blob: b9ac2657e1c5a2bab38102b8881b7bf233bef2bf [file] [log] [blame]
<
//===- 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/IR/IntrinsicsAArch64.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) override;
static const char *getName() { return DEBUG_TYPE; }
void setupMF(MachineFunction &MF, GISelKnownBits &KB,
CodeGenCoverage &CoverageInfo) override {
InstructionSelector::setupMF(MF, KB, CoverageInfo);
// hasFnAttribute() is expensive to call on every BRCOND selection, so
// cache it here for each run of the selector.
ProduceNonFlagSettingCondBr =
!MF.getFunction().hasFnAttribute(Attribute::SpeculativeLoadHardening);
}
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;
/// 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;
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;
bool selectTLSGlobalValue(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;
/// Returns a \p ComplexRendererFns which contains a base, offset, and whether
/// or not a shift + extend should be folded into an addressing mode. Returns
/// None when this is not profitable or possible.
ComplexRendererFns
selectExtendedSHL(MachineOperand &Root, MachineOperand &Base,
MachineOperand &Offset, unsigned SizeInBytes,
bool WantsExt) const;
ComplexRendererFns selectAddrModeRegisterOffset(MachineOperand &Root) const;
ComplexRendererFns selectAddrModeXRO(MachineOperand &Root,
unsigned SizeInBytes) const;
template <int Width>
ComplexRendererFns selectAddrModeXRO(MachineOperand &Root) const {
return selectAddrModeXRO(Root, Width / 8);
}
ComplexRendererFns selectAddrModeWRO(MachineOperand &Root,
unsigned SizeInBytes) const;
template <int Width>
ComplexRendererFns selectAddrModeWRO(MachineOperand &Root) const {
return selectAddrModeWRO(Root, Width / 8);
}
ComplexRendererFns selectShiftedRegister(MachineOperand &Root) const;
ComplexRendererFns selectArithShiftedRegister(MachineOperand &Root) const {
return selectShiftedRegister(Root);
}
ComplexRendererFns selectLogicalShiftedRegister(MachineOperand &Root) const {
// TODO: selectShiftedRegister should allow for rotates on logical shifts.
// For now, make them the same. The only difference between the two is that
// logical shifts are allowed to fold in rotates. Otherwise, these are
// functionally the same.
return selectShiftedRegister(Root);
}
/// Given an extend instruction, determine the correct shift-extend type for
/// that instruction.
///
/// If the instruction is going to be used in a load or store, pass
/// \p IsLoadStore = true.
AArch64_AM::ShiftExtendType
getExtendTypeForInst(MachineInstr &MI, MachineRegisterInfo &MRI,
bool IsLoadStore = false) const;
/// Instructions that accept extend modifiers like UXTW expect the register
/// being extended to be a GPR32. Narrow ExtReg to a 32-bit register using a
/// subregister copy if necessary. Return either ExtReg, or the result of the
/// new copy.
Register narrowExtendRegIfNeeded(Register ExtReg,
MachineIRBuilder &MIB) const;
ComplexRendererFns selectArithExtendedRegister(MachineOperand &Root) const;
void renderTruncImm(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx = -1) const;
void renderLogicalImm32(MachineInstrBuilder &MIB, const MachineInstr &I,
int OpIdx = -1) const;
void renderLogicalImm64(MachineInstrBuilder &MIB, const MachineInstr &I,
int OpIdx = -1) 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;
/// Return true if \p MI is a load or store of \p NumBytes bytes.
bool isLoadStoreOfNumBytes(const MachineInstr &MI, unsigned NumBytes) const;
/// Returns true if \p MI is guaranteed to have the high-half of a 64-bit
/// register zeroed out. In other words, the result of MI has been explicitly
/// zero extended.
bool isDef32(const MachineInstr &MI) const;
const AArch64TargetMachine &TM;
const AArch64Subtarget &STI;
const AArch64InstrInfo &TII;
const AArch64RegisterInfo &TRI;
const AArch64RegisterBankInfo &RBI;
bool ProduceNonFlagSettingCondBr = false;
#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::FPR32RegClass)
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_PTR_ADD:
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 Register DstReg = I.getOperand(0).getReg();
const Register 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, Register 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) {
Register DstReg = I.getOperand(0).getReg();
Register 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) {
Register DstReg = I.getOperand(0).getReg();
Register 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;
}
unsigned SrcSize = TRI.getRegSizeInBits(*SrcRC);
unsigned DstSize = TRI.getRegSizeInBits(*DstRC);
// If we're doing a cross-bank copy on different-sized registers, we need
// to do a bit more work.
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();
}
// Is this a cross-bank copy?
if (DstRegBank.getID() != SrcRegBank.getID()) {
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.
Register 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;
}
/// Returns the element immediate value of a vector shift operand if found.
/// This needs to detect a splat-like operation, e.g. a G_BUILD_VECTOR.
static Optional<int64_t> getVectorShiftImm(Register Reg,
MachineRegisterInfo &MRI) {
assert(MRI.getType(Reg).isVector() && "Expected a *vector* shift operand");
MachineInstr *OpMI = MRI.getVRegDef(Reg);
assert(OpMI && "Expected to find a vreg def for vector shift operand");
if (OpMI->getOpcode() != TargetOpcode::G_BUILD_VECTOR)
return None;
// Check all operands are identical immediates.
int64_t ImmVal = 0;
for (unsigned Idx = 1; Idx < OpMI->getNumOperands(); ++Idx) {
auto VRegAndVal = getConstantVRegValWithLookThrough(OpMI->getOperand(Idx).getReg(), MRI);
if (!VRegAndVal)
return None;
if (Idx == 1)
ImmVal = VRegAndVal->Value;
if (ImmVal != VRegAndVal->Value)
return None;
}
return ImmVal;
}
/// Matches and returns the shift immediate value for a SHL instruction given
/// a shift operand.
static Optional<int64_t> getVectorSHLImm(LLT SrcTy, Register Reg, MachineRegisterInfo &MRI) {
Optional<int64_t> ShiftImm = getVectorShiftImm(Reg, MRI);
if (!ShiftImm)
return None;
// Check the immediate is in range for a SHL.
int64_t Imm = *ShiftImm;
if (Imm < 0)
return None;
switch (SrcTy.getElementType().getSizeInBits()) {
default:
LLVM_DEBUG(dbgs() << "Unhandled element type for vector shift");
return None;
case 8:
if (Imm > 7)
return None;
break;
case 16:
if (Imm > 15)
return None;
break;
case 32:
if (Imm > 31)
return None;
break;
case 64:
if (Imm > 63)
return None;
break;
}
return Imm;
}
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;
// Check if we have a vector of constants on RHS that we can select as the
// immediate form.
Optional<int64_t> ImmVal = getVectorSHLImm(Ty, Src2Reg, MRI);
unsigned Opc = 0;
if (Ty == LLT::vector(2, 64)) {
Opc = ImmVal ? AArch64::SHLv2i64_shift : AArch64::USHLv2i64;
} else if (Ty == LLT::vector(4, 32)) {
Opc = ImmVal ? AArch64::SHLv4i32_shift : AArch64::USHLv4i32;
} else if (Ty == LLT::vector(2, 32)) {
Opc = ImmVal ? AArch64::SHLv2i32_shift : AArch64::USHLv2i32;
} else {
LLVM_DEBUG(dbgs() << "Unhandled G_SHL type");
return false;
}
MachineIRBuilder MIB(I);
auto Shl = MIB.buildInstr(Opc, {DstReg}, {Src1Reg});
if (ImmVal)
Shl.addImm(*ImmVal);
else
Shl.addUse(Src2Reg);
constrainSelectedInstRegOperands(*Shl, 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(2, 64)) {
Opc = AArch64::SSHLv2i64;
NegOpc = AArch64::NEGv2i64;
RC = &AArch64::FPR128RegClass;
} else 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.
Register SrcReg = I.getOperand(1).getReg();
Register 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::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_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) {
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())
return selectTLSGlobalValue(I, MRI);
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.isAtomic()) {
// For now we just support s8 acquire loads to be able to compile stack
// protector code.
if (MemOp.getOrdering() == AtomicOrdering::Acquire &&
MemOp.getSize() == 1) {
I.setDesc(TII.get(AArch64::LDARB));
return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
}
LLVM_DEBUG(dbgs() << "Atomic load/store not fully 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_PTR_ADD) {
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)) {
Register 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_PTR_ADD: {
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();
if (DstTy.isVector())
return false; // Should be handled by imported patterns.
assert((*RBI.getRegBank(DefReg, MRI, TRI)).getID() ==
AArch64::GPRRegBankID &&
"Unexpected ext regbank");
MachineIRBuilder MIB(I);
MachineInstr *ExtI;
// 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);