    TII.get(TargetOpcode::SUBREG_TO_REG))
                                .addDef(SubToRegDef)
                                .addImm(0)
                                .addUse(I.getOperand(1).getReg())
                                .addImm(AArch64::sub_32);
  Register SubToRegDef2 = MRI.createVirtualRegister(DstRC);
  // Need to anyext the second scalar before we can use bfm
  MachineInstr &SubRegMI2 = *BuildMI(*I.getParent(), I, I.getDebugLoc(),
                                    TII.get(TargetOpcode::SUBREG_TO_REG))
                                .addDef(SubToRegDef2)
                                .addImm(0)
                                .addUse(I.getOperand(2).getReg())
                                .addImm(AArch64::sub_32);
  MachineInstr &BFM =
      *BuildMI(*I.getParent(), I, I.getDebugLoc(), TII.get(AArch64::BFMXri))
           .addDef(I.getOperand(0).getReg())
           .addUse(SubToRegDef)
           .addUse(SubToRegDef2)
           .addImm(32)
           .addImm(31);
  constrainSelectedInstRegOperands(SubRegMI, TII, TRI, RBI);
  constrainSelectedInstRegOperands(SubRegMI2, TII, TRI, RBI);
  constrainSelectedInstRegOperands(BFM, TII, TRI, RBI);
  I.eraseFromParent();
  return true;
}

static bool getLaneCopyOpcode(unsigned &CopyOpc, unsigned &ExtractSubReg,
                              const unsigned EltSize) {
  // Choose a lane copy opcode and subregister based off of the size of the
  // vector's elements.
  switch (EltSize) {
  case 16:
    CopyOpc = AArch64::CPYi16;
    ExtractSubReg = AArch64::hsub;
    break;
  case 32:
    CopyOpc = AArch64::CPYi32;
    ExtractSubReg = AArch64::ssub;
    break;
  case 64:
    CopyOpc = AArch64::CPYi64;
    ExtractSubReg = AArch64::dsub;
    break;
  default:
    // Unknown size, bail out.
    LLVM_DEBUG(dbgs() << "Elt size '" << EltSize << "' unsupported.\n");
    return false;
  }
  return true;
}

MachineInstr *AArch64InstructionSelector::emitExtractVectorElt(
    Optional<Register> DstReg, const RegisterBank &DstRB, LLT ScalarTy,
    Register VecReg, unsigned LaneIdx, MachineIRBuilder &MIRBuilder) const {
  MachineRegisterInfo &MRI = *MIRBuilder.getMRI();
  unsigned CopyOpc = 0;
  unsigned ExtractSubReg = 0;
  if (!getLaneCopyOpcode(CopyOpc, ExtractSubReg, ScalarTy.getSizeInBits())) {
    LLVM_DEBUG(
        dbgs() << "Couldn't determine lane copy opcode for instruction.\n");
    return nullptr;
  }

  const TargetRegisterClass *DstRC =
      getRegClassForTypeOnBank(ScalarTy, DstRB, RBI, true);
  if (!DstRC) {
    LLVM_DEBUG(dbgs() << "Could not determine destination register class.\n");
    return nullptr;
  }

  const RegisterBank &VecRB = *RBI.getRegBank(VecReg, MRI, TRI);
  const LLT &VecTy = MRI.getType(VecReg);
  const TargetRegisterClass *VecRC =
      getRegClassForTypeOnBank(VecTy, VecRB, RBI, true);
  if (!VecRC) {
    LLVM_DEBUG(dbgs() << "Could not determine source register class.\n");
    return nullptr;
  }

  // The register that we're going to copy into.
  Register InsertReg = VecReg;
  if (!DstReg)
    DstReg = MRI.createVirtualRegister(DstRC);
  // If the lane index is 0, we just use a subregister COPY.
  if (LaneIdx == 0) {
    auto Copy = MIRBuilder.buildInstr(TargetOpcode::COPY, {*DstReg}, {})
                    .addReg(VecReg, 0, ExtractSubReg);
    RBI.constrainGenericRegister(*DstReg, *DstRC, MRI);
    return &*Copy;
  }

  // Lane copies require 128-bit wide registers. If we're dealing with an
  // unpacked vector, then we need to move up to that width. Insert an implicit
  // def and a subregister insert to get us there.
  if (VecTy.getSizeInBits() != 128) {
    MachineInstr *ScalarToVector = emitScalarToVector(
        VecTy.getSizeInBits(), &AArch64::FPR128RegClass, VecReg, MIRBuilder);
    if (!ScalarToVector)
      return nullptr;
    InsertReg = ScalarToVector->getOperand(0).getReg();
  }

  MachineInstr *LaneCopyMI =
      MIRBuilder.buildInstr(CopyOpc, {*DstReg}, {InsertReg}).addImm(LaneIdx);
  constrainSelectedInstRegOperands(*LaneCopyMI, TII, TRI, RBI);

  // Make sure that we actually constrain the initial copy.
  RBI.constrainGenericRegister(*DstReg, *DstRC, MRI);
  return LaneCopyMI;
}

bool AArch64InstructionSelector::selectExtractElt(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_EXTRACT_VECTOR_ELT &&
         "unexpected opcode!");
  Register DstReg = I.getOperand(0).getReg();
  const LLT NarrowTy = MRI.getType(DstReg);
  const Register SrcReg = I.getOperand(1).getReg();
  const LLT WideTy = MRI.getType(SrcReg);
  (void)WideTy;
  assert(WideTy.getSizeInBits() >= NarrowTy.getSizeInBits() &&
         "source register size too small!");
  assert(NarrowTy.isScalar() && "cannot extract vector into vector!");

  // Need the lane index to determine the correct copy opcode.
  MachineOperand &LaneIdxOp = I.getOperand(2);
  assert(LaneIdxOp.isReg() && "Lane index operand was not a register?");

  if (RBI.getRegBank(DstReg, MRI, TRI)->getID() != AArch64::FPRRegBankID) {
    LLVM_DEBUG(dbgs() << "Cannot extract into GPR.\n");
    return false;
  }

  // Find the index to extract from.
  auto VRegAndVal = getConstantVRegValWithLookThrough(LaneIdxOp.getReg(), MRI);
  if (!VRegAndVal)
    return false;
  unsigned LaneIdx = VRegAndVal->Value;

  MachineIRBuilder MIRBuilder(I);

  const RegisterBank &DstRB = *RBI.getRegBank(DstReg, MRI, TRI);
  MachineInstr *Extract = emitExtractVectorElt(DstReg, DstRB, NarrowTy, SrcReg,
                                               LaneIdx, MIRBuilder);
  if (!Extract)
    return false;

  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectSplitVectorUnmerge(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  unsigned NumElts = I.getNumOperands() - 1;
  Register SrcReg = I.getOperand(NumElts).getReg();
  const LLT NarrowTy = MRI.getType(I.getOperand(0).getReg());
  const LLT SrcTy = MRI.getType(SrcReg);

  assert(NarrowTy.isVector() && "Expected an unmerge into vectors");
  if (SrcTy.getSizeInBits() > 128) {
    LLVM_DEBUG(dbgs() << "Unexpected vector type for vec split unmerge");
    return false;
  }

  MachineIRBuilder MIB(I);

  // We implement a split vector operation by treating the sub-vectors as
  // scalars and extracting them.
  const RegisterBank &DstRB =
      *RBI.getRegBank(I.getOperand(0).getReg(), MRI, TRI);
  for (unsigned OpIdx = 0; OpIdx < NumElts; ++OpIdx) {
    Register Dst = I.getOperand(OpIdx).getReg();
    MachineInstr *Extract =
        emitExtractVectorElt(Dst, DstRB, NarrowTy, SrcReg, OpIdx, MIB);
    if (!Extract)
      return false;
  }
  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectUnmergeValues(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_UNMERGE_VALUES &&
         "unexpected opcode");

  // TODO: Handle unmerging into GPRs and from scalars to scalars.
  if (RBI.getRegBank(I.getOperand(0).getReg(), MRI, TRI)->getID() !=
          AArch64::FPRRegBankID ||
      RBI.getRegBank(I.getOperand(1).getReg(), MRI, TRI)->getID() !=
          AArch64::FPRRegBankID) {
    LLVM_DEBUG(dbgs() << "Unmerging vector-to-gpr and scalar-to-scalar "
                         "currently unsupported.\n");
    return false;
  }

  // The last operand is the vector source register, and every other operand is
  // a register to unpack into.
  unsigned NumElts = I.getNumOperands() - 1;
  Register SrcReg = I.getOperand(NumElts).getReg();
  const LLT NarrowTy = MRI.getType(I.getOperand(0).getReg());
  const LLT WideTy = MRI.getType(SrcReg);
  (void)WideTy;
  assert(WideTy.isVector() && "can only unmerge from vector types!");
  assert(WideTy.getSizeInBits() > NarrowTy.getSizeInBits() &&
         "source register size too small!");

  if (!NarrowTy.isScalar())
    return selectSplitVectorUnmerge(I, MRI);

  MachineIRBuilder MIB(I);

  // Choose a lane copy opcode and subregister based off of the size of the
  // vector's elements.
  unsigned CopyOpc = 0;
  unsigned ExtractSubReg = 0;
  if (!getLaneCopyOpcode(CopyOpc, ExtractSubReg, NarrowTy.getSizeInBits()))
    return false;

  // Set up for the lane copies.
  MachineBasicBlock &MBB = *I.getParent();

  // Stores the registers we'll be copying from.
  SmallVector<Register, 4> InsertRegs;

  // We'll use the first register twice, so we only need NumElts-1 registers.
  unsigned NumInsertRegs = NumElts - 1;

  // If our elements fit into exactly 128 bits, then we can copy from the source
  // directly. Otherwise, we need to do a bit of setup with some subregister
  // inserts.
  if (NarrowTy.getSizeInBits() * NumElts == 128) {
    InsertRegs = SmallVector<Register, 4>(NumInsertRegs, SrcReg);
  } else {
    // No. We have to perform subregister inserts. For each insert, create an
    // implicit def and a subregister insert, and save the register we create.
    for (unsigned Idx = 0; Idx < NumInsertRegs; ++Idx) {
      Register ImpDefReg = MRI.createVirtualRegister(&AArch64::FPR128RegClass);
      MachineInstr &ImpDefMI =
          *BuildMI(MBB, I, I.getDebugLoc(), TII.get(TargetOpcode::IMPLICIT_DEF),
                   ImpDefReg);

      // Now, create the subregister insert from SrcReg.
      Register InsertReg = MRI.createVirtualRegister(&AArch64::FPR128RegClass);
      MachineInstr &InsMI =
          *BuildMI(MBB, I, I.getDebugLoc(),
                   TII.get(TargetOpcode::INSERT_SUBREG), InsertReg)
               .addUse(ImpDefReg)
               .addUse(SrcReg)
               .addImm(AArch64::dsub);

      constrainSelectedInstRegOperands(ImpDefMI, TII, TRI, RBI);
      constrainSelectedInstRegOperands(InsMI, TII, TRI, RBI);

      // Save the register so that we can copy from it after.
      InsertRegs.push_back(InsertReg);
    }
  }

  // Now that we've created any necessary subregister inserts, we can
  // create the copies.
  //
  // Perform the first copy separately as a subregister copy.
  Register CopyTo = I.getOperand(0).getReg();
  auto FirstCopy = MIB.buildInstr(TargetOpcode::COPY, {CopyTo}, {})
                       .addReg(InsertRegs[0], 0, ExtractSubReg);
  constrainSelectedInstRegOperands(*FirstCopy, TII, TRI, RBI);

  // Now, perform the remaining copies as vector lane copies.
  unsigned LaneIdx = 1;
  for (Register InsReg : InsertRegs) {
    Register CopyTo = I.getOperand(LaneIdx).getReg();
    MachineInstr &CopyInst =
        *BuildMI(MBB, I, I.getDebugLoc(), TII.get(CopyOpc), CopyTo)
             .addUse(InsReg)
             .addImm(LaneIdx);
    constrainSelectedInstRegOperands(CopyInst, TII, TRI, RBI);
    ++LaneIdx;
  }

  // Separately constrain the first copy's destination. Because of the
  // limitation in constrainOperandRegClass, we can't guarantee that this will
  // actually be constrained. So, do it ourselves using the second operand.
  const TargetRegisterClass *RC =
      MRI.getRegClassOrNull(I.getOperand(1).getReg());
  if (!RC) {
    LLVM_DEBUG(dbgs() << "Couldn't constrain copy destination.\n");
    return false;
  }

  RBI.constrainGenericRegister(CopyTo, *RC, MRI);
  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectConcatVectors(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_CONCAT_VECTORS &&
         "Unexpected opcode");
  Register Dst = I.getOperand(0).getReg();
  Register Op1 = I.getOperand(1).getReg();
  Register Op2 = I.getOperand(2).getReg();
  MachineIRBuilder MIRBuilder(I);
  MachineInstr *ConcatMI = emitVectorConcat(Dst, Op1, Op2, MIRBuilder);
  if (!ConcatMI)
    return false;
  I.eraseFromParent();
  return true;
}

void AArch64InstructionSelector::collectShuffleMaskIndices(
    MachineInstr &I, MachineRegisterInfo &MRI,
    SmallVectorImpl<Optional<int>> &Idxs) const {
  MachineInstr *MaskDef = MRI.getVRegDef(I.getOperand(3).getReg());
  assert(
      MaskDef->getOpcode() == TargetOpcode::G_BUILD_VECTOR &&
      "G_SHUFFLE_VECTOR should have a constant mask operand as G_BUILD_VECTOR");
  // Find the constant indices.
  for (unsigned i = 1, e = MaskDef->getNumOperands(); i < e; ++i) {
    // Look through copies.
    MachineInstr *ScalarDef =
        getDefIgnoringCopies(MaskDef->getOperand(i).getReg(), MRI);
    assert(ScalarDef && "Could not find vreg def of shufflevec index op");
    if (ScalarDef->getOpcode() != TargetOpcode::G_CONSTANT) {
      // This be an undef if not a constant.
      assert(ScalarDef->getOpcode() == TargetOpcode::G_IMPLICIT_DEF);
      Idxs.push_back(None);
    } else {
      Idxs.push_back(ScalarDef->getOperand(1).getCImm()->getSExtValue());
    }
  }
}

unsigned
AArch64InstructionSelector::emitConstantPoolEntry(Constant *CPVal,
                                                  MachineFunction &MF) const {
  Type *CPTy = CPVal->getType();
  unsigned Align = MF.getDataLayout().getPrefTypeAlignment(CPTy);
  if (Align == 0)
    Align = MF.getDataLayout().getTypeAllocSize(CPTy);

  MachineConstantPool *MCP = MF.getConstantPool();
  return MCP->getConstantPoolIndex(CPVal, Align);
}

MachineInstr *AArch64InstructionSelector::emitLoadFromConstantPool(
    Constant *CPVal, MachineIRBuilder &MIRBuilder) const {
  unsigned CPIdx = emitConstantPoolEntry(CPVal, MIRBuilder.getMF());

  auto Adrp =
      MIRBuilder.buildInstr(AArch64::ADRP, {&AArch64::GPR64RegClass}, {})
          .addConstantPoolIndex(CPIdx, 0, AArch64II::MO_PAGE);

  MachineInstr *LoadMI = nullptr;
  switch (MIRBuilder.getDataLayout().getTypeStoreSize(CPVal->getType())) {
  case 16:
    LoadMI =
        &*MIRBuilder
              .buildInstr(AArch64::LDRQui, {&AArch64::FPR128RegClass}, {Adrp})
              .addConstantPoolIndex(CPIdx, 0,
                                    AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
    break;
  case 8:
    LoadMI = &*MIRBuilder
                 .buildInstr(AArch64::LDRDui, {&AArch64::FPR64RegClass}, {Adrp})
                 .addConstantPoolIndex(
                     CPIdx, 0, AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
    break;
  default:
    LLVM_DEBUG(dbgs() << "Could not load from constant pool of type "
                      << *CPVal->getType());
    return nullptr;
  }
  constrainSelectedInstRegOperands(*Adrp, TII, TRI, RBI);
  constrainSelectedInstRegOperands(*LoadMI, TII, TRI, RBI);
  return LoadMI;
}

/// Return an <Opcode, SubregIndex> pair to do an vector elt insert of a given
/// size and RB.
static std::pair<unsigned, unsigned>
getInsertVecEltOpInfo(const RegisterBank &RB, unsigned EltSize) {
  unsigned Opc, SubregIdx;
  if (RB.getID() == AArch64::GPRRegBankID) {
    if (EltSize == 32) {
      Opc = AArch64::INSvi32gpr;
      SubregIdx = AArch64::ssub;
    } else if (EltSize == 64) {
      Opc = AArch64::INSvi64gpr;
      SubregIdx = AArch64::dsub;
    } else {
      llvm_unreachable("invalid elt size!");
    }
  } else {
    if (EltSize == 8) {
      Opc = AArch64::INSvi8lane;
      SubregIdx = AArch64::bsub;
    } else if (EltSize == 16) {
      Opc = AArch64::INSvi16lane;
      SubregIdx = AArch64::hsub;
    } else if (EltSize == 32) {
      Opc = AArch64::INSvi32lane;
      SubregIdx = AArch64::ssub;
    } else if (EltSize == 64) {
      Opc = AArch64::INSvi64lane;
      SubregIdx = AArch64::dsub;
    } else {
      llvm_unreachable("invalid elt size!");
    }
  }
  return std::make_pair(Opc, SubregIdx);
}

MachineInstr *
AArch64InstructionSelector::emitADD(Register DefReg, MachineOperand &LHS,
                                    MachineOperand &RHS,
                                    MachineIRBuilder &MIRBuilder) const {
  assert(LHS.isReg() && RHS.isReg() && "Expected LHS and RHS to be registers!");
  MachineRegisterInfo &MRI = MIRBuilder.getMF().getRegInfo();
  static const unsigned OpcTable[2][2]{{AArch64::ADDXrr, AArch64::ADDXri},
                                       {AArch64::ADDWrr, AArch64::ADDWri}};
  bool Is32Bit = MRI.getType(LHS.getReg()).getSizeInBits() == 32;
  auto ImmFns = selectArithImmed(RHS);
  unsigned Opc = OpcTable[Is32Bit][ImmFns.hasValue()];
  auto AddMI = MIRBuilder.buildInstr(Opc, {DefReg}, {LHS.getReg()});

  // If we matched a valid constant immediate, add those operands.
  if (ImmFns) {
    for (auto &RenderFn : *ImmFns)
      RenderFn(AddMI);
  } else {
    AddMI.addUse(RHS.getReg());
  }

  constrainSelectedInstRegOperands(*AddMI, TII, TRI, RBI);
  return &*AddMI;
}

MachineInstr *
AArch64InstructionSelector::emitCMN(MachineOperand &LHS, MachineOperand &RHS,
                                    MachineIRBuilder &MIRBuilder) const {
  assert(LHS.isReg() && RHS.isReg() && "Expected LHS and RHS to be registers!");
  MachineRegisterInfo &MRI = MIRBuilder.getMF().getRegInfo();
  static const unsigned OpcTable[2][2]{{AArch64::ADDSXrr, AArch64::ADDSXri},
                                       {AArch64::ADDSWrr, AArch64::ADDSWri}};
  bool Is32Bit = (MRI.getType(LHS.getReg()).getSizeInBits() == 32);
  auto ImmFns = selectArithImmed(RHS);
  unsigned Opc = OpcTable[Is32Bit][ImmFns.hasValue()];
  Register ZReg = Is32Bit ? AArch64::WZR : AArch64::XZR;

  auto CmpMI = MIRBuilder.buildInstr(Opc, {ZReg}, {LHS.getReg()});

  // If we matched a valid constant immediate, add those operands.
  if (ImmFns) {
    for (auto &RenderFn : *ImmFns)
      RenderFn(CmpMI);
  } else {
    CmpMI.addUse(RHS.getReg());
  }

  constrainSelectedInstRegOperands(*CmpMI, TII, TRI, RBI);
  return &*CmpMI;
}

MachineInstr *
AArch64InstructionSelector::emitTST(const Register &LHS, const Register &RHS,
                                    MachineIRBuilder &MIRBuilder) const {
  MachineRegisterInfo &MRI = MIRBuilder.getMF().getRegInfo();
  unsigned RegSize = MRI.getType(LHS).getSizeInBits();
  bool Is32Bit = (RegSize == 32);
  static const unsigned OpcTable[2][2]{{AArch64::ANDSXrr, AArch64::ANDSXri},
                                       {AArch64::ANDSWrr, AArch64::ANDSWri}};
  Register ZReg = Is32Bit ? AArch64::WZR : AArch64::XZR;

  // We might be able to fold in an immediate into the TST. We need to make sure
  // it's a logical immediate though, since ANDS requires that.
  auto ValAndVReg = getConstantVRegValWithLookThrough(RHS, MRI);
  bool IsImmForm = ValAndVReg.hasValue() &&
                   AArch64_AM::isLogicalImmediate(ValAndVReg->Value, RegSize);
  unsigned Opc = OpcTable[Is32Bit][IsImmForm];
  auto TstMI = MIRBuilder.buildInstr(Opc, {ZReg}, {LHS});

  if (IsImmForm)
    TstMI.addImm(
        AArch64_AM::encodeLogicalImmediate(ValAndVReg->Value, RegSize));
  else
    TstMI.addUse(RHS);

  constrainSelectedInstRegOperands(*TstMI, TII, TRI, RBI);
  return &*TstMI;
}

MachineInstr *AArch64InstructionSelector::emitIntegerCompare(
    MachineOperand &LHS, MachineOperand &RHS, MachineOperand &Predicate,
    MachineIRBuilder &MIRBuilder) const {
  assert(LHS.isReg() && RHS.isReg() && "Expected LHS and RHS to be registers!");
  MachineRegisterInfo &MRI = MIRBuilder.getMF().getRegInfo();

  // Fold the compare if possible.
  MachineInstr *FoldCmp =
      tryFoldIntegerCompare(LHS, RHS, Predicate, MIRBuilder);
  if (FoldCmp)
    return FoldCmp;

  // Can't fold into a CMN. Just emit a normal compare.
  unsigned CmpOpc = 0;
  Register ZReg;

  LLT CmpTy = MRI.getType(LHS.getReg());
  assert((CmpTy.isScalar() || CmpTy.isPointer()) &&
         "Expected scalar or pointer");
  if (CmpTy == LLT::scalar(32)) {
    CmpOpc = AArch64::SUBSWrr;
    ZReg = AArch64::WZR;
  } else if (CmpTy == LLT::scalar(64) || CmpTy.isPointer()) {
    CmpOpc = AArch64::SUBSXrr;
    ZReg = AArch64::XZR;
  } else {
    return nullptr;
  }

  // Try to match immediate forms.
  auto ImmFns = selectArithImmed(RHS);
  if (ImmFns)
    CmpOpc = CmpOpc == AArch64::SUBSWrr ? AArch64::SUBSWri : AArch64::SUBSXri;

  auto CmpMI = MIRBuilder.buildInstr(CmpOpc).addDef(ZReg).addUse(LHS.getReg());
  // If we matched a valid constant immediate, add those operands.
  if (ImmFns) {
    for (auto &RenderFn : *ImmFns)
      RenderFn(CmpMI);
  } else {
    CmpMI.addUse(RHS.getReg());
  }

  // Make sure that we can constrain the compare that we emitted.
  constrainSelectedInstRegOperands(*CmpMI, TII, TRI, RBI);
  return &*CmpMI;
}

MachineInstr *AArch64InstructionSelector::emitVectorConcat(
    Optional<Register> Dst, Register Op1, Register Op2,
    MachineIRBuilder &MIRBuilder) const {
  // We implement a vector concat by:
  // 1. Use scalar_to_vector to insert the lower vector into the larger dest
  // 2. Insert the upper vector into the destination's upper element
  // TODO: some of this code is common with G_BUILD_VECTOR handling.
  MachineRegisterInfo &MRI = MIRBuilder.getMF().getRegInfo();

  const LLT Op1Ty = MRI.getType(Op1);
  const LLT Op2Ty = MRI.getType(Op2);

  if (Op1Ty != Op2Ty) {
    LLVM_DEBUG(dbgs() << "Could not do vector concat of differing vector tys");
    return nullptr;
  }
  assert(Op1Ty.isVector() && "Expected a vector for vector concat");

  if (Op1Ty.getSizeInBits() >= 128) {
    LLVM_DEBUG(dbgs() << "Vector concat not supported for full size vectors");
    return nullptr;
  }

  // At the moment we just support 64 bit vector concats.
  if (Op1Ty.getSizeInBits() != 64) {
    LLVM_DEBUG(dbgs() << "Vector concat supported for 64b vectors");
    return nullptr;
  }

  const LLT ScalarTy = LLT::scalar(Op1Ty.getSizeInBits());
  const RegisterBank &FPRBank = *RBI.getRegBank(Op1, MRI, TRI);
  const TargetRegisterClass *DstRC =
      getMinClassForRegBank(FPRBank, Op1Ty.getSizeInBits() * 2);

  MachineInstr *WidenedOp1 =
      emitScalarToVector(ScalarTy.getSizeInBits(), DstRC, Op1, MIRBuilder);
  MachineInstr *WidenedOp2 =
      emitScalarToVector(ScalarTy.getSizeInBits(), DstRC, Op2, MIRBuilder);
  if (!WidenedOp1 || !WidenedOp2) {
    LLVM_DEBUG(dbgs() << "Could not emit a vector from scalar value");
    return nullptr;
  }

  // Now do the insert of the upper element.
  unsigned InsertOpc, InsSubRegIdx;
  std::tie(InsertOpc, InsSubRegIdx) =
      getInsertVecEltOpInfo(FPRBank, ScalarTy.getSizeInBits());

  if (!Dst)
    Dst = MRI.createVirtualRegister(DstRC);
  auto InsElt =
      MIRBuilder
          .buildInstr(InsertOpc, {*Dst}, {WidenedOp1->getOperand(0).getReg()})
          .addImm(1) /* Lane index */
          .addUse(WidenedOp2->getOperand(0).getReg())
          .addImm(0);
  constrainSelectedInstRegOperands(*InsElt, TII, TRI, RBI);
  return &*InsElt;
}

MachineInstr *AArch64InstructionSelector::emitFMovForFConstant(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_FCONSTANT &&
         "Expected a G_FCONSTANT!");
  MachineOperand &ImmOp = I.getOperand(1);
  unsigned DefSize = MRI.getType(I.getOperand(0).getReg()).getSizeInBits();

  // Only handle 32 and 64 bit defs for now.
  if (DefSize != 32 && DefSize != 64)
    return nullptr;

  // Don't handle null values using FMOV.
  if (ImmOp.getFPImm()->isNullValue())
    return nullptr;

  // Get the immediate representation for the FMOV.
  const APFloat &ImmValAPF = ImmOp.getFPImm()->getValueAPF();
  int Imm = DefSize == 32 ? AArch64_AM::getFP32Imm(ImmValAPF)
                          : AArch64_AM::getFP64Imm(ImmValAPF);

  // If this is -1, it means the immediate can't be represented as the requested
  // floating point value. Bail.
  if (Imm == -1)
    return nullptr;

  // Update MI to represent the new FMOV instruction, constrain it, and return.
  ImmOp.ChangeToImmediate(Imm);
  unsigned MovOpc = DefSize == 32 ? AArch64::FMOVSi : AArch64::FMOVDi;
  I.setDesc(TII.get(MovOpc));
  constrainSelectedInstRegOperands(I, TII, TRI, RBI);
  return &I;
}

MachineInstr *
AArch64InstructionSelector::emitCSetForICMP(Register DefReg, unsigned Pred,
                                     MachineIRBuilder &MIRBuilder) const {
  // CSINC increments the result when the predicate is false. Invert it.
  const AArch64CC::CondCode InvCC = changeICMPPredToAArch64CC(
      CmpInst::getInversePredicate((CmpInst::Predicate)Pred));
  auto I =
      MIRBuilder
    .buildInstr(AArch64::CSINCWr, {DefReg}, {Register(AArch64::WZR), Register(AArch64::WZR)})
          .addImm(InvCC);
  constrainSelectedInstRegOperands(*I, TII, TRI, RBI);
  return &*I;
}

bool AArch64InstructionSelector::tryOptSelect(MachineInstr &I) const {
  MachineIRBuilder MIB(I);
  MachineRegisterInfo &MRI = *MIB.getMRI();
  const TargetRegisterInfo &TRI = *MRI.getTargetRegisterInfo();

  // We want to recognize this pattern:
  //
  // $z = G_FCMP pred, $x, $y
  // ...
  // $w = G_SELECT $z, $a, $b
  //
  // Where the value of $z is *only* ever used by the G_SELECT (possibly with
  // some copies/truncs in between.)
  //
  // If we see this, then we can emit something like this:
  //
  // fcmp $x, $y
  // fcsel $w, $a, $b, pred
  //
  // Rather than emitting both of the rather long sequences in the standard
  // G_FCMP/G_SELECT select methods.

  // First, check if the condition is defined by a compare.
  MachineInstr *CondDef = MRI.getVRegDef(I.getOperand(1).getReg());
  while (CondDef) {
    // We can only fold if all of the defs have one use.
    if (!MRI.hasOneUse(CondDef->getOperand(0).getReg()))
      return false;

    // We can skip over G_TRUNC since the condition is 1-bit.
    // Truncating/extending can have no impact on the value.
    unsigned Opc = CondDef->getOpcode();
    if (Opc != TargetOpcode::COPY && Opc != TargetOpcode::G_TRUNC)
      break;

    // Can't see past copies from physregs.
    if (Opc == TargetOpcode::COPY &&
        Register::isPhysicalRegister(CondDef->getOperand(1).getReg()))
      return false;

    CondDef = MRI.getVRegDef(CondDef->getOperand(1).getReg());
  }

  // Is the condition defined by a compare?
  if (!CondDef)
    return false;

  unsigned CondOpc = CondDef->getOpcode();
  if (CondOpc != TargetOpcode::G_ICMP && CondOpc != TargetOpcode::G_FCMP)
    return false;

  AArch64CC::CondCode CondCode;
  if (CondOpc == TargetOpcode::G_ICMP) {
    CondCode = changeICMPPredToAArch64CC(
        (CmpInst::Predicate)CondDef->getOperand(1).getPredicate());
    if (!emitIntegerCompare(CondDef->getOperand(2), CondDef->getOperand(3),
                            CondDef->getOperand(1), MIB)) {
      LLVM_DEBUG(dbgs() << "Couldn't emit compare for select!\n");
      return false;
    }
  } else {
    // Get the condition code for the select.
    AArch64CC::CondCode CondCode2;
    changeFCMPPredToAArch64CC(
        (CmpInst::Predicate)CondDef->getOperand(1).getPredicate(), CondCode,
        CondCode2);

    // changeFCMPPredToAArch64CC sets CondCode2 to AL when we require two
    // instructions to emit the comparison.
    // TODO: Handle FCMP_UEQ and FCMP_ONE. After that, this check will be
    // unnecessary.
    if (CondCode2 != AArch64CC::AL)
      return false;

    // Make sure we'll be able to select the compare.
    unsigned CmpOpc = selectFCMPOpc(*CondDef, MRI);
    if (!CmpOpc)
      return false;

    // Emit a new compare.
    auto Cmp = MIB.buildInstr(CmpOpc, {}, {CondDef->getOperand(2).getReg()});
    if (CmpOpc != AArch64::FCMPSri && CmpOpc != AArch64::FCMPDri)
      Cmp.addUse(CondDef->getOperand(3).getReg());
    constrainSelectedInstRegOperands(*Cmp, TII, TRI, RBI);
  }

  // Emit the select.
  unsigned CSelOpc = selectSelectOpc(I, MRI, RBI);
  auto CSel =
      MIB.buildInstr(CSelOpc, {I.getOperand(0).getReg()},
                     {I.getOperand(2).getReg(), I.getOperand(3).getReg()})
          .addImm(CondCode);
  constrainSelectedInstRegOperands(*CSel, TII, TRI, RBI);
  I.eraseFromParent();
  return true;
}

MachineInstr *AArch64InstructionSelector::tryFoldIntegerCompare(
    MachineOperand &LHS, MachineOperand &RHS, MachineOperand &Predicate,
    MachineIRBuilder &MIRBuilder) const {
  assert(LHS.isReg() && RHS.isReg() && Predicate.isPredicate() &&
         "Unexpected MachineOperand");
  MachineRegisterInfo &MRI = *MIRBuilder.getMRI();
  // We want to find this sort of thing:
  // x = G_SUB 0, y
  // G_ICMP z, x
  //
  // In this case, we can fold the G_SUB into the G_ICMP using a CMN instead.
  // e.g:
  //
  // cmn z, y

  // Helper lambda to detect the subtract followed by the compare.
  // Takes in the def of the LHS or RHS, and checks if it's a subtract from 0.
  auto IsCMN = [&](MachineInstr *DefMI, const AArch64CC::CondCode &CC) {
    if (!DefMI || DefMI->getOpcode() != TargetOpcode::G_SUB)
      return false;

    // Need to make sure NZCV is the same at the end of the transformation.
    if (CC != AArch64CC::EQ && CC != AArch64CC::NE)
      return false;

    // We want to match against SUBs.
    if (DefMI->getOpcode() != TargetOpcode::G_SUB)
      return false;

    // Make sure that we're getting
    // x = G_SUB 0, y
    auto ValAndVReg =
        getConstantVRegValWithLookThrough(DefMI->getOperand(1).getReg(), MRI);
    if (!ValAndVReg || ValAndVReg->Value != 0)
      return false;

    // This can safely be represented as a CMN.
    return true;
  };

  // Check if the RHS or LHS of the G_ICMP is defined by a SUB
  MachineInstr *LHSDef = getDefIgnoringCopies(LHS.getReg(), MRI);
  MachineInstr *RHSDef = getDefIgnoringCopies(RHS.getReg(), MRI);
  CmpInst::Predicate P = (CmpInst::Predicate)Predicate.getPredicate();
  const AArch64CC::CondCode CC = changeICMPPredToAArch64CC(P);

  // Given this:
  //
  // x = G_SUB 0, y
  // G_ICMP x, z
  //
  // Produce this:
  //
  // cmn y, z
  if (IsCMN(LHSDef, CC))
    return emitCMN(LHSDef->getOperand(2), RHS, MIRBuilder);

  // Same idea here, but with the RHS of the compare instead:
  //
  // Given this:
  //
  // x = G_SUB 0, y
  // G_ICMP z, x
  //
  // Produce this:
  //
  // cmn z, y
  if (IsCMN(RHSDef, CC))
    return emitCMN(LHS, RHSDef->getOperand(2), MIRBuilder);

  // Given this:
  //
  // z = G_AND x, y
  // G_ICMP z, 0
  //
  // Produce this if the compare is signed:
  //
  // tst x, y
  if (!isUnsignedICMPPred(P) && LHSDef &&
      LHSDef->getOpcode() == TargetOpcode::G_AND) {
    // Make sure that the RHS is 0.
    auto ValAndVReg = getConstantVRegValWithLookThrough(RHS.getReg(), MRI);
    if (!ValAndVReg || ValAndVReg->Value != 0)
      return nullptr;

    return emitTST(LHSDef->getOperand(1).getReg(),
                   LHSDef->getOperand(2).getReg(), MIRBuilder);
  }

  return nullptr;
}

bool AArch64InstructionSelector::tryOptVectorDup(MachineInstr &I) const {
  // Try to match a vector splat operation into a dup instruction.
  // We're looking for this pattern:
  //    %scalar:gpr(s64) = COPY $x0
  //    %undef:fpr(<2 x s64>) = G_IMPLICIT_DEF
  //    %cst0:gpr(s32) = G_CONSTANT i32 0
  //    %zerovec:fpr(<2 x s32>) = G_BUILD_VECTOR %cst0(s32), %cst0(s32)
  //    %ins:fpr(<2 x s64>) = G_INSERT_VECTOR_ELT %undef, %scalar(s64), %cst0(s32)
  //    %splat:fpr(<2 x s64>) = G_SHUFFLE_VECTOR %ins(<2 x s64>), %undef,
  //                                             %zerovec(<2 x s32>)
  //
  // ...into:
  // %splat = DUP %scalar
  // We use the regbank of the scalar to determine which kind of dup to use.
  MachineIRBuilder MIB(I);
  MachineRegisterInfo &MRI = *MIB.getMRI();
  const TargetRegisterInfo &TRI = *MRI.getTargetRegisterInfo();
  using namespace TargetOpcode;
  using namespace MIPatternMatch;

  // Begin matching the insert.
  auto *InsMI =
      getOpcodeDef(G_INSERT_VECTOR_ELT, I.getOperand(1).getReg(), MRI);
  if (!InsMI)
    return false;
  // Match the undef vector operand.
  auto *UndefMI =
      getOpcodeDef(G_IMPLICIT_DEF, InsMI->getOperand(1).getReg(), MRI);
  if (!UndefMI)
    return false;
  // Match the scalar being splatted.
  Register ScalarReg = InsMI->getOperand(2).getReg();
  const RegisterBank *ScalarRB = RBI.getRegBank(ScalarReg, MRI, TRI);
  // Match the index constant 0.
  int64_t Index = 0;
  if (!mi_match(InsMI->getOperand(3).getReg(), MRI, m_ICst(Index)) || Index)
    return false;

  // The shuffle's second operand doesn't matter if the mask is all zero.
  auto *ZeroVec = getOpcodeDef(G_BUILD_VECTOR, I.getOperand(3).getReg(), MRI);
  if (!ZeroVec)
    return false;
  int64_t Zero = 0;
  if (!mi_match(ZeroVec->getOperand(1).getReg(), MRI, m_ICst(Zero)) || Zero)
    return false;
  for (unsigned i = 1, e = ZeroVec->getNumOperands(); i < e; ++i) {
    if (ZeroVec->getOperand(i).getReg() != ZeroVec->getOperand(1).getReg())
      return false; // This wasn't an all zeros vector.
  }

  // We're done, now find out what kind of splat we need.
  LLT VecTy = MRI.getType(I.getOperand(0).getReg());
  LLT EltTy = VecTy.getElementType();
  if (VecTy.getSizeInBits() != 128 || EltTy.getSizeInBits() < 32) {
    LLVM_DEBUG(dbgs() << "Could not optimize splat pattern < 128b yet");
    return false;
  }
  bool IsFP = ScalarRB->getID() == AArch64::FPRRegBankID;
  static const unsigned OpcTable[2][2] = {
      {AArch64::DUPv4i32gpr, AArch64::DUPv2i64gpr},
      {AArch64::DUPv4i32lane, AArch64::DUPv2i64lane}};
  unsigned Opc = OpcTable[IsFP][EltTy.getSizeInBits() == 64];

  // For FP splats, we need to widen the scalar reg via undef too.
  if (IsFP) {
    MachineInstr *Widen = emitScalarToVector(
        EltTy.getSizeInBits(), &AArch64::FPR128RegClass, ScalarReg, MIB);
    if (!Widen)
      return false;
    ScalarReg = Widen->getOperand(0).getReg();
  }
  auto Dup = MIB.buildInstr(Opc, {I.getOperand(0).getReg()}, {ScalarReg});
  if (IsFP)
    Dup.addImm(0);
  constrainSelectedInstRegOperands(*Dup, TII, TRI, RBI);
  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::tryOptVectorShuffle(MachineInstr &I) const {
  if (TM.getOptLevel() == CodeGenOpt::None)
    return false;
  if (tryOptVectorDup(I))
    return true;
  return false;
}

bool AArch64InstructionSelector::selectShuffleVector(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  if (tryOptVectorShuffle(I))
    return true;
  const LLT DstTy = MRI.getType(I.getOperand(0).getReg());
  Register Src1Reg = I.getOperand(1).getReg();
  const LLT Src1Ty = MRI.getType(Src1Reg);
  Register Src2Reg = I.getOperand(2).getReg();
  const LLT Src2Ty = MRI.getType(Src2Reg);

  MachineBasicBlock &MBB = *I.getParent();
  MachineFunction &MF = *MBB.getParent();
  LLVMContext &Ctx = MF.getFunction().getContext();

  // G_SHUFFLE_VECTOR doesn't really have a strictly enforced constant mask
  // operand, it comes in as a normal vector value which we have to analyze to
  // find the mask indices. If the mask element is undef, then
  // collectShuffleMaskIndices() will add a None entry for that index into
  // the list.
  SmallVector<Optional<int>, 8> Mask;
  collectShuffleMaskIndices(I, MRI, Mask);
  assert(!Mask.empty() && "Expected to find mask indices");

  // G_SHUFFLE_VECTOR is weird in that the source operands can be scalars, if
  // it's originated from a <1 x T> type. Those should have been lowered into
  // G_BUILD_VECTOR earlier.
  if (!Src1Ty.isVector() || !Src2Ty.isVector()) {
    LLVM_DEBUG(dbgs() << "Could not select a \"scalar\" G_SHUFFLE_VECTOR\n");
    return false;
  }

  unsigned BytesPerElt = DstTy.getElementType().getSizeInBits() / 8;

  SmallVector<Constant *, 64> CstIdxs;
  for (auto &MaybeVal : Mask) {
    // For now, any undef indexes we'll just assume to be 0. This should be
    // optimized in future, e.g. to select DUP etc.
    int Val = MaybeVal.hasValue() ? *MaybeVal : 0;
    for (unsigned Byte = 0; Byte < BytesPerElt; ++Byte) {
      unsigned Offset = Byte + Val * BytesPerElt;
      CstIdxs.emplace_back(ConstantInt::get(Type::getInt8Ty(Ctx), Offset));
    }
  }

  MachineIRBuilder MIRBuilder(I);

  // Use a constant pool to load the index vector for TBL.
  Constant *CPVal = ConstantVector::get(CstIdxs);
  MachineInstr *IndexLoad = emitLoadFromConstantPool(CPVal, MIRBuilder);
  if (!IndexLoad) {
    LLVM_DEBUG(dbgs() << "Could not load from a constant pool");
    return false;
  }

  if (DstTy.getSizeInBits() != 128) {
    assert(DstTy.getSizeInBits() == 64 && "Unexpected shuffle result ty");
    // This case can be done with TBL1.
    MachineInstr *Concat = emitVectorConcat(None, Src1Reg, Src2Reg, MIRBuilder);
    if (!Concat) {
      LLVM_DEBUG(dbgs() << "Could not do vector concat for tbl1");
      return false;
    }

    // The constant pool load will be 64 bits, so need to convert to FPR128 reg.
    IndexLoad =
        emitScalarToVector(64, &AArch64::FPR128RegClass,
                           IndexLoad->getOperand(0).getReg(), MIRBuilder);

    auto TBL1 = MIRBuilder.buildInstr(
        AArch64::TBLv16i8One, {&AArch64::FPR128RegClass},
        {Concat->getOperand(0).getReg(), IndexLoad->getOperand(0).getReg()});
    constrainSelectedInstRegOperands(*TBL1, TII, TRI, RBI);

    auto Copy =
        MIRBuilder
            .buildInstr(TargetOpcode::COPY, {I.getOperand(0).getReg()}, {})
            .addReg(TBL1.getReg(0), 0, AArch64::dsub);
    RBI.constrainGenericRegister(Copy.getReg(0), AArch64::FPR64RegClass, MRI);
    I.eraseFromParent();
    return true;
  }

  // For TBL2 we need to emit a REG_SEQUENCE to tie together two consecutive
  // Q registers for regalloc.
  auto RegSeq = MIRBuilder
                    .buildInstr(TargetOpcode::REG_SEQUENCE,
                                {&AArch64::QQRegClass}, {Src1Reg})
                    .addImm(AArch64::qsub0)
                    .addUse(Src2Reg)
                    .addImm(AArch64::qsub1);

  auto TBL2 =
      MIRBuilder.buildInstr(AArch64::TBLv16i8Two, {I.getOperand(0).getReg()},
                            {RegSeq, IndexLoad->getOperand(0).getReg()});
  constrainSelectedInstRegOperands(*RegSeq, TII, TRI, RBI);
  constrainSelectedInstRegOperands(*TBL2, TII, TRI, RBI);
  I.eraseFromParent();
  return true;
}

MachineInstr *AArch64InstructionSelector::emitLaneInsert(
    Optional<Register> DstReg, Register SrcReg, Register EltReg,
    unsigned LaneIdx, const RegisterBank &RB,
    MachineIRBuilder &MIRBuilder) const {
  MachineInstr *InsElt = nullptr;
  const TargetRegisterClass *DstRC = &AArch64::FPR128RegClass;
  MachineRegisterInfo &MRI = *MIRBuilder.getMRI();

  // Create a register to define with the insert if one wasn't passed in.
  if (!DstReg)
    DstReg = MRI.createVirtualRegister(DstRC);

  unsigned EltSize = MRI.getType(EltReg).getSizeInBits();
  unsigned Opc = getInsertVecEltOpInfo(RB, EltSize).first;

  if (RB.getID() == AArch64::FPRRegBankID) {
    auto InsSub = emitScalarToVector(EltSize, DstRC, EltReg, MIRBuilder);
    InsElt = MIRBuilder.buildInstr(Opc, {*DstReg}, {SrcReg})
                 .addImm(LaneIdx)
                 .addUse(InsSub->getOperand(0).getReg())
                 .addImm(0);
  } else {
    InsElt = MIRBuilder.buildInstr(Opc, {*DstReg}, {SrcReg})
                 .addImm(LaneIdx)
                 .addUse(EltReg);
  }

  constrainSelectedInstRegOperands(*InsElt, TII, TRI, RBI);
  return InsElt;
}

bool AArch64InstructionSelector::selectInsertElt(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_INSERT_VECTOR_ELT);

  // Get information on the destination.
  Register DstReg = I.getOperand(0).getReg();
  const LLT DstTy = MRI.getType(DstReg);
  unsigned VecSize = DstTy.getSizeInBits();

  // Get information on the element we want to insert into the destination.
  Register EltReg = I.getOperand(2).getReg();
  const LLT EltTy = MRI.getType(EltReg);
  unsigned EltSize = EltTy.getSizeInBits();
  if (EltSize < 16 || EltSize > 64)
    return false; // Don't support all element types yet.

  // Find the definition of the index. Bail out if it's not defined by a
  // G_CONSTANT.
  Register IdxReg = I.getOperand(3).getReg();
  auto VRegAndVal = getConstantVRegValWithLookThrough(IdxReg, MRI);
  if (!VRegAndVal)
    return false;
  unsigned LaneIdx = VRegAndVal->Value;

  // Perform the lane insert.
  Register SrcReg = I.getOperand(1).getReg();
  const RegisterBank &EltRB = *RBI.getRegBank(EltReg, MRI, TRI);
  MachineIRBuilder MIRBuilder(I);

  if (VecSize < 128) {
    // If the vector we're inserting into is smaller than 128 bits, widen it
    // to 128 to do the insert.
    MachineInstr *ScalarToVec = emitScalarToVector(
        VecSize, &AArch64::FPR128RegClass, SrcReg, MIRBuilder);
    if (!ScalarToVec)
      return false;
    SrcReg = ScalarToVec->getOperand(0).getReg();
  }

  // Create an insert into a new FPR128 register.
  // Note that if our vector is already 128 bits, we end up emitting an extra
  // register.
  MachineInstr *InsMI =
      emitLaneInsert(None, SrcReg, EltReg, LaneIdx, EltRB, MIRBuilder);

  if (VecSize < 128) {
    // If we had to widen to perform the insert, then we have to demote back to
    // the original size to get the result we want.
    Register DemoteVec = InsMI->getOperand(0).getReg();
    const TargetRegisterClass *RC =
        getMinClassForRegBank(*RBI.getRegBank(DemoteVec, MRI, TRI), VecSize);
    if (RC != &AArch64::FPR32RegClass && RC != &AArch64::FPR64RegClass) {
      LLVM_DEBUG(dbgs() << "Unsupported register class!\n");
      return false;
    }
    unsigned SubReg = 0;
    if (!getSubRegForClass(RC, TRI, SubReg))
      return false;
    if (SubReg != AArch64::ssub && SubReg != AArch64::dsub) {
      LLVM_DEBUG(dbgs() << "Unsupported destination size! (" << VecSize
                        << "\n");
      return false;
    }
    MIRBuilder.buildInstr(TargetOpcode::COPY, {DstReg}, {})
        .addReg(DemoteVec, 0, SubReg);
    RBI.constrainGenericRegister(DstReg, *RC, MRI);
  } else {
    // No widening needed.
    InsMI->getOperand(0).setReg(DstReg);
    constrainSelectedInstRegOperands(*InsMI, TII, TRI, RBI);
  }

  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectBuildVector(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  assert(I.getOpcode() == TargetOpcode::G_BUILD_VECTOR);
  // Until we port more of the optimized selections, for now just use a vector
  // insert sequence.
  const LLT DstTy = MRI.getType(I.getOperand(0).getReg());
  const LLT EltTy = MRI.getType(I.getOperand(1).getReg());
  unsigned EltSize = EltTy.getSizeInBits();
  if (EltSize < 16 || EltSize > 64)
    return false; // Don't support all element types yet.
  const RegisterBank &RB = *RBI.getRegBank(I.getOperand(1).getReg(), MRI, TRI);
  MachineIRBuilder MIRBuilder(I);

  const TargetRegisterClass *DstRC = &AArch64::FPR128RegClass;
  MachineInstr *ScalarToVec =
      emitScalarToVector(DstTy.getElementType().getSizeInBits(), DstRC,
                         I.getOperand(1).getReg(), MIRBuilder);
  if (!ScalarToVec)
    return false;

  Register DstVec = ScalarToVec->getOperand(0).getReg();
  unsigned DstSize = DstTy.getSizeInBits();

  // Keep track of the last MI we inserted. Later on, we might be able to save
  // a copy using it.
  MachineInstr *PrevMI = nullptr;
  for (unsigned i = 2, e = DstSize / EltSize + 1; i < e; ++i) {
    // Note that if we don't do a subregister copy, we can end up making an
    // extra register.
    PrevMI = &*emitLaneInsert(None, DstVec, I.getOperand(i).getReg(), i - 1, RB,
                              MIRBuilder);
    DstVec = PrevMI->getOperand(0).getReg();
  }

  // If DstTy's size in bits is less than 128, then emit a subregister copy
  // from DstVec to the last register we've defined.
  if (DstSize < 128) {
    // Force this to be FPR using the destination vector.
    const TargetRegisterClass *RC =
        getMinClassForRegBank(*RBI.getRegBank(DstVec, MRI, TRI), DstSize);
    if (!RC)
      return false;
    if (RC != &AArch64::FPR32RegClass && RC != &AArch64::FPR64RegClass) {
      LLVM_DEBUG(dbgs() << "Unsupported register class!\n");
      return false;
    }

    unsigned SubReg = 0;
    if (!getSubRegForClass(RC, TRI, SubReg))
      return false;
    if (SubReg != AArch64::ssub && SubReg != AArch64::dsub) {
      LLVM_DEBUG(dbgs() << "Unsupported destination size! (" << DstSize
                        << "\n");
      return false;
    }

    Register Reg = MRI.createVirtualRegister(RC);
    Register DstReg = I.getOperand(0).getReg();

    MIRBuilder.buildInstr(TargetOpcode::COPY, {DstReg}, {})
        .addReg(DstVec, 0, SubReg);
    MachineOperand &RegOp = I.getOperand(1);
    RegOp.setReg(Reg);
    RBI.constrainGenericRegister(DstReg, *RC, MRI);
  } else {
    // We don't need a subregister copy. Save a copy by re-using the
    // destination register on the final insert.
    assert(PrevMI && "PrevMI was null?");
    PrevMI->getOperand(0).setReg(I.getOperand(0).getReg());
    constrainSelectedInstRegOperands(*PrevMI, TII, TRI, RBI);
  }

  I.eraseFromParent();
  return true;
}

/// Helper function to find an intrinsic ID on an a MachineInstr. Returns the
/// ID if it exists, and 0 otherwise.
static unsigned findIntrinsicID(MachineInstr &I) {
  auto IntrinOp = find_if(I.operands(), [&](const MachineOperand &Op) {
    return Op.isIntrinsicID();
  });
  if (IntrinOp == I.operands_end())
    return 0;
  return IntrinOp->getIntrinsicID();
}

/// Helper function to emit the correct opcode for a llvm.aarch64.stlxr
/// intrinsic.
static unsigned getStlxrOpcode(unsigned NumBytesToStore) {
  switch (NumBytesToStore) {
  // TODO: 1 and 2 byte stores
  case 4:
    return AArch64::STLXRW;
  case 8:
    return AArch64::STLXRX;
  default:
    LLVM_DEBUG(dbgs() << "Unexpected number of bytes to store! ("
                      << NumBytesToStore << ")\n");
    break;
  }
  return 0;
}

bool AArch64InstructionSelector::selectIntrinsicWithSideEffects(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  // Find the intrinsic ID.
  unsigned IntrinID = findIntrinsicID(I);
  if (!IntrinID)
    return false;
  MachineIRBuilder MIRBuilder(I);

  // Select the instruction.
  switch (IntrinID) {
  default:
    return false;
  case Intrinsic::trap:
    MIRBuilder.buildInstr(AArch64::BRK, {}, {}).addImm(1);
    break;
  case Intrinsic::debugtrap:
    if (!STI.isTargetWindows())
      return false;
    MIRBuilder.buildInstr(AArch64::BRK, {}, {}).addImm(0xF000);
    break;
  case Intrinsic::aarch64_stlxr:
    Register StatReg = I.getOperand(0).getReg();
    assert(RBI.getSizeInBits(StatReg, MRI, TRI) == 32 &&
           "Status register must be 32 bits!");
    Register SrcReg = I.getOperand(2).getReg();

    if (RBI.getSizeInBits(SrcReg, MRI, TRI) != 64) {
      LLVM_DEBUG(dbgs() << "Only support 64-bit sources right now.\n");
      return false;
    }

    Register PtrReg = I.getOperand(3).getReg();
    assert(MRI.getType(PtrReg).isPointer() && "Expected pointer operand");

    // Expect only one memory operand.
    if (!I.hasOneMemOperand())
      return false;

    const MachineMemOperand *MemOp = *I.memoperands_begin();
    unsigned NumBytesToStore = MemOp->getSize();
    unsigned Opc = getStlxrOpcode(NumBytesToStore);
    if (!Opc)
      return false;
    unsigned NumBitsToStore = NumBytesToStore * 8;
    if (NumBitsToStore != 64) {
      // The intrinsic always has a 64-bit source, but we might actually want
      // a differently-sized source for the instruction. Try to get it.
      // TODO: For 1 and 2-byte stores, this will have a G_AND. For now, let's
      // just handle 4-byte stores.
      // TODO: If we don't find a G_ZEXT, we'll have to truncate the value down
      // to the right size for the STLXR.
      MachineInstr *Zext = getOpcodeDef(TargetOpcode::G_ZEXT, SrcReg, MRI);
      if (!Zext)
        return false;
      SrcReg = Zext->getOperand(1).getReg();
      // We should get an appropriately-sized register here.
      if (RBI.getSizeInBits(SrcReg, MRI, TRI) != NumBitsToStore)
        return false;
    }
    auto StoreMI = MIRBuilder.buildInstr(Opc, {StatReg}, {SrcReg, PtrReg})
                       .addMemOperand(*I.memoperands_begin());
    constrainSelectedInstRegOperands(*StoreMI, TII, TRI, RBI);
  }

  I.eraseFromParent();
  return true;
}

bool AArch64InstructionSelector::selectIntrinsic(
    MachineInstr &I, MachineRegisterInfo &MRI) const {
  unsigned IntrinID = findIntrinsicID(I);
  if (!IntrinID)
    return false;
  MachineIRBuilder MIRBuilder(I);

  switch (IntrinID) {
  default:
    break;
  case Intrinsic::aarch64_crypto_sha1h:
    Register DstReg = I.getOperand(0).getReg();
    Register SrcReg = I.getOperand(2).getReg();

    // FIXME: Should this be an assert?
    if (MRI.getType(DstReg).getSizeInBits() != 32 ||
        MRI.getType(SrcReg).getSizeInBits() != 32)
      return false;

    // The operation has to happen on FPRs. Set up some new FPR registers for
    // the source and destination if they are on GPRs.
    if (RBI.getRegBank(SrcReg, MRI, TRI)->getID() != AArch64::FPRRegBankID) {
      SrcReg = MRI.createVirtualRegister(&AArch64::FPR32RegClass);
      MIRBuilder.buildCopy({SrcReg}, {I.getOperand(2)});

      // Make sure the copy ends up getting constrained properly.
      RBI.constrainGenericRegister(I.getOperand(2).getReg(),
                                   AArch64::GPR32RegClass, MRI);
    }

    if (RBI.getRegBank(DstReg, MRI, TRI)->getID() != AArch64::FPRRegBankID)
      DstReg = MRI.createVirtualRegister(&AArch64::FPR32RegClass);

    // Actually insert the instruction.
    auto SHA1Inst = MIRBuilder.buildInstr(AArch64::SHA1Hrr, {DstReg}, {SrcReg});
    constrainSelectedInstRegOperands(*SHA1Inst, TII, TRI, RBI);

    // Did we create a new register for the destination?
    if (DstReg != I.getOperand(0).getReg()) {
      // Yep. Copy the result of the instruction back into the original
      // destination.
      MIRBuilder.buildCopy({I.getOperand(0)}, {DstReg});
      RBI.constrainGenericRegister(I.getOperand(0).getReg(),
                                   AArch64::GPR32RegClass, MRI);
    }

    I.eraseFromParent();
    return true;
  }
  return false;
}

static Optional<uint64_t> getImmedFromMO(const MachineOperand &Root) {
  auto &MI = *Root.getParent();
  auto &MBB = *MI.getParent();
  auto &MF = *MBB.getParent();
  auto &MRI = MF.getRegInfo();
  uint64_t Immed;
  if (Root.isImm())
    Immed = Root.getImm();
  else if (Root.isCImm())
    Immed = Root.getCImm()->getZExtValue();
  else if (Root.isReg()) {
    auto ValAndVReg =
        getConstantVRegValWithLookThrough(Root.getReg(), MRI, true);
    if (!ValAndVReg)
      return None;
    Immed = ValAndVReg->Value;
  } else
    return None;
  return Immed;
}

InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectShiftA_32(const MachineOperand &Root) const {
  auto MaybeImmed = getImmedFromMO(Root);
  if (MaybeImmed == None || *MaybeImmed > 31)
    return None;
  uint64_t Enc = (32 - *MaybeImmed) & 0x1f;
  return {{[=](MachineInstrBuilder &MIB) { MIB.addImm(Enc); }}};
}

InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectShiftB_32(const MachineOperand &Root) const {
  auto MaybeImmed = getImmedFromMO(Root);
  if (MaybeImmed == None || *MaybeImmed > 31)
    return None;
  uint64_t Enc = 31 - *MaybeImmed;
  return {{[=](MachineInstrBuilder &MIB) { MIB.addImm(Enc); }}};
}

InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectShiftA_64(const MachineOperand &Root) const {
  auto MaybeImmed = getImmedFromMO(Root);
  if (MaybeImmed == None || *MaybeImmed > 63)
    return None;
  uint64_t Enc = (64 - *MaybeImmed) & 0x3f;
  return {{[=](MachineInstrBuilder &MIB) { MIB.addImm(Enc); }}};
}

InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectShiftB_64(const MachineOperand &Root) const {
  auto MaybeImmed = getImmedFromMO(Root);
  if (MaybeImmed == None || *MaybeImmed > 63)
    return None;
  uint64_t Enc = 63 - *MaybeImmed;
  return {{[=](MachineInstrBuilder &MIB) { MIB.addImm(Enc); }}};
}

/// Helper to select an immediate value that can be represented as a 12-bit
/// value shifted left by either 0 or 12. If it is possible to do so, return
/// the immediate and shift value. If not, return None.
///
/// Used by selectArithImmed and selectNegArithImmed.
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::select12BitValueWithLeftShift(
    uint64_t Immed) const {
  unsigned ShiftAmt;
  if (Immed >> 12 == 0) {
    ShiftAmt = 0;
  } else if ((Immed & 0xfff) == 0 && Immed >> 24 == 0) {
    ShiftAmt = 12;
    Immed = Immed >> 12;
  } else
    return None;

  unsigned ShVal = AArch64_AM::getShifterImm(AArch64_AM::LSL, ShiftAmt);
  return {{
      [=](MachineInstrBuilder &MIB) { MIB.addImm(Immed); },
      [=](MachineInstrBuilder &MIB) { MIB.addImm(ShVal); },
  }};
}

/// SelectArithImmed - Select an immediate value that can be represented as
/// a 12-bit value shifted left by either 0 or 12.  If so, return true with
/// Val set to the 12-bit value and Shift set to the shifter operand.
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectArithImmed(MachineOperand &Root) const {
  // This function is called from the addsub_shifted_imm ComplexPattern,
  // which lists [imm] as the list of opcode it's interested in, however
  // we still need to check whether the operand is actually an immediate
  // here because the ComplexPattern opcode list is only used in
  // root-level opcode matching.
  auto MaybeImmed = getImmedFromMO(Root);
  if (MaybeImmed == None)
    return None;
  return select12BitValueWithLeftShift(*MaybeImmed);
}

/// SelectNegArithImmed - As above, but negates the value before trying to
/// select it.
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectNegArithImmed(MachineOperand &Root) const {
  // We need a register here, because we need to know if we have a 64 or 32
  // bit immediate.
  if (!Root.isReg())
    return None;
  auto MaybeImmed = getImmedFromMO(Root);
  if (MaybeImmed == None)
    return None;
  uint64_t Immed = *MaybeImmed;

  // This negation is almost always valid, but "cmp wN, #0" and "cmn wN, #0"
  // have the opposite effect on the C flag, so this pattern mustn't match under
  // those circumstances.
  if (Immed == 0)
    return None;

  // Check if we're dealing with a 32-bit type on the root or a 64-bit type on
  // the root.
  MachineRegisterInfo &MRI = Root.getParent()->getMF()->getRegInfo();
  if (MRI.getType(Root.getReg()).getSizeInBits() == 32)
    Immed = ~((uint32_t)Immed) + 1;
  else
    Immed = ~Immed + 1ULL;

  if (Immed & 0xFFFFFFFFFF000000ULL)
    return None;

  Immed &= 0xFFFFFFULL;
  return select12BitValueWithLeftShift(Immed);
}

/// Return true if it is worth folding MI into an extended register. That is,
/// if it's safe to pull it into the addressing mode of a load or store as a
/// shift.
bool AArch64InstructionSelector::isWorthFoldingIntoExtendedReg(
    MachineInstr &MI, const MachineRegisterInfo &MRI) const {
  // Always fold if there is one use, or if we're optimizing for size.
  Register DefReg = MI.getOperand(0).getReg();
  if (MRI.hasOneUse(DefReg) ||
      MI.getParent()->getParent()->getFunction().hasMinSize())
    return true;

  // It's better to avoid folding and recomputing shifts when we don't have a
  // fastpath.
  if (!STI.hasLSLFast())
    return false;

  // We have a fastpath, so folding a shift in and potentially computing it
  // many times may be beneficial. Check if this is only used in memory ops.
  // If it is, then we should fold.
  return all_of(MRI.use_instructions(DefReg),
                [](MachineInstr &Use) { return Use.mayLoadOrStore(); });
}

/// This is used for computing addresses like this:
///
/// ldr x1, [x2, x3, lsl #3]
///
/// Where x2 is the base register, and x3 is an offset register. The shift-left
/// is a constant value specific to this load instruction. That is, we'll never
/// see anything other than a 3 here (which corresponds to the size of the
/// element being loaded.)
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectAddrModeShiftedExtendXReg(
    MachineOperand &Root, unsigned SizeInBytes) const {
  if (!Root.isReg())
    return None;
  MachineRegisterInfo &MRI = Root.getParent()->getMF()->getRegInfo();

  // Make sure that the memory op is a valid size.
  int64_t LegalShiftVal = Log2_32(SizeInBytes);
  if (LegalShiftVal == 0)
    return None;

  // We want to find something like this:
  //
  // val = G_CONSTANT LegalShiftVal
  // shift = G_SHL off_reg val
  // ptr = G_GEP base_reg shift
  // x = G_LOAD ptr
  //
  // And fold it into this addressing mode:
  //
  // ldr x, [base_reg, off_reg, lsl #LegalShiftVal]

  // Check if we can find the G_GEP.
  MachineInstr *Gep = getOpcodeDef(TargetOpcode::G_GEP, Root.getReg(), MRI);
  if (!Gep || !isWorthFoldingIntoExtendedReg(*Gep, MRI))
    return None;

  // Now, try to match an opcode which will match our specific offset.
  // We want a G_SHL or a G_MUL.
  MachineInstr *OffsetInst = getDefIgnoringCopies(Gep->getOperand(2).getReg(), MRI);
  if (!OffsetInst)
    return None;

  unsigned OffsetOpc = OffsetInst->getOpcode();
  if (OffsetOpc != TargetOpcode::G_SHL && OffsetOpc != TargetOpcode::G_MUL)
    return None;

  if (!isWorthFoldingIntoExtendedReg(*OffsetInst, MRI))
    return None;

  // Now, try to find the specific G_CONSTANT. Start by assuming that the
  // register we will offset is the LHS, and the register containing the
  // constant is the RHS.
  Register OffsetReg = OffsetInst->getOperand(1).getReg();
  Register ConstantReg = OffsetInst->getOperand(2).getReg();
  auto ValAndVReg = getConstantVRegValWithLookThrough(ConstantReg, MRI);
  if (!ValAndVReg) {
    // We didn't get a constant on the RHS. If the opcode is a shift, then
    // we're done.
    if (OffsetOpc == TargetOpcode::G_SHL)
      return None;

    // If we have a G_MUL, we can use either register. Try looking at the RHS.
    std::swap(OffsetReg, ConstantReg);
    ValAndVReg = getConstantVRegValWithLookThrough(ConstantReg, MRI);
    if (!ValAndVReg)
      return None;
  }

  // The value must fit into 3 bits, and must be positive. Make sure that is
  // true.
  int64_t ImmVal = ValAndVReg->Value;

  // Since we're going to pull this into a shift, the constant value must be
  // a power of 2. If we got a multiply, then we need to check this.
  if (OffsetOpc == TargetOpcode::G_MUL) {
    if (!isPowerOf2_32(ImmVal))
      return None;

    // Got a power of 2. So, the amount we'll shift is the log base-2 of that.
    ImmVal = Log2_32(ImmVal);
  }

  if ((ImmVal & 0x7) != ImmVal)
    return None;

  // We are only allowed to shift by LegalShiftVal. This shift value is built
  // into the instruction, so we can't just use whatever we want.
  if (ImmVal != LegalShiftVal)
    return None;

  // We can use the LHS of the GEP as the base, and the LHS of the shift as an
  // offset. Signify that we are shifting by setting the shift flag to 1.
  return {{
      [=](MachineInstrBuilder &MIB) { MIB.add(Gep->getOperand(1)); },
      [=](MachineInstrBuilder &MIB) { MIB.addUse(OffsetReg); },
      [=](MachineInstrBuilder &MIB) { MIB.addImm(0); },
      [=](MachineInstrBuilder &MIB) { MIB.addImm(1); },
  }};
}

/// This is used for computing addresses like this:
///
/// ldr x1, [x2, x3]
///
/// Where x2 is the base register, and x3 is an offset register.
///
/// When possible (or profitable) to fold a G_GEP into the address calculation,
/// this will do so. Otherwise, it will return None.
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectAddrModeRegisterOffset(
    MachineOperand &Root) const {
  MachineRegisterInfo &MRI = Root.getParent()->getMF()->getRegInfo();

  // We need a GEP.
  MachineInstr *Gep = MRI.getVRegDef(Root.getReg());
  if (!Gep || Gep->getOpcode() != TargetOpcode::G_GEP)
    return None;

  // If this is used more than once, let's not bother folding.
  // TODO: Check if they are memory ops. If they are, then we can still fold
  // without having to recompute anything.
  if (!MRI.hasOneUse(Gep->getOperand(0).getReg()))
    return None;

  // Base is the GEP's LHS, offset is its RHS.
  return {{
      [=](MachineInstrBuilder &MIB) { MIB.add(Gep->getOperand(1)); },
      [=](MachineInstrBuilder &MIB) { MIB.add(Gep->getOperand(2)); },
      [=](MachineInstrBuilder &MIB) { MIB.addImm(0); },
      [=](MachineInstrBuilder &MIB) { MIB.addImm(0); },
  }};
}

/// This is intended to be equivalent to selectAddrModeXRO in
/// AArch64ISelDAGtoDAG. It's used for selecting X register offset loads.
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectAddrModeXRO(MachineOperand &Root,
                                              unsigned SizeInBytes) const {
  MachineRegisterInfo &MRI = Root.getParent()->getMF()->getRegInfo();

  // If we have a constant offset, then we probably don't want to match a
  // register offset.
  if (isBaseWithConstantOffset(Root, MRI))
    return None;

  // Try to fold shifts into the addressing mode.
  auto AddrModeFns = selectAddrModeShiftedExtendXReg(Root, SizeInBytes);
  if (AddrModeFns)
    return AddrModeFns;

  // If that doesn't work, see if it's possible to fold in registers from
  // a GEP.
  return selectAddrModeRegisterOffset(Root);
}

/// Select a "register plus unscaled signed 9-bit immediate" address.  This
/// should only match when there is an offset that is not valid for a scaled
/// immediate addressing mode.  The "Size" argument is the size in bytes of the
/// memory reference, which is needed here to know what is valid for a scaled
/// immediate.
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectAddrModeUnscaled(MachineOperand &Root,
                                                   unsigned Size) const {
  MachineRegisterInfo &MRI =
      Root.getParent()->getParent()->getParent()->getRegInfo();

  if (!Root.isReg())
    return None;

  if (!isBaseWithConstantOffset(Root, MRI))
    return None;

  MachineInstr *RootDef = MRI.getVRegDef(Root.getReg());
  if (!RootDef)
    return None;

  MachineOperand &OffImm = RootDef->getOperand(2);
  if (!OffImm.isReg())
    return None;
  MachineInstr *RHS = MRI.getVRegDef(OffImm.getReg());
  if (!RHS || RHS->getOpcode() != TargetOpcode::G_CONSTANT)
    return None;
  int64_t RHSC;
  MachineOperand &RHSOp1 = RHS->getOperand(1);
  if (!RHSOp1.isCImm() || RHSOp1.getCImm()->getBitWidth() > 64)
    return None;
  RHSC = RHSOp1.getCImm()->getSExtValue();

  // If the offset is valid as a scaled immediate, don't match here.
  if ((RHSC & (Size - 1)) == 0 && RHSC >= 0 && RHSC < (0x1000 << Log2_32(Size)))
    return None;
  if (RHSC >= -256 && RHSC < 256) {
    MachineOperand &Base = RootDef->getOperand(1);
    return {{
        [=](MachineInstrBuilder &MIB) { MIB.add(Base); },
        [=](MachineInstrBuilder &MIB) { MIB.addImm(RHSC); },
    }};
  }
  return None;
}

/// Select a "register plus scaled unsigned 12-bit immediate" address.  The
/// "Size" argument is the size in bytes of the memory reference, which
/// determines the scale.
InstructionSelector::ComplexRendererFns
AArch64InstructionSelector::selectAddrModeIndexed(MachineOperand &Root,
                                                  unsigned Size) const {
  MachineRegisterInfo &MRI =
      Root.getParent()->getParent()->getParent()->getRegInfo();

  if (!Root.isReg())
    return None;

  MachineInstr *RootDef = MRI.getVRegDef(Root.getReg());
  if (!RootDef)
    return None;

  if (RootDef->getOpcode() == TargetOpcode::G_FRAME_INDEX) {
    return {{
        [=](MachineInstrBuilder &MIB) { MIB.add(RootDef->getOperand(1)); },
        [=](MachineInstrBuilder &MIB) { MIB.addImm(0); },
    }};
  }

  if (isBaseWithConstantOffset(Root, MRI)) {
    MachineOperand &LHS = RootDef->getOperand(1);
    MachineOperand &RHS = RootDef->getOperand(2);
    MachineInstr *LHSDef = MRI.getVRegDef(LHS.getReg());
    MachineInstr *RHSDef = MRI.getVRegDef(RHS.getReg());
    if (LHSDef && RHSDef) {
      int64_t RHSC = (int64_t)RHSDef->getOperand(1).getCImm()->getZExtValue();
      unsigned Scale = Log2_32(Size);
      if ((RHSC & (Size - 1)) == 0 && RHSC >= 0 && RHSC < (0x1000 << Scale)) {
        if (LHSDef->getOpcode() == TargetOpcode::G_FRAME_INDEX)
          return {{
              [=](MachineInstrBuilder &MIB) { MIB.add(LHSDef->getOperand(1)); },
              [=](MachineInstrBuilder &MIB) { MIB.addImm(RHSC >> Scale); },
          }};

        return {{
            [=](MachineInstrBuilder &MIB) { MIB.add(LHS); },
            [=](MachineInstrBuilder &MIB) { MIB.addImm(RHSC >> Scale); },
        }};
      }
    }
  }

  // Before falling back to our general case, check if the unscaled
  // instructions can handle this. If so, that's preferable.
  if (selectAddrModeUnscaled(Root, Size).hasValue())
    return None;

  return {{
      [=](MachineInstrBuilder &MIB) { MIB.add(Root); },
      [=](MachineInstrBuilder &MIB) { MIB.addImm(0); },
  }};
}

void AArch64InstructionSelector::renderTruncImm(MachineInstrBuilder &MIB,
                                                const MachineInstr &MI) const {
  const MachineRegisterInfo &MRI = MI.getParent()->getParent()->getRegInfo();
  assert(MI.getOpcode() == TargetOpcode::G_CONSTANT && "Expected G_CONSTANT");
  Optional<int64_t> CstVal = getConstantVRegVal(MI.getOperand(0).getReg(), MRI);
  assert(CstVal && "Expected constant value");
  MIB.addImm(CstVal.getValue());
}

namespace llvm {
InstructionSelector *
createAArch64InstructionSelector(const AArch64TargetMachine &TM,
                                 AArch64Subtarget &Subtarget,
                                 AArch64RegisterBankInfo &RBI) {
  return new AArch64InstructionSelector(TM, Subtarget, RBI);
}
}