llvm-project/llvm/lib/Target/AArch64/AArch64FastISel.cpp

//===-- AArch6464FastISel.cpp - AArch64 FastISel implementation -----------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the AArch64-specific support for the FastISel class. Some
// of the target-specific code is generated by tablegen in the file
// AArch64GenFastISel.inc, which is #included here.
//
//===----------------------------------------------------------------------===//

#include "AArch64.h"
#include "AArch64Subtarget.h"
#include "AArch64TargetMachine.h"
#include "MCTargetDesc/AArch64AddressingModes.h"
#include "llvm/CodeGen/CallingConvLower.h"
#include "llvm/CodeGen/FastISel.h"
#include "llvm/CodeGen/FunctionLoweringInfo.h"
#include "llvm/CodeGen/MachineConstantPool.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GetElementPtrTypeIterator.h"
#include "llvm/IR/GlobalAlias.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Operator.h"
#include "llvm/Support/CommandLine.h"
using namespace llvm;

namespace {

class AArch64FastISel : public FastISel {

  class Address {
  public:
    typedef enum {
      RegBase,
      FrameIndexBase
    } BaseKind;

  private:
    BaseKind Kind;
    union {
      unsigned Reg;
      int FI;
    } Base;
    int64_t Offset;

  public:
    Address() : Kind(RegBase), Offset(0) { Base.Reg = 0; }
    void setKind(BaseKind K) { Kind = K; }
    BaseKind getKind() const { return Kind; }
    bool isRegBase() const { return Kind == RegBase; }
    bool isFIBase() const { return Kind == FrameIndexBase; }
    void setReg(unsigned Reg) {
      assert(isRegBase() && "Invalid base register access!");
      Base.Reg = Reg;
    }
    unsigned getReg() const {
      assert(isRegBase() && "Invalid base register access!");
      return Base.Reg;
    }
    void setFI(unsigned FI) {
      assert(isFIBase() && "Invalid base frame index  access!");
      Base.FI = FI;
    }
    unsigned getFI() const {
      assert(isFIBase() && "Invalid base frame index access!");
      return Base.FI;
    }
    void setOffset(int64_t O) { Offset = O; }
    int64_t getOffset() { return Offset; }

    bool isValid() { return isFIBase() || (isRegBase() && getReg() != 0); }
  };

  /// Subtarget - Keep a pointer to the AArch64Subtarget around so that we can
  /// make the right decision when generating code for different targets.
  const AArch64Subtarget *Subtarget;
  LLVMContext *Context;

  bool FastLowerCall(CallLoweringInfo &CLI) override;
  bool FastLowerIntrinsicCall(const IntrinsicInst *II) override;

private:
  // Selection routines.
  bool SelectLoad(const Instruction *I);
  bool SelectStore(const Instruction *I);
  bool SelectBranch(const Instruction *I);
  bool SelectIndirectBr(const Instruction *I);
  bool SelectCmp(const Instruction *I);
  bool SelectSelect(const Instruction *I);
  bool SelectFPExt(const Instruction *I);
  bool SelectFPTrunc(const Instruction *I);
  bool SelectFPToInt(const Instruction *I, bool Signed);
  bool SelectIntToFP(const Instruction *I, bool Signed);
  bool SelectRem(const Instruction *I, unsigned ISDOpcode);
  bool SelectRet(const Instruction *I);
  bool SelectTrunc(const Instruction *I);
  bool SelectIntExt(const Instruction *I);
  bool SelectMul(const Instruction *I);
  bool SelectShift(const Instruction *I, bool IsLeftShift, bool IsArithmetic);

  // Utility helper routines.
  bool isTypeLegal(Type *Ty, MVT &VT);
  bool isLoadStoreTypeLegal(Type *Ty, MVT &VT);
  bool ComputeAddress(const Value *Obj, Address &Addr);
  bool SimplifyAddress(Address &Addr, MVT VT, int64_t ScaleFactor,
                       bool UseUnscaled);
  void AddLoadStoreOperands(Address &Addr, const MachineInstrBuilder &MIB,
                            unsigned Flags, bool UseUnscaled);
  bool IsMemCpySmall(uint64_t Len, unsigned Alignment);
  bool TryEmitSmallMemCpy(Address Dest, Address Src, uint64_t Len,
                          unsigned Alignment);
  bool foldXALUIntrinsic(AArch64CC::CondCode &CC, const Instruction *I,
                         const Value *Cond);

  // Emit functions.
  bool EmitCmp(Value *Src1Value, Value *Src2Value, bool isZExt);
  bool EmitLoad(MVT VT, unsigned &ResultReg, Address Addr,
                bool UseUnscaled = false);
  bool EmitStore(MVT VT, unsigned SrcReg, Address Addr,
                 bool UseUnscaled = false);
  unsigned EmitIntExt(MVT SrcVT, unsigned SrcReg, MVT DestVT, bool isZExt);
  unsigned Emiti1Ext(unsigned SrcReg, MVT DestVT, bool isZExt);
  unsigned Emit_MUL_rr(MVT RetVT, unsigned Op0, bool Op0IsKill,
                       unsigned Op1, bool Op1IsKill);
  unsigned Emit_SMULL_rr(MVT RetVT, unsigned Op0, bool Op0IsKill,
                         unsigned Op1, bool Op1IsKill);
  unsigned Emit_UMULL_rr(MVT RetVT, unsigned Op0, bool Op0IsKill,
                         unsigned Op1, bool Op1IsKill);
  unsigned Emit_LSL_ri(MVT RetVT, unsigned Op0, bool Op0IsKill, uint64_t Imm);
  unsigned Emit_LSR_ri(MVT RetVT, unsigned Op0, bool Op0IsKill, uint64_t Imm);
  unsigned Emit_ASR_ri(MVT RetVT, unsigned Op0, bool Op0IsKill, uint64_t Imm);

  unsigned AArch64MaterializeFP(const ConstantFP *CFP, MVT VT);
  unsigned AArch64MaterializeGV(const GlobalValue *GV);

  // Call handling routines.
private:
  CCAssignFn *CCAssignFnForCall(CallingConv::ID CC) const;
  bool ProcessCallArgs(CallLoweringInfo &CLI, SmallVectorImpl<MVT> &ArgVTs,
                       unsigned &NumBytes);
  bool FinishCall(CallLoweringInfo &CLI, MVT RetVT, unsigned NumBytes);

public:
  // Backend specific FastISel code.
  unsigned TargetMaterializeAlloca(const AllocaInst *AI) override;
  unsigned TargetMaterializeConstant(const Constant *C) override;

  explicit AArch64FastISel(FunctionLoweringInfo &funcInfo,
                         const TargetLibraryInfo *libInfo)
      : FastISel(funcInfo, libInfo) {
    Subtarget = &TM.getSubtarget<AArch64Subtarget>();
    Context = &funcInfo.Fn->getContext();
  }

  bool TargetSelectInstruction(const Instruction *I) override;

#include "AArch64GenFastISel.inc"
};

} // end anonymous namespace

#include "AArch64GenCallingConv.inc"

CCAssignFn *AArch64FastISel::CCAssignFnForCall(CallingConv::ID CC) const {
  if (CC == CallingConv::WebKit_JS)
    return CC_AArch64_WebKit_JS;
  return Subtarget->isTargetDarwin() ? CC_AArch64_DarwinPCS : CC_AArch64_AAPCS;
}

unsigned AArch64FastISel::TargetMaterializeAlloca(const AllocaInst *AI) {
  assert(TLI.getValueType(AI->getType(), true) == MVT::i64 &&
         "Alloca should always return a pointer.");

  // Don't handle dynamic allocas.
  if (!FuncInfo.StaticAllocaMap.count(AI))
    return 0;

  DenseMap<const AllocaInst *, int>::iterator SI =
      FuncInfo.StaticAllocaMap.find(AI);

  if (SI != FuncInfo.StaticAllocaMap.end()) {
    unsigned ResultReg = createResultReg(&AArch64::GPR64RegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ADDXri),
            ResultReg)
        .addFrameIndex(SI->second)
        .addImm(0)
        .addImm(0);
    return ResultReg;
  }

  return 0;
}

unsigned AArch64FastISel::AArch64MaterializeFP(const ConstantFP *CFP, MVT VT) {
  if (VT != MVT::f32 && VT != MVT::f64)
    return 0;

  const APFloat Val = CFP->getValueAPF();
  bool is64bit = (VT == MVT::f64);

  // This checks to see if we can use FMOV instructions to materialize
  // a constant, otherwise we have to materialize via the constant pool.
  if (TLI.isFPImmLegal(Val, VT)) {
    int Imm;
    unsigned Opc;
    if (is64bit) {
      Imm = AArch64_AM::getFP64Imm(Val);
      Opc = AArch64::FMOVDi;
    } else {
      Imm = AArch64_AM::getFP32Imm(Val);
      Opc = AArch64::FMOVSi;
    }
    unsigned ResultReg = createResultReg(TLI.getRegClassFor(VT));
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), ResultReg)
        .addImm(Imm);
    return ResultReg;
  }

  // Materialize via constant pool.  MachineConstantPool wants an explicit
  // alignment.
  unsigned Align = DL.getPrefTypeAlignment(CFP->getType());
  if (Align == 0)
    Align = DL.getTypeAllocSize(CFP->getType());

  unsigned Idx = MCP.getConstantPoolIndex(cast<Constant>(CFP), Align);
  unsigned ADRPReg = createResultReg(&AArch64::GPR64commonRegClass);
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ADRP),
          ADRPReg).addConstantPoolIndex(Idx, 0, AArch64II::MO_PAGE);

  unsigned Opc = is64bit ? AArch64::LDRDui : AArch64::LDRSui;
  unsigned ResultReg = createResultReg(TLI.getRegClassFor(VT));
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), ResultReg)
      .addReg(ADRPReg)
      .addConstantPoolIndex(Idx, 0, AArch64II::MO_PAGEOFF | AArch64II::MO_NC);
  return ResultReg;
}

unsigned AArch64FastISel::AArch64MaterializeGV(const GlobalValue *GV) {
  // We can't handle thread-local variables quickly yet.
  if (GV->isThreadLocal())
    return 0;

  // MachO still uses GOT for large code-model accesses, but ELF requires
  // movz/movk sequences, which FastISel doesn't handle yet.
  if (TM.getCodeModel() != CodeModel::Small && !Subtarget->isTargetMachO())
    return 0;

  unsigned char OpFlags = Subtarget->ClassifyGlobalReference(GV, TM);

  EVT DestEVT = TLI.getValueType(GV->getType(), true);
  if (!DestEVT.isSimple())
    return 0;

  unsigned ADRPReg = createResultReg(&AArch64::GPR64commonRegClass);
  unsigned ResultReg;

  if (OpFlags & AArch64II::MO_GOT) {
    // ADRP + LDRX
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ADRP),
            ADRPReg)
        .addGlobalAddress(GV, 0, AArch64II::MO_GOT | AArch64II::MO_PAGE);

    ResultReg = createResultReg(&AArch64::GPR64RegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::LDRXui),
            ResultReg)
        .addReg(ADRPReg)
        .addGlobalAddress(GV, 0, AArch64II::MO_GOT | AArch64II::MO_PAGEOFF |
                          AArch64II::MO_NC);
  } else {
    // ADRP + ADDX
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ADRP),
            ADRPReg).addGlobalAddress(GV, 0, AArch64II::MO_PAGE);

    ResultReg = createResultReg(&AArch64::GPR64spRegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ADDXri),
            ResultReg)
        .addReg(ADRPReg)
        .addGlobalAddress(GV, 0, AArch64II::MO_PAGEOFF | AArch64II::MO_NC)
        .addImm(0);
  }
  return ResultReg;
}

unsigned AArch64FastISel::TargetMaterializeConstant(const Constant *C) {
  EVT CEVT = TLI.getValueType(C->getType(), true);

  // Only handle simple types.
  if (!CEVT.isSimple())
    return 0;
  MVT VT = CEVT.getSimpleVT();

  // FIXME: Handle ConstantInt.
  if (const ConstantFP *CFP = dyn_cast<ConstantFP>(C))
    return AArch64MaterializeFP(CFP, VT);
  else if (const GlobalValue *GV = dyn_cast<GlobalValue>(C))
    return AArch64MaterializeGV(GV);

  return 0;
}

// Computes the address to get to an object.
bool AArch64FastISel::ComputeAddress(const Value *Obj, Address &Addr) {
  const User *U = nullptr;
  unsigned Opcode = Instruction::UserOp1;
  if (const Instruction *I = dyn_cast<Instruction>(Obj)) {
    // Don't walk into other basic blocks unless the object is an alloca from
    // another block, otherwise it may not have a virtual register assigned.
    if (FuncInfo.StaticAllocaMap.count(static_cast<const AllocaInst *>(Obj)) ||
        FuncInfo.MBBMap[I->getParent()] == FuncInfo.MBB) {
      Opcode = I->getOpcode();
      U = I;
    }
  } else if (const ConstantExpr *C = dyn_cast<ConstantExpr>(Obj)) {
    Opcode = C->getOpcode();
    U = C;
  }

  if (const PointerType *Ty = dyn_cast<PointerType>(Obj->getType()))
    if (Ty->getAddressSpace() > 255)
      // Fast instruction selection doesn't support the special
      // address spaces.
      return false;

  switch (Opcode) {
  default:
    break;
  case Instruction::BitCast: {
    // Look through bitcasts.
    return ComputeAddress(U->getOperand(0), Addr);
  }
  case Instruction::IntToPtr: {
    // Look past no-op inttoptrs.
    if (TLI.getValueType(U->getOperand(0)->getType()) == TLI.getPointerTy())
      return ComputeAddress(U->getOperand(0), Addr);
    break;
  }
  case Instruction::PtrToInt: {
    // Look past no-op ptrtoints.
    if (TLI.getValueType(U->getType()) == TLI.getPointerTy())
      return ComputeAddress(U->getOperand(0), Addr);
    break;
  }
  case Instruction::GetElementPtr: {
    Address SavedAddr = Addr;
    uint64_t TmpOffset = Addr.getOffset();

    // Iterate through the GEP folding the constants into offsets where
    // we can.
    gep_type_iterator GTI = gep_type_begin(U);
    for (User::const_op_iterator i = U->op_begin() + 1, e = U->op_end(); i != e;
         ++i, ++GTI) {
      const Value *Op = *i;
      if (StructType *STy = dyn_cast<StructType>(*GTI)) {
        const StructLayout *SL = DL.getStructLayout(STy);
        unsigned Idx = cast<ConstantInt>(Op)->getZExtValue();
        TmpOffset += SL->getElementOffset(Idx);
      } else {
        uint64_t S = DL.getTypeAllocSize(GTI.getIndexedType());
        for (;;) {
          if (const ConstantInt *CI = dyn_cast<ConstantInt>(Op)) {
            // Constant-offset addressing.
            TmpOffset += CI->getSExtValue() * S;
            break;
          }
          if (canFoldAddIntoGEP(U, Op)) {
            // A compatible add with a constant operand. Fold the constant.
            ConstantInt *CI =
                cast<ConstantInt>(cast<AddOperator>(Op)->getOperand(1));
            TmpOffset += CI->getSExtValue() * S;
            // Iterate on the other operand.
            Op = cast<AddOperator>(Op)->getOperand(0);
            continue;
          }
          // Unsupported
          goto unsupported_gep;
        }
      }
    }

    // Try to grab the base operand now.
    Addr.setOffset(TmpOffset);
    if (ComputeAddress(U->getOperand(0), Addr))
      return true;

    // We failed, restore everything and try the other options.
    Addr = SavedAddr;

  unsupported_gep:
    break;
  }
  case Instruction::Alloca: {
    const AllocaInst *AI = cast<AllocaInst>(Obj);
    DenseMap<const AllocaInst *, int>::iterator SI =
        FuncInfo.StaticAllocaMap.find(AI);
    if (SI != FuncInfo.StaticAllocaMap.end()) {
      Addr.setKind(Address::FrameIndexBase);
      Addr.setFI(SI->second);
      return true;
    }
    break;
  }
  }

  // Try to get this in a register if nothing else has worked.
  if (!Addr.isValid())
    Addr.setReg(getRegForValue(Obj));
  return Addr.isValid();
}

bool AArch64FastISel::isTypeLegal(Type *Ty, MVT &VT) {
  EVT evt = TLI.getValueType(Ty, true);

  // Only handle simple types.
  if (evt == MVT::Other || !evt.isSimple())
    return false;
  VT = evt.getSimpleVT();

  // This is a legal type, but it's not something we handle in fast-isel.
  if (VT == MVT::f128)
    return false;

  // Handle all other legal types, i.e. a register that will directly hold this
  // value.
  return TLI.isTypeLegal(VT);
}

bool AArch64FastISel::isLoadStoreTypeLegal(Type *Ty, MVT &VT) {
  if (isTypeLegal(Ty, VT))
    return true;

  // If this is a type than can be sign or zero-extended to a basic operation
  // go ahead and accept it now. For stores, this reflects truncation.
  if (VT == MVT::i1 || VT == MVT::i8 || VT == MVT::i16)
    return true;

  return false;
}

bool AArch64FastISel::SimplifyAddress(Address &Addr, MVT VT,
                                      int64_t ScaleFactor, bool UseUnscaled) {
  bool needsLowering = false;
  int64_t Offset = Addr.getOffset();
  switch (VT.SimpleTy) {
  default:
    return false;
  case MVT::i1:
  case MVT::i8:
  case MVT::i16:
  case MVT::i32:
  case MVT::i64:
  case MVT::f32:
  case MVT::f64:
    if (!UseUnscaled)
      // Using scaled, 12-bit, unsigned immediate offsets.
      needsLowering = ((Offset & 0xfff) != Offset);
    else
      // Using unscaled, 9-bit, signed immediate offsets.
      needsLowering = (Offset > 256 || Offset < -256);
    break;
  }

  //If this is a stack pointer and the offset needs to be simplified then put
  // the alloca address into a register, set the base type back to register and
  // continue. This should almost never happen.
  if (needsLowering && Addr.getKind() == Address::FrameIndexBase) {
    unsigned ResultReg = createResultReg(&AArch64::GPR64RegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ADDXri),
            ResultReg)
        .addFrameIndex(Addr.getFI())
        .addImm(0)
        .addImm(0);
    Addr.setKind(Address::RegBase);
    Addr.setReg(ResultReg);
  }

  // Since the offset is too large for the load/store instruction get the
  // reg+offset into a register.
  if (needsLowering) {
    uint64_t UnscaledOffset = Addr.getOffset() * ScaleFactor;
    unsigned ResultReg = FastEmit_ri_(MVT::i64, ISD::ADD, Addr.getReg(), false,
                                      UnscaledOffset, MVT::i64);
    if (ResultReg == 0)
      return false;
    Addr.setReg(ResultReg);
    Addr.setOffset(0);
  }
  return true;
}

void AArch64FastISel::AddLoadStoreOperands(Address &Addr,
                                           const MachineInstrBuilder &MIB,
                                           unsigned Flags, bool UseUnscaled) {
  int64_t Offset = Addr.getOffset();
  // Frame base works a bit differently. Handle it separately.
  if (Addr.getKind() == Address::FrameIndexBase) {
    int FI = Addr.getFI();
    // FIXME: We shouldn't be using getObjectSize/getObjectAlignment.  The size
    // and alignment should be based on the VT.
    MachineMemOperand *MMO = FuncInfo.MF->getMachineMemOperand(
        MachinePointerInfo::getFixedStack(FI, Offset), Flags,
        MFI.getObjectSize(FI), MFI.getObjectAlignment(FI));
    // Now add the rest of the operands.
    MIB.addFrameIndex(FI).addImm(Offset).addMemOperand(MMO);
  } else {
    // Now add the rest of the operands.
    MIB.addReg(Addr.getReg());
    MIB.addImm(Offset);
  }
}

bool AArch64FastISel::EmitLoad(MVT VT, unsigned &ResultReg, Address Addr,
                               bool UseUnscaled) {
  // Negative offsets require unscaled, 9-bit, signed immediate offsets.
  // Otherwise, we try using scaled, 12-bit, unsigned immediate offsets.
  if (!UseUnscaled && Addr.getOffset() < 0)
    UseUnscaled = true;

  unsigned Opc;
  const TargetRegisterClass *RC;
  bool VTIsi1 = false;
  int64_t ScaleFactor = 0;
  switch (VT.SimpleTy) {
  default:
    return false;
  case MVT::i1:
    VTIsi1 = true;
  // Intentional fall-through.
  case MVT::i8:
    Opc = UseUnscaled ? AArch64::LDURBBi : AArch64::LDRBBui;
    RC = &AArch64::GPR32RegClass;
    ScaleFactor = 1;
    break;
  case MVT::i16:
    Opc = UseUnscaled ? AArch64::LDURHHi : AArch64::LDRHHui;
    RC = &AArch64::GPR32RegClass;
    ScaleFactor = 2;
    break;
  case MVT::i32:
    Opc = UseUnscaled ? AArch64::LDURWi : AArch64::LDRWui;
    RC = &AArch64::GPR32RegClass;
    ScaleFactor = 4;
    break;
  case MVT::i64:
    Opc = UseUnscaled ? AArch64::LDURXi : AArch64::LDRXui;
    RC = &AArch64::GPR64RegClass;
    ScaleFactor = 8;
    break;
  case MVT::f32:
    Opc = UseUnscaled ? AArch64::LDURSi : AArch64::LDRSui;
    RC = TLI.getRegClassFor(VT);
    ScaleFactor = 4;
    break;
  case MVT::f64:
    Opc = UseUnscaled ? AArch64::LDURDi : AArch64::LDRDui;
    RC = TLI.getRegClassFor(VT);
    ScaleFactor = 8;
    break;
  }
  // Scale the offset.
  if (!UseUnscaled) {
    int64_t Offset = Addr.getOffset();
    if (Offset & (ScaleFactor - 1))
      // Retry using an unscaled, 9-bit, signed immediate offset.
      return EmitLoad(VT, ResultReg, Addr, /*UseUnscaled*/ true);

    Addr.setOffset(Offset / ScaleFactor);
  }

  // Simplify this down to something we can handle.
  if (!SimplifyAddress(Addr, VT, UseUnscaled ? 1 : ScaleFactor, UseUnscaled))
    return false;

  // Create the base instruction, then add the operands.
  ResultReg = createResultReg(RC);
  MachineInstrBuilder MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
                                    TII.get(Opc), ResultReg);
  AddLoadStoreOperands(Addr, MIB, MachineMemOperand::MOLoad, UseUnscaled);

  // Loading an i1 requires special handling.
  if (VTIsi1) {
    MRI.constrainRegClass(ResultReg, &AArch64::GPR32RegClass);
    unsigned ANDReg = createResultReg(&AArch64::GPR32spRegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ANDWri),
            ANDReg)
        .addReg(ResultReg)
        .addImm(AArch64_AM::encodeLogicalImmediate(1, 32));
    ResultReg = ANDReg;
  }
  return true;
}

bool AArch64FastISel::SelectLoad(const Instruction *I) {
  MVT VT;
  // Verify we have a legal type before going any further.  Currently, we handle
  // simple types that will directly fit in a register (i32/f32/i64/f64) or
  // those that can be sign or zero-extended to a basic operation (i1/i8/i16).
  if (!isLoadStoreTypeLegal(I->getType(), VT) || cast<LoadInst>(I)->isAtomic())
    return false;

  // See if we can handle this address.
  Address Addr;
  if (!ComputeAddress(I->getOperand(0), Addr))
    return false;

  unsigned ResultReg;
  if (!EmitLoad(VT, ResultReg, Addr))
    return false;

  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::EmitStore(MVT VT, unsigned SrcReg, Address Addr,
                                bool UseUnscaled) {
  // Negative offsets require unscaled, 9-bit, signed immediate offsets.
  // Otherwise, we try using scaled, 12-bit, unsigned immediate offsets.
  if (!UseUnscaled && Addr.getOffset() < 0)
    UseUnscaled = true;

  unsigned StrOpc;
  bool VTIsi1 = false;
  int64_t ScaleFactor = 0;
  // Using scaled, 12-bit, unsigned immediate offsets.
  switch (VT.SimpleTy) {
  default:
    return false;
  case MVT::i1:
    VTIsi1 = true;
  case MVT::i8:
    StrOpc = UseUnscaled ? AArch64::STURBBi : AArch64::STRBBui;
    ScaleFactor = 1;
    break;
  case MVT::i16:
    StrOpc = UseUnscaled ? AArch64::STURHHi : AArch64::STRHHui;
    ScaleFactor = 2;
    break;
  case MVT::i32:
    StrOpc = UseUnscaled ? AArch64::STURWi : AArch64::STRWui;
    ScaleFactor = 4;
    break;
  case MVT::i64:
    StrOpc = UseUnscaled ? AArch64::STURXi : AArch64::STRXui;
    ScaleFactor = 8;
    break;
  case MVT::f32:
    StrOpc = UseUnscaled ? AArch64::STURSi : AArch64::STRSui;
    ScaleFactor = 4;
    break;
  case MVT::f64:
    StrOpc = UseUnscaled ? AArch64::STURDi : AArch64::STRDui;
    ScaleFactor = 8;
    break;
  }
  // Scale the offset.
  if (!UseUnscaled) {
    int64_t Offset = Addr.getOffset();
    if (Offset & (ScaleFactor - 1))
      // Retry using an unscaled, 9-bit, signed immediate offset.
      return EmitStore(VT, SrcReg, Addr, /*UseUnscaled*/ true);

    Addr.setOffset(Offset / ScaleFactor);
  }

  // Simplify this down to something we can handle.
  if (!SimplifyAddress(Addr, VT, UseUnscaled ? 1 : ScaleFactor, UseUnscaled))
    return false;

  // Storing an i1 requires special handling.
  if (VTIsi1) {
    MRI.constrainRegClass(SrcReg, &AArch64::GPR32RegClass);
    unsigned ANDReg = createResultReg(&AArch64::GPR32spRegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ANDWri),
            ANDReg)
        .addReg(SrcReg)
        .addImm(AArch64_AM::encodeLogicalImmediate(1, 32));
    SrcReg = ANDReg;
  }
  // Create the base instruction, then add the operands.
  MachineInstrBuilder MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
                                    TII.get(StrOpc)).addReg(SrcReg);
  AddLoadStoreOperands(Addr, MIB, MachineMemOperand::MOStore, UseUnscaled);
  return true;
}

bool AArch64FastISel::SelectStore(const Instruction *I) {
  MVT VT;
  Value *Op0 = I->getOperand(0);
  // Verify we have a legal type before going any further.  Currently, we handle
  // simple types that will directly fit in a register (i32/f32/i64/f64) or
  // those that can be sign or zero-extended to a basic operation (i1/i8/i16).
  if (!isLoadStoreTypeLegal(Op0->getType(), VT) ||
      cast<StoreInst>(I)->isAtomic())
    return false;

  // Get the value to be stored into a register.
  unsigned SrcReg = getRegForValue(Op0);
  if (SrcReg == 0)
    return false;

  // See if we can handle this address.
  Address Addr;
  if (!ComputeAddress(I->getOperand(1), Addr))
    return false;

  if (!EmitStore(VT, SrcReg, Addr))
    return false;
  return true;
}

static AArch64CC::CondCode getCompareCC(CmpInst::Predicate Pred) {
  switch (Pred) {
  case CmpInst::FCMP_ONE:
  case CmpInst::FCMP_UEQ:
  default:
    // AL is our "false" for now. The other two need more compares.
    return AArch64CC::AL;
  case CmpInst::ICMP_EQ:
  case CmpInst::FCMP_OEQ:
    return AArch64CC::EQ;
  case CmpInst::ICMP_SGT:
  case CmpInst::FCMP_OGT:
    return AArch64CC::GT;
  case CmpInst::ICMP_SGE:
  case CmpInst::FCMP_OGE:
    return AArch64CC::GE;
  case CmpInst::ICMP_UGT:
  case CmpInst::FCMP_UGT:
    return AArch64CC::HI;
  case CmpInst::FCMP_OLT:
    return AArch64CC::MI;
  case CmpInst::ICMP_ULE:
  case CmpInst::FCMP_OLE:
    return AArch64CC::LS;
  case CmpInst::FCMP_ORD:
    return AArch64CC::VC;
  case CmpInst::FCMP_UNO:
    return AArch64CC::VS;
  case CmpInst::FCMP_UGE:
    return AArch64CC::PL;
  case CmpInst::ICMP_SLT:
  case CmpInst::FCMP_ULT:
    return AArch64CC::LT;
  case CmpInst::ICMP_SLE:
  case CmpInst::FCMP_ULE:
    return AArch64CC::LE;
  case CmpInst::FCMP_UNE:
  case CmpInst::ICMP_NE:
    return AArch64CC::NE;
  case CmpInst::ICMP_UGE:
    return AArch64CC::HS;
  case CmpInst::ICMP_ULT:
    return AArch64CC::LO;
  }
}

bool AArch64FastISel::SelectBranch(const Instruction *I) {
  const BranchInst *BI = cast<BranchInst>(I);
  MachineBasicBlock *TBB = FuncInfo.MBBMap[BI->getSuccessor(0)];
  MachineBasicBlock *FBB = FuncInfo.MBBMap[BI->getSuccessor(1)];

  AArch64CC::CondCode CC = AArch64CC::NE;
  if (const CmpInst *CI = dyn_cast<CmpInst>(BI->getCondition())) {
    if (CI->hasOneUse() && (CI->getParent() == I->getParent())) {
      // We may not handle every CC for now.
      CC = getCompareCC(CI->getPredicate());
      if (CC == AArch64CC::AL)
        return false;

      // Emit the cmp.
      if (!EmitCmp(CI->getOperand(0), CI->getOperand(1), CI->isUnsigned()))
        return false;

      // Emit the branch.
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::Bcc))
          .addImm(CC)
          .addMBB(TBB);
      FuncInfo.MBB->addSuccessor(TBB);

      FastEmitBranch(FBB, DbgLoc);
      return true;
    }
  } else if (TruncInst *TI = dyn_cast<TruncInst>(BI->getCondition())) {
    MVT SrcVT;
    if (TI->hasOneUse() && TI->getParent() == I->getParent() &&
        (isLoadStoreTypeLegal(TI->getOperand(0)->getType(), SrcVT))) {
      unsigned CondReg = getRegForValue(TI->getOperand(0));
      if (CondReg == 0)
        return false;

      // Issue an extract_subreg to get the lower 32-bits.
      if (SrcVT == MVT::i64)
        CondReg = FastEmitInst_extractsubreg(MVT::i32, CondReg, /*Kill=*/true,
                                             AArch64::sub_32);

      MRI.constrainRegClass(CondReg, &AArch64::GPR32RegClass);
      unsigned ANDReg = createResultReg(&AArch64::GPR32spRegClass);
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
              TII.get(AArch64::ANDWri), ANDReg)
          .addReg(CondReg)
          .addImm(AArch64_AM::encodeLogicalImmediate(1, 32));
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
              TII.get(AArch64::SUBSWri))
          .addReg(ANDReg)
          .addReg(ANDReg)
          .addImm(0)
          .addImm(0);

      if (FuncInfo.MBB->isLayoutSuccessor(TBB)) {
        std::swap(TBB, FBB);
        CC = AArch64CC::EQ;
      }
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::Bcc))
          .addImm(CC)
          .addMBB(TBB);
      FuncInfo.MBB->addSuccessor(TBB);
      FastEmitBranch(FBB, DbgLoc);
      return true;
    }
  } else if (const ConstantInt *CI =
                 dyn_cast<ConstantInt>(BI->getCondition())) {
    uint64_t Imm = CI->getZExtValue();
    MachineBasicBlock *Target = (Imm == 0) ? FBB : TBB;
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::B))
        .addMBB(Target);
    FuncInfo.MBB->addSuccessor(Target);
    return true;
  } else if (foldXALUIntrinsic(CC, I, BI->getCondition())) {
    // Fake request the condition, otherwise the intrinsic might be completely
    // optimized away.
    unsigned CondReg = getRegForValue(BI->getCondition());
    if (!CondReg)
      return false;

    // Emit the branch.
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::Bcc))
      .addImm(CC)
      .addMBB(TBB);
    FuncInfo.MBB->addSuccessor(TBB);

    FastEmitBranch(FBB, DbgLoc);
    return true;
  }

  unsigned CondReg = getRegForValue(BI->getCondition());
  if (CondReg == 0)
    return false;

  // We've been divorced from our compare!  Our block was split, and
  // now our compare lives in a predecessor block.  We musn't
  // re-compare here, as the children of the compare aren't guaranteed
  // live across the block boundary (we *could* check for this).
  // Regardless, the compare has been done in the predecessor block,
  // and it left a value for us in a virtual register.  Ergo, we test
  // the one-bit value left in the virtual register.
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::SUBSWri),
          AArch64::WZR)
      .addReg(CondReg)
      .addImm(0)
      .addImm(0);

  if (FuncInfo.MBB->isLayoutSuccessor(TBB)) {
    std::swap(TBB, FBB);
    CC = AArch64CC::EQ;
  }

  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::Bcc))
      .addImm(CC)
      .addMBB(TBB);
  FuncInfo.MBB->addSuccessor(TBB);
  FastEmitBranch(FBB, DbgLoc);
  return true;
}

bool AArch64FastISel::SelectIndirectBr(const Instruction *I) {
  const IndirectBrInst *BI = cast<IndirectBrInst>(I);
  unsigned AddrReg = getRegForValue(BI->getOperand(0));
  if (AddrReg == 0)
    return false;

  // Emit the indirect branch.
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::BR))
      .addReg(AddrReg);

  // Make sure the CFG is up-to-date.
  for (unsigned i = 0, e = BI->getNumSuccessors(); i != e; ++i)
    FuncInfo.MBB->addSuccessor(FuncInfo.MBBMap[BI->getSuccessor(i)]);

  return true;
}

bool AArch64FastISel::EmitCmp(Value *Src1Value, Value *Src2Value, bool isZExt) {
  Type *Ty = Src1Value->getType();
  EVT SrcEVT = TLI.getValueType(Ty, true);
  if (!SrcEVT.isSimple())
    return false;
  MVT SrcVT = SrcEVT.getSimpleVT();

  // Check to see if the 2nd operand is a constant that we can encode directly
  // in the compare.
  uint64_t Imm;
  bool UseImm = false;
  bool isNegativeImm = false;
  if (const ConstantInt *ConstInt = dyn_cast<ConstantInt>(Src2Value)) {
    if (SrcVT == MVT::i64 || SrcVT == MVT::i32 || SrcVT == MVT::i16 ||
        SrcVT == MVT::i8 || SrcVT == MVT::i1) {
      const APInt &CIVal = ConstInt->getValue();

      Imm = (isZExt) ? CIVal.getZExtValue() : CIVal.getSExtValue();
      if (CIVal.isNegative()) {
        isNegativeImm = true;
        Imm = -Imm;
      }
      // FIXME: We can handle more immediates using shifts.
      UseImm = ((Imm & 0xfff) == Imm);
    }
  } else if (const ConstantFP *ConstFP = dyn_cast<ConstantFP>(Src2Value)) {
    if (SrcVT == MVT::f32 || SrcVT == MVT::f64)
      if (ConstFP->isZero() && !ConstFP->isNegative())
        UseImm = true;
  }

  unsigned ZReg;
  unsigned CmpOpc;
  bool isICmp = true;
  bool needsExt = false;
  switch (SrcVT.SimpleTy) {
  default:
    return false;
  case MVT::i1:
  case MVT::i8:
  case MVT::i16:
    needsExt = true;
  // Intentional fall-through.
  case MVT::i32:
    ZReg = AArch64::WZR;
    if (UseImm)
      CmpOpc = isNegativeImm ? AArch64::ADDSWri : AArch64::SUBSWri;
    else
      CmpOpc = AArch64::SUBSWrr;
    break;
  case MVT::i64:
    ZReg = AArch64::XZR;
    if (UseImm)
      CmpOpc = isNegativeImm ? AArch64::ADDSXri : AArch64::SUBSXri;
    else
      CmpOpc = AArch64::SUBSXrr;
    break;
  case MVT::f32:
    isICmp = false;
    CmpOpc = UseImm ? AArch64::FCMPSri : AArch64::FCMPSrr;
    break;
  case MVT::f64:
    isICmp = false;
    CmpOpc = UseImm ? AArch64::FCMPDri : AArch64::FCMPDrr;
    break;
  }

  unsigned SrcReg1 = getRegForValue(Src1Value);
  if (SrcReg1 == 0)
    return false;

  unsigned SrcReg2;
  if (!UseImm) {
    SrcReg2 = getRegForValue(Src2Value);
    if (SrcReg2 == 0)
      return false;
  }

  // We have i1, i8, or i16, we need to either zero extend or sign extend.
  if (needsExt) {
    SrcReg1 = EmitIntExt(SrcVT, SrcReg1, MVT::i32, isZExt);
    if (SrcReg1 == 0)
      return false;
    if (!UseImm) {
      SrcReg2 = EmitIntExt(SrcVT, SrcReg2, MVT::i32, isZExt);
      if (SrcReg2 == 0)
        return false;
    }
  }

  if (isICmp) {
    if (UseImm)
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(CmpOpc))
          .addReg(ZReg)
          .addReg(SrcReg1)
          .addImm(Imm)
          .addImm(0);
    else
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(CmpOpc))
          .addReg(ZReg)
          .addReg(SrcReg1)
          .addReg(SrcReg2);
  } else {
    if (UseImm)
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(CmpOpc))
          .addReg(SrcReg1);
    else
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(CmpOpc))
          .addReg(SrcReg1)
          .addReg(SrcReg2);
  }
  return true;
}

bool AArch64FastISel::SelectCmp(const Instruction *I) {
  const CmpInst *CI = cast<CmpInst>(I);

  // We may not handle every CC for now.
  AArch64CC::CondCode CC = getCompareCC(CI->getPredicate());
  if (CC == AArch64CC::AL)
    return false;

  // Emit the cmp.
  if (!EmitCmp(CI->getOperand(0), CI->getOperand(1), CI->isUnsigned()))
    return false;

  // Now set a register based on the comparison.
  AArch64CC::CondCode invertedCC = getInvertedCondCode(CC);
  unsigned ResultReg = createResultReg(&AArch64::GPR32RegClass);
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::CSINCWr),
          ResultReg)
      .addReg(AArch64::WZR)
      .addReg(AArch64::WZR)
      .addImm(invertedCC);

  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::SelectSelect(const Instruction *I) {
  const SelectInst *SI = cast<SelectInst>(I);

  EVT DestEVT = TLI.getValueType(SI->getType(), true);
  if (!DestEVT.isSimple())
    return false;

  MVT DestVT = DestEVT.getSimpleVT();
  if (DestVT != MVT::i32 && DestVT != MVT::i64 && DestVT != MVT::f32 &&
      DestVT != MVT::f64)
    return false;

  unsigned SelectOpc;
  switch (DestVT.SimpleTy) {
  default: return false;
  case MVT::i32: SelectOpc = AArch64::CSELWr;    break;
  case MVT::i64: SelectOpc = AArch64::CSELXr;    break;
  case MVT::f32: SelectOpc = AArch64::FCSELSrrr; break;
  case MVT::f64: SelectOpc = AArch64::FCSELDrrr; break;
  }

  const Value *Cond = SI->getCondition();
  bool NeedTest = true;
  AArch64CC::CondCode CC = AArch64CC::NE;
  if (foldXALUIntrinsic(CC, I, Cond))
    NeedTest = false;

  unsigned CondReg = getRegForValue(Cond);
  if (!CondReg)
    return false;
  bool CondIsKill = hasTrivialKill(Cond);

  if (NeedTest) {
    MRI.constrainRegClass(CondReg, &AArch64::GPR32RegClass);
    unsigned ANDReg = createResultReg(&AArch64::GPR32spRegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ANDWri),
            ANDReg)
      .addReg(CondReg, getKillRegState(CondIsKill))
      .addImm(AArch64_AM::encodeLogicalImmediate(1, 32));

    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::SUBSWri))
      .addReg(ANDReg)
      .addReg(ANDReg)
      .addImm(0)
      .addImm(0);
  }

  unsigned TrueReg = getRegForValue(SI->getTrueValue());
  bool TrueIsKill = hasTrivialKill(SI->getTrueValue());

  unsigned FalseReg = getRegForValue(SI->getFalseValue());
  bool FalseIsKill = hasTrivialKill(SI->getFalseValue());

  if (!TrueReg || !FalseReg)
    return false;

  unsigned ResultReg = createResultReg(TLI.getRegClassFor(DestVT));
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(SelectOpc),
          ResultReg)
    .addReg(TrueReg, getKillRegState(TrueIsKill))
    .addReg(FalseReg, getKillRegState(FalseIsKill))
    .addImm(CC);

  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::SelectFPExt(const Instruction *I) {
  Value *V = I->getOperand(0);
  if (!I->getType()->isDoubleTy() || !V->getType()->isFloatTy())
    return false;

  unsigned Op = getRegForValue(V);
  if (Op == 0)
    return false;

  unsigned ResultReg = createResultReg(&AArch64::FPR64RegClass);
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::FCVTDSr),
          ResultReg).addReg(Op);
  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::SelectFPTrunc(const Instruction *I) {
  Value *V = I->getOperand(0);
  if (!I->getType()->isFloatTy() || !V->getType()->isDoubleTy())
    return false;

  unsigned Op = getRegForValue(V);
  if (Op == 0)
    return false;

  unsigned ResultReg = createResultReg(&AArch64::FPR32RegClass);
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::FCVTSDr),
          ResultReg).addReg(Op);
  UpdateValueMap(I, ResultReg);
  return true;
}

// FPToUI and FPToSI
bool AArch64FastISel::SelectFPToInt(const Instruction *I, bool Signed) {
  MVT DestVT;
  if (!isTypeLegal(I->getType(), DestVT) || DestVT.isVector())
    return false;

  unsigned SrcReg = getRegForValue(I->getOperand(0));
  if (SrcReg == 0)
    return false;

  EVT SrcVT = TLI.getValueType(I->getOperand(0)->getType(), true);
  if (SrcVT == MVT::f128)
    return false;

  unsigned Opc;
  if (SrcVT == MVT::f64) {
    if (Signed)
      Opc = (DestVT == MVT::i32) ? AArch64::FCVTZSUWDr : AArch64::FCVTZSUXDr;
    else
      Opc = (DestVT == MVT::i32) ? AArch64::FCVTZUUWDr : AArch64::FCVTZUUXDr;
  } else {
    if (Signed)
      Opc = (DestVT == MVT::i32) ? AArch64::FCVTZSUWSr : AArch64::FCVTZSUXSr;
    else
      Opc = (DestVT == MVT::i32) ? AArch64::FCVTZUUWSr : AArch64::FCVTZUUXSr;
  }
  unsigned ResultReg = createResultReg(
      DestVT == MVT::i32 ? &AArch64::GPR32RegClass : &AArch64::GPR64RegClass);
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), ResultReg)
      .addReg(SrcReg);
  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::SelectIntToFP(const Instruction *I, bool Signed) {
  MVT DestVT;
  if (!isTypeLegal(I->getType(), DestVT) || DestVT.isVector())
    return false;
  assert ((DestVT == MVT::f32 || DestVT == MVT::f64) &&
          "Unexpected value type.");

  unsigned SrcReg = getRegForValue(I->getOperand(0));
  if (SrcReg == 0)
    return false;

  EVT SrcVT = TLI.getValueType(I->getOperand(0)->getType(), true);

  // Handle sign-extension.
  if (SrcVT == MVT::i16 || SrcVT == MVT::i8 || SrcVT == MVT::i1) {
    SrcReg =
        EmitIntExt(SrcVT.getSimpleVT(), SrcReg, MVT::i32, /*isZExt*/ !Signed);
    if (SrcReg == 0)
      return false;
  }

  MRI.constrainRegClass(SrcReg, SrcVT == MVT::i64 ? &AArch64::GPR64RegClass
                                                  : &AArch64::GPR32RegClass);

  unsigned Opc;
  if (SrcVT == MVT::i64) {
    if (Signed)
      Opc = (DestVT == MVT::f32) ? AArch64::SCVTFUXSri : AArch64::SCVTFUXDri;
    else
      Opc = (DestVT == MVT::f32) ? AArch64::UCVTFUXSri : AArch64::UCVTFUXDri;
  } else {
    if (Signed)
      Opc = (DestVT == MVT::f32) ? AArch64::SCVTFUWSri : AArch64::SCVTFUWDri;
    else
      Opc = (DestVT == MVT::f32) ? AArch64::UCVTFUWSri : AArch64::UCVTFUWDri;
  }

  unsigned ResultReg = createResultReg(TLI.getRegClassFor(DestVT));
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), ResultReg)
      .addReg(SrcReg);
  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::ProcessCallArgs(CallLoweringInfo &CLI,
                                      SmallVectorImpl<MVT> &OutVTs,
                                      unsigned &NumBytes) {
  CallingConv::ID CC = CLI.CallConv;
  SmallVector<CCValAssign, 16> ArgLocs;
  CCState CCInfo(CC, false, *FuncInfo.MF, TM, ArgLocs, *Context);
  CCInfo.AnalyzeCallOperands(OutVTs, CLI.OutFlags, CCAssignFnForCall(CC));

  // Get a count of how many bytes are to be pushed on the stack.
  NumBytes = CCInfo.getNextStackOffset();

  // Issue CALLSEQ_START
  unsigned AdjStackDown = TII.getCallFrameSetupOpcode();
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AdjStackDown))
    .addImm(NumBytes);

  // Process the args.
  for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i) {
    CCValAssign &VA = ArgLocs[i];
    const Value *ArgVal = CLI.OutVals[VA.getValNo()];
    MVT ArgVT = OutVTs[VA.getValNo()];

    unsigned ArgReg = getRegForValue(ArgVal);
    if (!ArgReg)
      return false;

    // Handle arg promotion: SExt, ZExt, AExt.
    switch (VA.getLocInfo()) {
    case CCValAssign::Full:
      break;
    case CCValAssign::SExt: {
      MVT DestVT = VA.getLocVT();
      MVT SrcVT = ArgVT;
      ArgReg = EmitIntExt(SrcVT, ArgReg, DestVT, /*isZExt=*/false);
      if (!ArgReg)
        return false;
      break;
    }
    case CCValAssign::AExt:
    // Intentional fall-through.
    case CCValAssign::ZExt: {
      MVT DestVT = VA.getLocVT();
      MVT SrcVT = ArgVT;
      ArgReg = EmitIntExt(SrcVT, ArgReg, DestVT, /*isZExt=*/true);
      if (!ArgReg)
        return false;
      break;
    }
    default:
      llvm_unreachable("Unknown arg promotion!");
    }

    // Now copy/store arg to correct locations.
    if (VA.isRegLoc() && !VA.needsCustom()) {
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
              TII.get(TargetOpcode::COPY), VA.getLocReg()).addReg(ArgReg);
      CLI.OutRegs.push_back(VA.getLocReg());
    } else if (VA.needsCustom()) {
      // FIXME: Handle custom args.
      return false;
    } else {
      assert(VA.isMemLoc() && "Assuming store on stack.");

      // Don't emit stores for undef values.
      if (isa<UndefValue>(ArgVal))
        continue;

      // Need to store on the stack.
      unsigned ArgSize = (ArgVT.getSizeInBits() + 7) / 8;

      unsigned BEAlign = 0;
      if (ArgSize < 8 && !Subtarget->isLittleEndian())
        BEAlign = 8 - ArgSize;

      Address Addr;
      Addr.setKind(Address::RegBase);
      Addr.setReg(AArch64::SP);
      Addr.setOffset(VA.getLocMemOffset() + BEAlign);

      if (!EmitStore(ArgVT, ArgReg, Addr))
        return false;
    }
  }
  return true;
}

bool AArch64FastISel::FinishCall(CallLoweringInfo &CLI, MVT RetVT,
                                 unsigned NumBytes) {
  CallingConv::ID CC = CLI.CallConv;

  // Issue CALLSEQ_END
  unsigned AdjStackUp = TII.getCallFrameDestroyOpcode();
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AdjStackUp))
    .addImm(NumBytes).addImm(0);

  // Now the return value.
  if (RetVT != MVT::isVoid) {
    SmallVector<CCValAssign, 16> RVLocs;
    CCState CCInfo(CC, false, *FuncInfo.MF, TM, RVLocs, *Context);
    CCInfo.AnalyzeCallResult(RetVT, CCAssignFnForCall(CC));

    // Only handle a single return value.
    if (RVLocs.size() != 1)
      return false;

    // Copy all of the result registers out of their specified physreg.
    MVT CopyVT = RVLocs[0].getValVT();
    unsigned ResultReg = createResultReg(TLI.getRegClassFor(CopyVT));
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
            TII.get(TargetOpcode::COPY), ResultReg)
      .addReg(RVLocs[0].getLocReg());
    CLI.InRegs.push_back(RVLocs[0].getLocReg());

    CLI.ResultReg = ResultReg;
    CLI.NumResultRegs = 1;
  }

  return true;
}

bool AArch64FastISel::FastLowerCall(CallLoweringInfo &CLI) {
  CallingConv::ID CC  = CLI.CallConv;
  bool IsVarArg       = CLI.IsVarArg;
  const Value *Callee = CLI.Callee;
  const char *SymName = CLI.SymName;

  // Only handle global variable Callees.
  const GlobalValue *GV = dyn_cast<GlobalValue>(Callee);
  if (!GV)
    return false;

  // Let SDISel handle vararg functions.
  if (IsVarArg)
    return false;

  // FIXME: Only handle *simple* calls for now.
  MVT RetVT;
  if (CLI.RetTy->isVoidTy())
    RetVT = MVT::isVoid;
  else if (!isTypeLegal(CLI.RetTy, RetVT))
    return false;

  for (auto Flag : CLI.OutFlags)
    if (Flag.isInReg() || Flag.isSRet() || Flag.isNest() || Flag.isByVal())
      return false;

  // Set up the argument vectors.
  SmallVector<MVT, 16> OutVTs;
  OutVTs.reserve(CLI.OutVals.size());

  for (auto *Val : CLI.OutVals) {
    MVT VT;
    if (!isTypeLegal(Val->getType(), VT) &&
        !(VT == MVT::i1 || VT == MVT::i8 || VT == MVT::i16))
      return false;

    // We don't handle vector parameters yet.
    if (VT.isVector() || VT.getSizeInBits() > 64)
      return false;

    OutVTs.push_back(VT);
  }

  // Handle the arguments now that we've gotten them.
  unsigned NumBytes;
  if (!ProcessCallArgs(CLI, OutVTs, NumBytes))
    return false;

  // Issue the call.
  MachineInstrBuilder MIB;
  MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::BL));
  CLI.Call = MIB;
  if (!SymName)
    MIB.addGlobalAddress(GV, 0, 0);
  else
    MIB.addExternalSymbol(SymName, 0);

  // Add implicit physical register uses to the call.
  for (auto Reg : CLI.OutRegs)
    MIB.addReg(Reg, RegState::Implicit);

  // Add a register mask with the call-preserved registers.
  // Proper defs for return values will be added by setPhysRegsDeadExcept().
  MIB.addRegMask(TRI.getCallPreservedMask(CC));

  // Finish off the call including any return values.
  return FinishCall(CLI, RetVT, NumBytes);
}

bool AArch64FastISel::IsMemCpySmall(uint64_t Len, unsigned Alignment) {
  if (Alignment)
    return Len / Alignment <= 4;
  else
    return Len < 32;
}

bool AArch64FastISel::TryEmitSmallMemCpy(Address Dest, Address Src,
                                         uint64_t Len, unsigned Alignment) {
  // Make sure we don't bloat code by inlining very large memcpy's.
  if (!IsMemCpySmall(Len, Alignment))
    return false;

  int64_t UnscaledOffset = 0;
  Address OrigDest = Dest;
  Address OrigSrc = Src;

  while (Len) {
    MVT VT;
    if (!Alignment || Alignment >= 8) {
      if (Len >= 8)
        VT = MVT::i64;
      else if (Len >= 4)
        VT = MVT::i32;
      else if (Len >= 2)
        VT = MVT::i16;
      else {
        VT = MVT::i8;
      }
    } else {
      // Bound based on alignment.
      if (Len >= 4 && Alignment == 4)
        VT = MVT::i32;
      else if (Len >= 2 && Alignment == 2)
        VT = MVT::i16;
      else {
        VT = MVT::i8;
      }
    }

    bool RV;
    unsigned ResultReg;
    RV = EmitLoad(VT, ResultReg, Src);
    if (!RV)
      return false;

    RV = EmitStore(VT, ResultReg, Dest);
    if (!RV)
      return false;

    int64_t Size = VT.getSizeInBits() / 8;
    Len -= Size;
    UnscaledOffset += Size;

    // We need to recompute the unscaled offset for each iteration.
    Dest.setOffset(OrigDest.getOffset() + UnscaledOffset);
    Src.setOffset(OrigSrc.getOffset() + UnscaledOffset);
  }

  return true;
}

/// \brief Check if it is possible to fold the condition from the XALU intrinsic
/// into the user. The condition code will only be updated on success.
bool AArch64FastISel::foldXALUIntrinsic(AArch64CC::CondCode &CC,
                                        const Instruction *I,
                                        const Value *Cond) {
  if (!isa<ExtractValueInst>(Cond))
    return false;

  const auto *EV = cast<ExtractValueInst>(Cond);
  if (!isa<IntrinsicInst>(EV->getAggregateOperand()))
    return false;

  const auto *II = cast<IntrinsicInst>(EV->getAggregateOperand());
  MVT RetVT;
  const Function *Callee = II->getCalledFunction();
  Type *RetTy =
  cast<StructType>(Callee->getReturnType())->getTypeAtIndex(0U);
  if (!isTypeLegal(RetTy, RetVT))
    return false;

  if (RetVT != MVT::i32 && RetVT != MVT::i64)
    return false;

  AArch64CC::CondCode TmpCC;
  switch (II->getIntrinsicID()) {
    default: return false;
    case Intrinsic::sadd_with_overflow:
    case Intrinsic::ssub_with_overflow: TmpCC = AArch64CC::VS; break;
    case Intrinsic::uadd_with_overflow: TmpCC = AArch64CC::HS; break;
    case Intrinsic::usub_with_overflow: TmpCC = AArch64CC::LO; break;
    case Intrinsic::smul_with_overflow:
    case Intrinsic::umul_with_overflow: TmpCC = AArch64CC::NE; break;
  }

  // Check if both instructions are in the same basic block.
  if (II->getParent() != I->getParent())
    return false;

  // Make sure nothing is in the way
  BasicBlock::const_iterator Start = I;
  BasicBlock::const_iterator End = II;
  for (auto Itr = std::prev(Start); Itr != End; --Itr) {
    // We only expect extractvalue instructions between the intrinsic and the
    // instruction to be selected.
    if (!isa<ExtractValueInst>(Itr))
      return false;

    // Check that the extractvalue operand comes from the intrinsic.
    const auto *EVI = cast<ExtractValueInst>(Itr);
    if (EVI->getAggregateOperand() != II)
      return false;
  }

  CC = TmpCC;
  return true;
}

bool AArch64FastISel::FastLowerIntrinsicCall(const IntrinsicInst *II) {
  // FIXME: Handle more intrinsics.
  switch (II->getIntrinsicID()) {
  default: return false;
  case Intrinsic::frameaddress: {
    MachineFrameInfo *MFI = FuncInfo.MF->getFrameInfo();
    MFI->setFrameAddressIsTaken(true);

    const AArch64RegisterInfo *RegInfo =
      static_cast<const AArch64RegisterInfo *>(TM.getRegisterInfo());
    unsigned FramePtr = RegInfo->getFrameRegister(*(FuncInfo.MF));
    unsigned SrcReg = FramePtr;

    // Recursively load frame address
    // ldr x0, [fp]
    // ldr x0, [x0]
    // ldr x0, [x0]
    // ...
    unsigned DestReg;
    unsigned Depth = cast<ConstantInt>(II->getOperand(0))->getZExtValue();
    while (Depth--) {
      DestReg = createResultReg(&AArch64::GPR64RegClass);
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
              TII.get(AArch64::LDRXui), DestReg)
        .addReg(SrcReg).addImm(0);
      SrcReg = DestReg;
    }

    UpdateValueMap(II, SrcReg);
    return true;
  }
  case Intrinsic::memcpy:
  case Intrinsic::memmove: {
    const auto *MTI = cast<MemTransferInst>(II);
    // Don't handle volatile.
    if (MTI->isVolatile())
      return false;

    // Disable inlining for memmove before calls to ComputeAddress.  Otherwise,
    // we would emit dead code because we don't currently handle memmoves.
    bool IsMemCpy = (II->getIntrinsicID() == Intrinsic::memcpy);
    if (isa<ConstantInt>(MTI->getLength()) && IsMemCpy) {
      // Small memcpy's are common enough that we want to do them without a call
      // if possible.
      uint64_t Len = cast<ConstantInt>(MTI->getLength())->getZExtValue();
      unsigned Alignment = MTI->getAlignment();
      if (IsMemCpySmall(Len, Alignment)) {
        Address Dest, Src;
        if (!ComputeAddress(MTI->getRawDest(), Dest) ||
            !ComputeAddress(MTI->getRawSource(), Src))
          return false;
        if (TryEmitSmallMemCpy(Dest, Src, Len, Alignment))
          return true;
      }
    }

    if (!MTI->getLength()->getType()->isIntegerTy(64))
      return false;

    if (MTI->getSourceAddressSpace() > 255 || MTI->getDestAddressSpace() > 255)
      // Fast instruction selection doesn't support the special
      // address spaces.
      return false;

    const char *IntrMemName = isa<MemCpyInst>(II) ? "memcpy" : "memmove";
    return LowerCallTo(II, IntrMemName, II->getNumArgOperands() - 2);
  }
  case Intrinsic::memset: {
    const MemSetInst *MSI = cast<MemSetInst>(II);
    // Don't handle volatile.
    if (MSI->isVolatile())
      return false;

    if (!MSI->getLength()->getType()->isIntegerTy(64))
      return false;

    if (MSI->getDestAddressSpace() > 255)
      // Fast instruction selection doesn't support the special
      // address spaces.
      return false;

    return LowerCallTo(II, "memset", II->getNumArgOperands() - 2);
  }
  case Intrinsic::trap: {
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::BRK))
        .addImm(1);
    return true;
  }
  case Intrinsic::sadd_with_overflow:
  case Intrinsic::uadd_with_overflow:
  case Intrinsic::ssub_with_overflow:
  case Intrinsic::usub_with_overflow:
  case Intrinsic::smul_with_overflow:
  case Intrinsic::umul_with_overflow: {
    // This implements the basic lowering of the xalu with overflow intrinsics.
    const Function *Callee = II->getCalledFunction();
    auto *Ty = cast<StructType>(Callee->getReturnType());
    Type *RetTy = Ty->getTypeAtIndex(0U);
    Type *CondTy = Ty->getTypeAtIndex(1);

    MVT VT;
    if (!isTypeLegal(RetTy, VT))
      return false;

    if (VT != MVT::i32 && VT != MVT::i64)
      return false;

    const Value *LHS = II->getArgOperand(0);
    const Value *RHS = II->getArgOperand(1);
    // Canonicalize immediate to the RHS.
    if (isa<ConstantInt>(LHS) && !isa<ConstantInt>(RHS) &&
        isCommutativeIntrinsic(II))
      std::swap(LHS, RHS);

    unsigned LHSReg = getRegForValue(LHS);
    if (!LHSReg)
      return false;
    bool LHSIsKill = hasTrivialKill(LHS);

    unsigned RHSReg = 0;
    bool RHSIsKill = false;
    bool UseImm = true;
    if (!isa<ConstantInt>(RHS)) {
      RHSReg = getRegForValue(RHS);
      if (!RHSReg)
        return false;
      RHSIsKill = hasTrivialKill(RHS);
      UseImm = false;
    }

    unsigned Opc = 0;
    unsigned MulReg = 0;
    AArch64CC::CondCode CC = AArch64CC::Invalid;
    bool Is64Bit = VT == MVT::i64;
    switch (II->getIntrinsicID()) {
    default: llvm_unreachable("Unexpected intrinsic!");
    case Intrinsic::sadd_with_overflow:
      if (UseImm)
        Opc = Is64Bit ? AArch64::ADDSXri : AArch64::ADDSWri;
      else
        Opc = Is64Bit ? AArch64::ADDSXrr : AArch64::ADDSWrr;
      CC = AArch64CC::VS;
      break;
    case Intrinsic::uadd_with_overflow:
      if (UseImm)
        Opc = Is64Bit ? AArch64::ADDSXri : AArch64::ADDSWri;
      else
        Opc = Is64Bit ? AArch64::ADDSXrr : AArch64::ADDSWrr;
      CC = AArch64CC::HS;
      break;
    case Intrinsic::ssub_with_overflow:
      if (UseImm)
        Opc = Is64Bit ? AArch64::SUBSXri : AArch64::SUBSWri;
      else
        Opc = Is64Bit ? AArch64::SUBSXrr : AArch64::SUBSWrr;
      CC = AArch64CC::VS;
      break;
    case Intrinsic::usub_with_overflow:
      if (UseImm)
        Opc = Is64Bit ? AArch64::SUBSXri : AArch64::SUBSWri;
      else
        Opc = Is64Bit ? AArch64::SUBSXrr : AArch64::SUBSWrr;
      CC = AArch64CC::LO;
      break;
    case Intrinsic::smul_with_overflow: {
      CC = AArch64CC::NE;
      if (UseImm) {
        RHSReg = getRegForValue(RHS);
        if (!RHSReg)
          return false;
        RHSIsKill = hasTrivialKill(RHS);
      }
      if (VT == MVT::i32) {
        MulReg = Emit_SMULL_rr(MVT::i64, LHSReg, LHSIsKill, RHSReg, RHSIsKill);
        unsigned ShiftReg = Emit_LSR_ri(MVT::i64, MulReg, false, 32);
        MulReg = FastEmitInst_extractsubreg(VT, MulReg, /*IsKill=*/true,
                                            AArch64::sub_32);
        ShiftReg = FastEmitInst_extractsubreg(VT, ShiftReg, /*IsKill=*/true,
                                              AArch64::sub_32);
        unsigned CmpReg = createResultReg(TLI.getRegClassFor(VT));
        BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
                TII.get(AArch64::SUBSWrs), CmpReg)
          .addReg(ShiftReg, getKillRegState(true))
          .addReg(MulReg, getKillRegState(false))
          .addImm(159); // 159 <-> asr #31
      } else {
        assert(VT == MVT::i64 && "Unexpected value type.");
        MulReg = Emit_MUL_rr(VT, LHSReg, LHSIsKill, RHSReg, RHSIsKill);
        unsigned SMULHReg = FastEmit_rr(VT, VT, ISD::MULHS, LHSReg, LHSIsKill,
                                        RHSReg, RHSIsKill);
        unsigned CmpReg = createResultReg(TLI.getRegClassFor(VT));
        BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
                TII.get(AArch64::SUBSXrs), CmpReg)
          .addReg(SMULHReg, getKillRegState(true))
          .addReg(MulReg, getKillRegState(false))
          .addImm(191); // 191 <-> asr #63
      }
      break;
    }
    case Intrinsic::umul_with_overflow: {
      CC = AArch64CC::NE;
      if (UseImm) {
        RHSReg = getRegForValue(RHS);
        if (!RHSReg)
          return false;
        RHSIsKill = hasTrivialKill(RHS);
      }
      if (VT == MVT::i32) {
        MulReg = Emit_UMULL_rr(MVT::i64, LHSReg, LHSIsKill, RHSReg, RHSIsKill);
        unsigned CmpReg = createResultReg(TLI.getRegClassFor(MVT::i64));
        BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
                TII.get(AArch64::SUBSXrs), CmpReg)
          .addReg(AArch64::XZR, getKillRegState(true))
          .addReg(MulReg, getKillRegState(false))
          .addImm(96); // 96 <-> lsr #32
        MulReg = FastEmitInst_extractsubreg(VT, MulReg, /*IsKill=*/true,
                                            AArch64::sub_32);
      } else {
        assert(VT == MVT::i64 && "Unexpected value type.");
        MulReg = Emit_MUL_rr(VT, LHSReg, LHSIsKill, RHSReg, RHSIsKill);
        unsigned UMULHReg = FastEmit_rr(VT, VT, ISD::MULHU, LHSReg, LHSIsKill,
                                        RHSReg, RHSIsKill);
        unsigned CmpReg = createResultReg(TLI.getRegClassFor(VT));
        BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
                TII.get(AArch64::SUBSXrr), CmpReg)
        .addReg(AArch64::XZR, getKillRegState(true))
        .addReg(UMULHReg, getKillRegState(false));
      }
      break;
    }
    }

    unsigned ResultReg = createResultReg(TLI.getRegClassFor(VT));
    if (Opc) {
      MachineInstrBuilder MIB;
      MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc),
                    ResultReg)
              .addReg(LHSReg, getKillRegState(LHSIsKill));
      if (UseImm)
        MIB.addImm(cast<ConstantInt>(RHS)->getZExtValue());
      else
        MIB.addReg(RHSReg, getKillRegState(RHSIsKill));
    }
    else
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
              TII.get(TargetOpcode::COPY), ResultReg)
        .addReg(MulReg);

    unsigned ResultReg2 = FuncInfo.CreateRegs(CondTy);
    assert((ResultReg+1) == ResultReg2 && "Nonconsecutive result registers.");
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::CSINCWr),
            ResultReg2)
      .addReg(AArch64::WZR, getKillRegState(true))
      .addReg(AArch64::WZR, getKillRegState(true))
      .addImm(getInvertedCondCode(CC));

    UpdateValueMap(II, ResultReg, 2);
    return true;
  }
  }
  return false;
}

bool AArch64FastISel::SelectRet(const Instruction *I) {
  const ReturnInst *Ret = cast<ReturnInst>(I);
  const Function &F = *I->getParent()->getParent();

  if (!FuncInfo.CanLowerReturn)
    return false;

  if (F.isVarArg())
    return false;

  // Build a list of return value registers.
  SmallVector<unsigned, 4> RetRegs;

  if (Ret->getNumOperands() > 0) {
    CallingConv::ID CC = F.getCallingConv();
    SmallVector<ISD::OutputArg, 4> Outs;
    GetReturnInfo(F.getReturnType(), F.getAttributes(), Outs, TLI);

    // Analyze operands of the call, assigning locations to each operand.
    SmallVector<CCValAssign, 16> ValLocs;
    CCState CCInfo(CC, F.isVarArg(), *FuncInfo.MF, TM, ValLocs,
                   I->getContext());
    CCAssignFn *RetCC = CC == CallingConv::WebKit_JS ? RetCC_AArch64_WebKit_JS
                                                     : RetCC_AArch64_AAPCS;
    CCInfo.AnalyzeReturn(Outs, RetCC);

    // Only handle a single return value for now.
    if (ValLocs.size() != 1)
      return false;

    CCValAssign &VA = ValLocs[0];
    const Value *RV = Ret->getOperand(0);

    // Don't bother handling odd stuff for now.
    if (VA.getLocInfo() != CCValAssign::Full)
      return false;
    // Only handle register returns for now.
    if (!VA.isRegLoc())
      return false;
    unsigned Reg = getRegForValue(RV);
    if (Reg == 0)
      return false;

    unsigned SrcReg = Reg + VA.getValNo();
    unsigned DestReg = VA.getLocReg();
    // Avoid a cross-class copy. This is very unlikely.
    if (!MRI.getRegClass(SrcReg)->contains(DestReg))
      return false;

    EVT RVEVT = TLI.getValueType(RV->getType());
    if (!RVEVT.isSimple())
      return false;

    // Vectors (of > 1 lane) in big endian need tricky handling.
    if (RVEVT.isVector() && RVEVT.getVectorNumElements() > 1)
      return false;

    MVT RVVT = RVEVT.getSimpleVT();
    if (RVVT == MVT::f128)
      return false;
    MVT DestVT = VA.getValVT();
    // Special handling for extended integers.
    if (RVVT != DestVT) {
      if (RVVT != MVT::i1 && RVVT != MVT::i8 && RVVT != MVT::i16)
        return false;

      if (!Outs[0].Flags.isZExt() && !Outs[0].Flags.isSExt())
        return false;

      bool isZExt = Outs[0].Flags.isZExt();
      SrcReg = EmitIntExt(RVVT, SrcReg, DestVT, isZExt);
      if (SrcReg == 0)
        return false;
    }

    // Make the copy.
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
            TII.get(TargetOpcode::COPY), DestReg).addReg(SrcReg);

    // Add register to return instruction.
    RetRegs.push_back(VA.getLocReg());
  }

  MachineInstrBuilder MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
                                    TII.get(AArch64::RET_ReallyLR));
  for (unsigned i = 0, e = RetRegs.size(); i != e; ++i)
    MIB.addReg(RetRegs[i], RegState::Implicit);
  return true;
}

bool AArch64FastISel::SelectTrunc(const Instruction *I) {
  Type *DestTy = I->getType();
  Value *Op = I->getOperand(0);
  Type *SrcTy = Op->getType();

  EVT SrcEVT = TLI.getValueType(SrcTy, true);
  EVT DestEVT = TLI.getValueType(DestTy, true);
  if (!SrcEVT.isSimple())
    return false;
  if (!DestEVT.isSimple())
    return false;

  MVT SrcVT = SrcEVT.getSimpleVT();
  MVT DestVT = DestEVT.getSimpleVT();

  if (SrcVT != MVT::i64 && SrcVT != MVT::i32 && SrcVT != MVT::i16 &&
      SrcVT != MVT::i8)
    return false;
  if (DestVT != MVT::i32 && DestVT != MVT::i16 && DestVT != MVT::i8 &&
      DestVT != MVT::i1)
    return false;

  unsigned SrcReg = getRegForValue(Op);
  if (!SrcReg)
    return false;

  // If we're truncating from i64 to a smaller non-legal type then generate an
  // AND.  Otherwise, we know the high bits are undefined and a truncate doesn't
  // generate any code.
  if (SrcVT == MVT::i64) {
    uint64_t Mask = 0;
    switch (DestVT.SimpleTy) {
    default:
      // Trunc i64 to i32 is handled by the target-independent fast-isel.
      return false;
    case MVT::i1:
      Mask = 0x1;
      break;
    case MVT::i8:
      Mask = 0xff;
      break;
    case MVT::i16:
      Mask = 0xffff;
      break;
    }
    // Issue an extract_subreg to get the lower 32-bits.
    unsigned Reg32 = FastEmitInst_extractsubreg(MVT::i32, SrcReg, /*Kill=*/true,
                                                AArch64::sub_32);
    MRI.constrainRegClass(Reg32, &AArch64::GPR32RegClass);
    // Create the AND instruction which performs the actual truncation.
    unsigned ANDReg = createResultReg(&AArch64::GPR32spRegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ANDWri),
            ANDReg)
        .addReg(Reg32)
        .addImm(AArch64_AM::encodeLogicalImmediate(Mask, 32));
    SrcReg = ANDReg;
  }

  UpdateValueMap(I, SrcReg);
  return true;
}

unsigned AArch64FastISel::Emiti1Ext(unsigned SrcReg, MVT DestVT, bool isZExt) {
  assert((DestVT == MVT::i8 || DestVT == MVT::i16 || DestVT == MVT::i32 ||
          DestVT == MVT::i64) &&
         "Unexpected value type.");
  // Handle i8 and i16 as i32.
  if (DestVT == MVT::i8 || DestVT == MVT::i16)
    DestVT = MVT::i32;

  if (isZExt) {
    MRI.constrainRegClass(SrcReg, &AArch64::GPR32RegClass);
    unsigned ResultReg = createResultReg(&AArch64::GPR32spRegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::ANDWri),
            ResultReg)
        .addReg(SrcReg)
        .addImm(AArch64_AM::encodeLogicalImmediate(1, 32));

    if (DestVT == MVT::i64) {
      // We're ZExt i1 to i64.  The ANDWri Wd, Ws, #1 implicitly clears the
      // upper 32 bits.  Emit a SUBREG_TO_REG to extend from Wd to Xd.
      unsigned Reg64 = MRI.createVirtualRegister(&AArch64::GPR64RegClass);
      BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
              TII.get(AArch64::SUBREG_TO_REG), Reg64)
          .addImm(0)
          .addReg(ResultReg)
          .addImm(AArch64::sub_32);
      ResultReg = Reg64;
    }
    return ResultReg;
  } else {
    if (DestVT == MVT::i64) {
      // FIXME: We're SExt i1 to i64.
      return 0;
    }
    unsigned ResultReg = createResultReg(&AArch64::GPR32RegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::SBFMWri),
            ResultReg)
        .addReg(SrcReg)
        .addImm(0)
        .addImm(0);
    return ResultReg;
  }
}

unsigned AArch64FastISel::Emit_MUL_rr(MVT RetVT, unsigned Op0, bool Op0IsKill,
                                      unsigned Op1, bool Op1IsKill) {
  unsigned Opc, ZReg;
  switch (RetVT.SimpleTy) {
  default: return 0;
  case MVT::i8:
  case MVT::i16:
  case MVT::i32:
    RetVT = MVT::i32;
    Opc = AArch64::MADDWrrr; ZReg = AArch64::WZR; break;
  case MVT::i64:
    Opc = AArch64::MADDXrrr; ZReg = AArch64::XZR; break;
  }

  // Create the base instruction, then add the operands.
  unsigned ResultReg = createResultReg(TLI.getRegClassFor(RetVT));
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), ResultReg)
    .addReg(Op0, getKillRegState(Op0IsKill))
    .addReg(Op1, getKillRegState(Op1IsKill))
    .addReg(ZReg, getKillRegState(true));

  return ResultReg;
}

unsigned AArch64FastISel::Emit_SMULL_rr(MVT RetVT, unsigned Op0, bool Op0IsKill,
                                        unsigned Op1, bool Op1IsKill) {
  if (RetVT != MVT::i64)
    return 0;

  // Create the base instruction, then add the operands.
  unsigned ResultReg = createResultReg(&AArch64::GPR64RegClass);
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::SMADDLrrr),
          ResultReg)
    .addReg(Op0, getKillRegState(Op0IsKill))
    .addReg(Op1, getKillRegState(Op1IsKill))
    .addReg(AArch64::XZR, getKillRegState(true));

  return ResultReg;
}

unsigned AArch64FastISel::Emit_UMULL_rr(MVT RetVT, unsigned Op0, bool Op0IsKill,
                                        unsigned Op1, bool Op1IsKill) {
  if (RetVT != MVT::i64)
    return 0;

  // Create the base instruction, then add the operands.
  unsigned ResultReg = createResultReg(&AArch64::GPR64RegClass);
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(AArch64::UMADDLrrr),
          ResultReg)
    .addReg(Op0, getKillRegState(Op0IsKill))
    .addReg(Op1, getKillRegState(Op1IsKill))
    .addReg(AArch64::XZR, getKillRegState(true));

  return ResultReg;
}

unsigned AArch64FastISel::Emit_LSL_ri(MVT RetVT, unsigned Op0, bool Op0IsKill,
                                      uint64_t Shift) {
  unsigned Opc, ImmR, ImmS;
  switch (RetVT.SimpleTy) {
  default: return 0;
  case MVT::i8:
  case MVT::i16:
  case MVT::i32:
    RetVT = MVT::i32;
    Opc = AArch64::UBFMWri; ImmR = -Shift % 32; ImmS = 31 - Shift; break;
  case MVT::i64:
    Opc = AArch64::UBFMXri; ImmR = -Shift % 64; ImmS = 63 - Shift; break;
  }

  return FastEmitInst_rii(Opc, TLI.getRegClassFor(RetVT), Op0, Op0IsKill, ImmR,
                          ImmS);
}

unsigned AArch64FastISel::Emit_LSR_ri(MVT RetVT, unsigned Op0, bool Op0IsKill,
                                      uint64_t Shift) {
  unsigned Opc, ImmS;
  switch (RetVT.SimpleTy) {
  default: return 0;
  case MVT::i8:
  case MVT::i16:
  case MVT::i32:
    RetVT = MVT::i32;
    Opc = AArch64::UBFMWri; ImmS = 31; break;
  case MVT::i64:
    Opc = AArch64::UBFMXri; ImmS = 63; break;
  }

  return FastEmitInst_rii(Opc, TLI.getRegClassFor(RetVT), Op0, Op0IsKill, Shift,
                          ImmS);
}

unsigned AArch64FastISel::Emit_ASR_ri(MVT RetVT, unsigned Op0, bool Op0IsKill,
                                      uint64_t Shift) {
  unsigned Opc, ImmS;
  switch (RetVT.SimpleTy) {
  default: return 0;
  case MVT::i8:
  case MVT::i16:
  case MVT::i32:
    RetVT = MVT::i32;
    Opc = AArch64::SBFMWri; ImmS = 31; break;
  case MVT::i64:
    Opc = AArch64::SBFMXri; ImmS = 63; break;
  }

  return FastEmitInst_rii(Opc, TLI.getRegClassFor(RetVT), Op0, Op0IsKill, Shift,
                          ImmS);
}

unsigned AArch64FastISel::EmitIntExt(MVT SrcVT, unsigned SrcReg, MVT DestVT,
                                     bool isZExt) {
  assert(DestVT != MVT::i1 && "ZeroExt/SignExt an i1?");

  // FastISel does not have plumbing to deal with extensions where the SrcVT or
  // DestVT are odd things, so test to make sure that they are both types we can
  // handle (i1/i8/i16/i32 for SrcVT and i8/i16/i32/i64 for DestVT), otherwise
  // bail out to SelectionDAG.
  if (((DestVT != MVT::i8) && (DestVT != MVT::i16) &&
       (DestVT != MVT::i32) && (DestVT != MVT::i64)) ||
      ((SrcVT !=  MVT::i1) && (SrcVT !=  MVT::i8) &&
       (SrcVT !=  MVT::i16) && (SrcVT !=  MVT::i32)))
    return 0;

  unsigned Opc;
  unsigned Imm = 0;

  switch (SrcVT.SimpleTy) {
  default:
    return 0;
  case MVT::i1:
    return Emiti1Ext(SrcReg, DestVT, isZExt);
  case MVT::i8:
    if (DestVT == MVT::i64)
      Opc = isZExt ? AArch64::UBFMXri : AArch64::SBFMXri;
    else
      Opc = isZExt ? AArch64::UBFMWri : AArch64::SBFMWri;
    Imm = 7;
    break;
  case MVT::i16:
    if (DestVT == MVT::i64)
      Opc = isZExt ? AArch64::UBFMXri : AArch64::SBFMXri;
    else
      Opc = isZExt ? AArch64::UBFMWri : AArch64::SBFMWri;
    Imm = 15;
    break;
  case MVT::i32:
    assert(DestVT == MVT::i64 && "IntExt i32 to i32?!?");
    Opc = isZExt ? AArch64::UBFMXri : AArch64::SBFMXri;
    Imm = 31;
    break;
  }

  // Handle i8 and i16 as i32.
  if (DestVT == MVT::i8 || DestVT == MVT::i16)
    DestVT = MVT::i32;
  else if (DestVT == MVT::i64) {
    unsigned Src64 = MRI.createVirtualRegister(&AArch64::GPR64RegClass);
    BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
            TII.get(AArch64::SUBREG_TO_REG), Src64)
        .addImm(0)
        .addReg(SrcReg)
        .addImm(AArch64::sub_32);
    SrcReg = Src64;
  }

  unsigned ResultReg = createResultReg(TLI.getRegClassFor(DestVT));
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc), ResultReg)
      .addReg(SrcReg)
      .addImm(0)
      .addImm(Imm);

  return ResultReg;
}

bool AArch64FastISel::SelectIntExt(const Instruction *I) {
  // On ARM, in general, integer casts don't involve legal types; this code
  // handles promotable integers.  The high bits for a type smaller than
  // the register size are assumed to be undefined.
  Type *DestTy = I->getType();
  Value *Src = I->getOperand(0);
  Type *SrcTy = Src->getType();

  bool isZExt = isa<ZExtInst>(I);
  unsigned SrcReg = getRegForValue(Src);
  if (!SrcReg)
    return false;

  EVT SrcEVT = TLI.getValueType(SrcTy, true);
  EVT DestEVT = TLI.getValueType(DestTy, true);
  if (!SrcEVT.isSimple())
    return false;
  if (!DestEVT.isSimple())
    return false;

  MVT SrcVT = SrcEVT.getSimpleVT();
  MVT DestVT = DestEVT.getSimpleVT();
  unsigned ResultReg = EmitIntExt(SrcVT, SrcReg, DestVT, isZExt);
  if (ResultReg == 0)
    return false;
  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::SelectRem(const Instruction *I, unsigned ISDOpcode) {
  EVT DestEVT = TLI.getValueType(I->getType(), true);
  if (!DestEVT.isSimple())
    return false;

  MVT DestVT = DestEVT.getSimpleVT();
  if (DestVT != MVT::i64 && DestVT != MVT::i32)
    return false;

  unsigned DivOpc;
  bool is64bit = (DestVT == MVT::i64);
  switch (ISDOpcode) {
  default:
    return false;
  case ISD::SREM:
    DivOpc = is64bit ? AArch64::SDIVXr : AArch64::SDIVWr;
    break;
  case ISD::UREM:
    DivOpc = is64bit ? AArch64::UDIVXr : AArch64::UDIVWr;
    break;
  }
  unsigned MSubOpc = is64bit ? AArch64::MSUBXrrr : AArch64::MSUBWrrr;
  unsigned Src0Reg = getRegForValue(I->getOperand(0));
  if (!Src0Reg)
    return false;

  unsigned Src1Reg = getRegForValue(I->getOperand(1));
  if (!Src1Reg)
    return false;

  unsigned QuotReg = createResultReg(TLI.getRegClassFor(DestVT));
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(DivOpc), QuotReg)
      .addReg(Src0Reg)
      .addReg(Src1Reg);
  // The remainder is computed as numerator - (quotient * denominator) using the
  // MSUB instruction.
  unsigned ResultReg = createResultReg(TLI.getRegClassFor(DestVT));
  BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(MSubOpc), ResultReg)
      .addReg(QuotReg)
      .addReg(Src1Reg)
      .addReg(Src0Reg);
  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::SelectMul(const Instruction *I) {
  EVT SrcEVT = TLI.getValueType(I->getOperand(0)->getType(), true);
  if (!SrcEVT.isSimple())
    return false;
  MVT SrcVT = SrcEVT.getSimpleVT();

  // Must be simple value type.  Don't handle vectors.
  if (SrcVT != MVT::i64 && SrcVT != MVT::i32 && SrcVT != MVT::i16 &&
      SrcVT != MVT::i8)
    return false;

  unsigned Src0Reg = getRegForValue(I->getOperand(0));
  if (!Src0Reg)
    return false;
  bool Src0IsKill = hasTrivialKill(I->getOperand(0));

  unsigned Src1Reg = getRegForValue(I->getOperand(1));
  if (!Src1Reg)
    return false;
  bool Src1IsKill = hasTrivialKill(I->getOperand(1));

  unsigned ResultReg =
    Emit_MUL_rr(SrcVT, Src0Reg, Src0IsKill, Src1Reg, Src1IsKill);

  if (!ResultReg)
    return false;

  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::SelectShift(const Instruction *I, bool IsLeftShift,
                                  bool IsArithmetic) {
  EVT RetEVT = TLI.getValueType(I->getType(), true);
  if (!RetEVT.isSimple())
    return false;
  MVT RetVT = RetEVT.getSimpleVT();

  if (!isa<ConstantInt>(I->getOperand(1)))
    return false;

  unsigned Op0Reg = getRegForValue(I->getOperand(0));
  if (!Op0Reg)
    return false;
  bool Op0IsKill = hasTrivialKill(I->getOperand(0));

  uint64_t ShiftVal = cast<ConstantInt>(I->getOperand(1))->getZExtValue();

  unsigned ResultReg;
  if (IsLeftShift)
    ResultReg = Emit_LSL_ri(RetVT, Op0Reg, Op0IsKill, ShiftVal);
  else {
    if (IsArithmetic)
      ResultReg = Emit_ASR_ri(RetVT, Op0Reg, Op0IsKill, ShiftVal);
    else
      ResultReg = Emit_LSR_ri(RetVT, Op0Reg, Op0IsKill, ShiftVal);
  }

  if (!ResultReg)
    return false;

  UpdateValueMap(I, ResultReg);
  return true;
}

bool AArch64FastISel::TargetSelectInstruction(const Instruction *I) {
  switch (I->getOpcode()) {
  default:
    break;
  case Instruction::Load:
    return SelectLoad(I);
  case Instruction::Store:
    return SelectStore(I);
  case Instruction::Br:
    return SelectBranch(I);
  case Instruction::IndirectBr:
    return SelectIndirectBr(I);
  case Instruction::FCmp:
  case Instruction::ICmp:
    return SelectCmp(I);
  case Instruction::Select:
    return SelectSelect(I);
  case Instruction::FPExt:
    return SelectFPExt(I);
  case Instruction::FPTrunc:
    return SelectFPTrunc(I);
  case Instruction::FPToSI:
    return SelectFPToInt(I, /*Signed=*/true);
  case Instruction::FPToUI:
    return SelectFPToInt(I, /*Signed=*/false);
  case Instruction::SIToFP:
    return SelectIntToFP(I, /*Signed=*/true);
  case Instruction::UIToFP:
    return SelectIntToFP(I, /*Signed=*/false);
  case Instruction::SRem:
    return SelectRem(I, ISD::SREM);
  case Instruction::URem:
    return SelectRem(I, ISD::UREM);
  case Instruction::Ret:
    return SelectRet(I);
  case Instruction::Trunc:
    return SelectTrunc(I);
  case Instruction::ZExt:
  case Instruction::SExt:
    return SelectIntExt(I);

  // FIXME: All of these should really be handled by the target-independent
  // selector -> improve FastISel tblgen.
  case Instruction::Mul:
    return SelectMul(I);
  case Instruction::Shl:
      return SelectShift(I, /*IsLeftShift=*/true, /*IsArithmetic=*/false);
  case Instruction::LShr:
    return SelectShift(I, /*IsLeftShift=*/false, /*IsArithmetic=*/false);
  case Instruction::AShr:
    return SelectShift(I, /*IsLeftShift=*/false, /*IsArithmetic=*/true);
  }
  return false;
  // Silence warnings.
  (void)&CC_AArch64_DarwinPCS_VarArg;
}

namespace llvm {
llvm::FastISel *AArch64::createFastISel(FunctionLoweringInfo &funcInfo,
                                        const TargetLibraryInfo *libInfo) {
  return new AArch64FastISel(funcInfo, libInfo);
}
}