blob: 830bf77b4e5d05c48aad88fb4c49914f61b5f886 [file] [log] [blame]
//===- AArch64InstrInfo.cpp - AArch64 Instruction Information -------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file contains the AArch64 implementation of the TargetInstrInfo class.
//
//===----------------------------------------------------------------------===//
#include "AArch64ExpandImm.h"
#include "AArch64InstrInfo.h"
#include "AArch64FrameLowering.h"
#include "AArch64MachineFunctionInfo.h"
#include "AArch64Subtarget.h"
#include "MCTargetDesc/AArch64AddressingModes.h"
#include "Utils/AArch64BaseInfo.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineCombinerPattern.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineMemOperand.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/RegisterScavenging.h"
#include "llvm/CodeGen/StackMaps.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/IR/DebugInfoMetadata.h"
#include "llvm/IR/DebugLoc.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCInstBuilder.h"
#include "llvm/MC/MCInstrDesc.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
#include <cassert>
#include <cstdint>
#include <iterator>
#include <utility>
using namespace llvm;
#define GET_INSTRINFO_CTOR_DTOR
#include "AArch64GenInstrInfo.inc"
static cl::opt<unsigned> TBZDisplacementBits(
"aarch64-tbz-offset-bits", cl::Hidden, cl::init(14),
cl::desc("Restrict range of TB[N]Z instructions (DEBUG)"));
static cl::opt<unsigned> CBZDisplacementBits(
"aarch64-cbz-offset-bits", cl::Hidden, cl::init(19),
cl::desc("Restrict range of CB[N]Z instructions (DEBUG)"));
static cl::opt<unsigned>
BCCDisplacementBits("aarch64-bcc-offset-bits", cl::Hidden, cl::init(19),
cl::desc("Restrict range of Bcc instructions (DEBUG)"));
static cl::opt<unsigned>
BDisplacementBits("aarch64-b-offset-bits", cl::Hidden, cl::init(26),
cl::desc("Restrict range of B instructions (DEBUG)"));
AArch64InstrInfo::AArch64InstrInfo(const AArch64Subtarget &STI)
: AArch64GenInstrInfo(AArch64::ADJCALLSTACKDOWN, AArch64::ADJCALLSTACKUP,
AArch64::CATCHRET),
RI(STI.getTargetTriple()), Subtarget(STI) {}
/// GetInstSize - Return the number of bytes of code the specified
/// instruction may be. This returns the maximum number of bytes.
unsigned AArch64InstrInfo::getInstSizeInBytes(const MachineInstr &MI) const {
const MachineBasicBlock &MBB = *MI.getParent();
const MachineFunction *MF = MBB.getParent();
const Function &F = MF->getFunction();
const MCAsmInfo *MAI = MF->getTarget().getMCAsmInfo();
{
auto Op = MI.getOpcode();
if (Op == AArch64::INLINEASM || Op == AArch64::INLINEASM_BR)
return getInlineAsmLength(MI.getOperand(0).getSymbolName(), *MAI);
}
// Meta-instructions emit no code.
if (MI.isMetaInstruction())
return 0;
// FIXME: We currently only handle pseudoinstructions that don't get expanded
// before the assembly printer.
unsigned NumBytes = 0;
const MCInstrDesc &Desc = MI.getDesc();
// Size should be preferably set in
// llvm/lib/Target/AArch64/AArch64InstrInfo.td (default case).
// Specific cases handle instructions of variable sizes
switch (Desc.getOpcode()) {
default:
if (Desc.getSize())
return Desc.getSize();
// Anything not explicitly designated otherwise (i.e. pseudo-instructions
// with fixed constant size but not specified in .td file) is a normal
// 4-byte insn.
NumBytes = 4;
break;
case TargetOpcode::STACKMAP:
// The upper bound for a stackmap intrinsic is the full length of its shadow
NumBytes = StackMapOpers(&MI).getNumPatchBytes();
assert(NumBytes % 4 == 0 && "Invalid number of NOP bytes requested!");
break;
case TargetOpcode::PATCHPOINT:
// The size of the patchpoint intrinsic is the number of bytes requested
NumBytes = PatchPointOpers(&MI).getNumPatchBytes();
assert(NumBytes % 4 == 0 && "Invalid number of NOP bytes requested!");
break;
case TargetOpcode::STATEPOINT:
NumBytes = StatepointOpers(&MI).getNumPatchBytes();
assert(NumBytes % 4 == 0 && "Invalid number of NOP bytes requested!");
// No patch bytes means a normal call inst is emitted
if (NumBytes == 0)
NumBytes = 4;
break;
case TargetOpcode::PATCHABLE_FUNCTION_ENTER:
// If `patchable-function-entry` is set, PATCHABLE_FUNCTION_ENTER
// instructions are expanded to the specified number of NOPs. Otherwise,
// they are expanded to 36-byte XRay sleds.
NumBytes =
F.getFnAttributeAsParsedInteger("patchable-function-entry", 9) * 4;
break;
case TargetOpcode::PATCHABLE_FUNCTION_EXIT:
case TargetOpcode::PATCHABLE_TYPED_EVENT_CALL:
// An XRay sled can be 4 bytes of alignment plus a 32-byte block.
NumBytes = 36;
break;
case TargetOpcode::PATCHABLE_EVENT_CALL:
// EVENT_CALL XRay sleds are exactly 6 instructions long (no alignment).
NumBytes = 24;
break;
case AArch64::SPACE:
NumBytes = MI.getOperand(1).getImm();
break;
case TargetOpcode::BUNDLE:
NumBytes = getInstBundleLength(MI);
break;
}
return NumBytes;
}
unsigned AArch64InstrInfo::getInstBundleLength(const MachineInstr &MI) const {
unsigned Size = 0;
MachineBasicBlock::const_instr_iterator I = MI.getIterator();
MachineBasicBlock::const_instr_iterator E = MI.getParent()->instr_end();
while (++I != E && I->isInsideBundle()) {
assert(!I->isBundle() && "No nested bundle!");
Size += getInstSizeInBytes(*I);
}
return Size;
}
static void parseCondBranch(MachineInstr *LastInst, MachineBasicBlock *&Target,
SmallVectorImpl<MachineOperand> &Cond) {
// Block ends with fall-through condbranch.
switch (LastInst->getOpcode()) {
default:
llvm_unreachable("Unknown branch instruction?");
case AArch64::Bcc:
Target = LastInst->getOperand(1).getMBB();
Cond.push_back(LastInst->getOperand(0));
break;
case AArch64::CBZW:
case AArch64::CBZX:
case AArch64::CBNZW:
case AArch64::CBNZX:
Target = LastInst->getOperand(1).getMBB();
Cond.push_back(MachineOperand::CreateImm(-1));
Cond.push_back(MachineOperand::CreateImm(LastInst->getOpcode()));
Cond.push_back(LastInst->getOperand(0));
break;
case AArch64::TBZW:
case AArch64::TBZX:
case AArch64::TBNZW:
case AArch64::TBNZX:
Target = LastInst->getOperand(2).getMBB();
Cond.push_back(MachineOperand::CreateImm(-1));
Cond.push_back(MachineOperand::CreateImm(LastInst->getOpcode()));
Cond.push_back(LastInst->getOperand(0));
Cond.push_back(LastInst->getOperand(1));
}
}
static unsigned getBranchDisplacementBits(unsigned Opc) {
switch (Opc) {
default:
llvm_unreachable("unexpected opcode!");
case AArch64::B:
return BDisplacementBits;
case AArch64::TBNZW:
case AArch64::TBZW:
case AArch64::TBNZX:
case AArch64::TBZX:
return TBZDisplacementBits;
case AArch64::CBNZW:
case AArch64::CBZW:
case AArch64::CBNZX:
case AArch64::CBZX:
return CBZDisplacementBits;
case AArch64::Bcc:
return BCCDisplacementBits;
}
}
bool AArch64InstrInfo::isBranchOffsetInRange(unsigned BranchOp,
int64_t BrOffset) const {
unsigned Bits = getBranchDisplacementBits(BranchOp);
assert(Bits >= 3 && "max branch displacement must be enough to jump"
"over conditional branch expansion");
return isIntN(Bits, BrOffset / 4);
}
MachineBasicBlock *
AArch64InstrInfo::getBranchDestBlock(const MachineInstr &MI) const {
switch (MI.getOpcode()) {
default:
llvm_unreachable("unexpected opcode!");
case AArch64::B:
return MI.getOperand(0).getMBB();
case AArch64::TBZW:
case AArch64::TBNZW:
case AArch64::TBZX:
case AArch64::TBNZX:
return MI.getOperand(2).getMBB();
case AArch64::CBZW:
case AArch64::CBNZW:
case AArch64::CBZX:
case AArch64::CBNZX:
case AArch64::Bcc:
return MI.getOperand(1).getMBB();
}
}
void AArch64InstrInfo::insertIndirectBranch(MachineBasicBlock &MBB,
MachineBasicBlock &NewDestBB,
MachineBasicBlock &RestoreBB,
const DebugLoc &DL,
int64_t BrOffset,
RegScavenger *RS) const {
assert(RS && "RegScavenger required for long branching");
assert(MBB.empty() &&
"new block should be inserted for expanding unconditional branch");
assert(MBB.pred_size() == 1);
assert(RestoreBB.empty() &&
"restore block should be inserted for restoring clobbered registers");
auto buildIndirectBranch = [&](Register Reg, MachineBasicBlock &DestBB) {
// Offsets outside of the signed 33-bit range are not supported for ADRP +
// ADD.
if (!isInt<33>(BrOffset))
report_fatal_error(
"Branch offsets outside of the signed 33-bit range not supported");
BuildMI(MBB, MBB.end(), DL, get(AArch64::ADRP), Reg)
.addSym(DestBB.getSymbol(), AArch64II::MO_PAGE);
BuildMI(MBB, MBB.end(), DL, get(AArch64::ADDXri), Reg)
.addReg(Reg)
.addSym(DestBB.getSymbol(), AArch64II::MO_PAGEOFF | AArch64II::MO_NC)
.addImm(0);
BuildMI(MBB, MBB.end(), DL, get(AArch64::BR)).addReg(Reg);
};
RS->enterBasicBlockEnd(MBB);
// If X16 is unused, we can rely on the linker to insert a range extension
// thunk if NewDestBB is out of range of a single B instruction.
constexpr Register Reg = AArch64::X16;
if (!RS->isRegUsed(Reg)) {
insertUnconditionalBranch(MBB, &NewDestBB, DL);
RS->setRegUsed(Reg);
return;
}
// If there's a free register and it's worth inflating the code size,
// manually insert the indirect branch.
Register Scavenged = RS->FindUnusedReg(&AArch64::GPR64RegClass);
if (Scavenged != AArch64::NoRegister &&
MBB.getSectionID() == MBBSectionID::ColdSectionID) {
buildIndirectBranch(Scavenged, NewDestBB);
RS->setRegUsed(Scavenged);
return;
}
// Note: Spilling X16 briefly moves the stack pointer, making it incompatible
// with red zones.
AArch64FunctionInfo *AFI = MBB.getParent()->getInfo<AArch64FunctionInfo>();
if (!AFI || AFI->hasRedZone().value_or(true))
report_fatal_error(
"Unable to insert indirect branch inside function that has red zone");
// Otherwise, spill X16 and defer range extension to the linker.
BuildMI(MBB, MBB.end(), DL, get(AArch64::STRXpre))
.addReg(AArch64::SP, RegState::Define)
.addReg(Reg)
.addReg(AArch64::SP)
.addImm(-16);
BuildMI(MBB, MBB.end(), DL, get(AArch64::B)).addMBB(&RestoreBB);
BuildMI(RestoreBB, RestoreBB.end(), DL, get(AArch64::LDRXpost))
.addReg(AArch64::SP, RegState::Define)
.addReg(Reg, RegState::Define)
.addReg(AArch64::SP)
.addImm(16);
}
// Branch analysis.
bool AArch64InstrInfo::analyzeBranch(MachineBasicBlock &MBB,
MachineBasicBlock *&TBB,
MachineBasicBlock *&FBB,
SmallVectorImpl<MachineOperand> &Cond,
bool AllowModify) const {
// If the block has no terminators, it just falls into the block after it.
MachineBasicBlock::iterator I = MBB.getLastNonDebugInstr();
if (I == MBB.end())
return false;
// Skip over SpeculationBarrierEndBB terminators
if (I->getOpcode() == AArch64::SpeculationBarrierISBDSBEndBB ||
I->getOpcode() == AArch64::SpeculationBarrierSBEndBB) {
--I;
}
if (!isUnpredicatedTerminator(*I))
return false;
// Get the last instruction in the block.
MachineInstr *LastInst = &*I;
// If there is only one terminator instruction, process it.
unsigned LastOpc = LastInst->getOpcode();
if (I == MBB.begin() || !isUnpredicatedTerminator(*--I)) {
if (isUncondBranchOpcode(LastOpc)) {
TBB = LastInst->getOperand(0).getMBB();
return false;
}
if (isCondBranchOpcode(LastOpc)) {
// Block ends with fall-through condbranch.
parseCondBranch(LastInst, TBB, Cond);
return false;
}
return true; // Can't handle indirect branch.
}
// Get the instruction before it if it is a terminator.
MachineInstr *SecondLastInst = &*I;
unsigned SecondLastOpc = SecondLastInst->getOpcode();
// If AllowModify is true and the block ends with two or more unconditional
// branches, delete all but the first unconditional branch.
if (AllowModify && isUncondBranchOpcode(LastOpc)) {
while (isUncondBranchOpcode(SecondLastOpc)) {
LastInst->eraseFromParent();
LastInst = SecondLastInst;
LastOpc = LastInst->getOpcode();
if (I == MBB.begin() || !isUnpredicatedTerminator(*--I)) {
// Return now the only terminator is an unconditional branch.
TBB = LastInst->getOperand(0).getMBB();
return false;
}
SecondLastInst = &*I;
SecondLastOpc = SecondLastInst->getOpcode();
}
}
// If we're allowed to modify and the block ends in a unconditional branch
// which could simply fallthrough, remove the branch. (Note: This case only
// matters when we can't understand the whole sequence, otherwise it's also
// handled by BranchFolding.cpp.)
if (AllowModify && isUncondBranchOpcode(LastOpc) &&
MBB.isLayoutSuccessor(getBranchDestBlock(*LastInst))) {
LastInst->eraseFromParent();
LastInst = SecondLastInst;
LastOpc = LastInst->getOpcode();
if (I == MBB.begin() || !isUnpredicatedTerminator(*--I)) {
assert(!isUncondBranchOpcode(LastOpc) &&
"unreachable unconditional branches removed above");
if (isCondBranchOpcode(LastOpc)) {
// Block ends with fall-through condbranch.
parseCondBranch(LastInst, TBB, Cond);
return false;
}
return true; // Can't handle indirect branch.
}
SecondLastInst = &*I;
SecondLastOpc = SecondLastInst->getOpcode();
}
// If there are three terminators, we don't know what sort of block this is.
if (SecondLastInst && I != MBB.begin() && isUnpredicatedTerminator(*--I))
return true;
// If the block ends with a B and a Bcc, handle it.
if (isCondBranchOpcode(SecondLastOpc) && isUncondBranchOpcode(LastOpc)) {
parseCondBranch(SecondLastInst, TBB, Cond);
FBB = LastInst->getOperand(0).getMBB();
return false;
}
// If the block ends with two unconditional branches, handle it. The second
// one is not executed, so remove it.
if (isUncondBranchOpcode(SecondLastOpc) && isUncondBranchOpcode(LastOpc)) {
TBB = SecondLastInst->getOperand(0).getMBB();
I = LastInst;
if (AllowModify)
I->eraseFromParent();
return false;
}
// ...likewise if it ends with an indirect branch followed by an unconditional
// branch.
if (isIndirectBranchOpcode(SecondLastOpc) && isUncondBranchOpcode(LastOpc)) {
I = LastInst;
if (AllowModify)
I->eraseFromParent();
return true;
}
// Otherwise, can't handle this.
return true;
}
bool AArch64InstrInfo::analyzeBranchPredicate(MachineBasicBlock &MBB,
MachineBranchPredicate &MBP,
bool AllowModify) const {
// For the moment, handle only a block which ends with a cb(n)zx followed by
// a fallthrough. Why this? Because it is a common form.
// TODO: Should we handle b.cc?
MachineBasicBlock::iterator I = MBB.getLastNonDebugInstr();
if (I == MBB.end())
return true;
// Skip over SpeculationBarrierEndBB terminators
if (I->getOpcode() == AArch64::SpeculationBarrierISBDSBEndBB ||
I->getOpcode() == AArch64::SpeculationBarrierSBEndBB) {
--I;
}
if (!isUnpredicatedTerminator(*I))
return true;
// Get the last instruction in the block.
MachineInstr *LastInst = &*I;
unsigned LastOpc = LastInst->getOpcode();
if (!isCondBranchOpcode(LastOpc))
return true;
switch (LastOpc) {
default:
return true;
case AArch64::CBZW:
case AArch64::CBZX:
case AArch64::CBNZW:
case AArch64::CBNZX:
break;
};
MBP.TrueDest = LastInst->getOperand(1).getMBB();
assert(MBP.TrueDest && "expected!");
MBP.FalseDest = MBB.getNextNode();
MBP.ConditionDef = nullptr;
MBP.SingleUseCondition = false;
MBP.LHS = LastInst->getOperand(0);
MBP.RHS = MachineOperand::CreateImm(0);
MBP.Predicate = LastOpc == AArch64::CBNZX ? MachineBranchPredicate::PRED_NE
: MachineBranchPredicate::PRED_EQ;
return false;
}
bool AArch64InstrInfo::reverseBranchCondition(
SmallVectorImpl<MachineOperand> &Cond) const {
if (Cond[0].getImm() != -1) {
// Regular Bcc
AArch64CC::CondCode CC = (AArch64CC::CondCode)(int)Cond[0].getImm();
Cond[0].setImm(AArch64CC::getInvertedCondCode(CC));
} else {
// Folded compare-and-branch
switch (Cond[1].getImm()) {
default:
llvm_unreachable("Unknown conditional branch!");
case AArch64::CBZW:
Cond[1].setImm(AArch64::CBNZW);
break;
case AArch64::CBNZW:
Cond[1].setImm(AArch64::CBZW);
break;
case AArch64::CBZX:
Cond[1].setImm(AArch64::CBNZX);
break;
case AArch64::CBNZX:
Cond[1].setImm(AArch64::CBZX);
break;
case AArch64::TBZW:
Cond[1].setImm(AArch64::TBNZW);
break;
case AArch64::TBNZW:
Cond[1].setImm(AArch64::TBZW);
break;
case AArch64::TBZX:
Cond[1].setImm(AArch64::TBNZX);
break;
case AArch64::TBNZX:
Cond[1].setImm(AArch64::TBZX);
break;
}
}
return false;
}
unsigned AArch64InstrInfo::removeBranch(MachineBasicBlock &MBB,
int *BytesRemoved) const {
MachineBasicBlock::iterator I = MBB.getLastNonDebugInstr();
if (I == MBB.end())
return 0;
if (!isUncondBranchOpcode(I->getOpcode()) &&
!isCondBranchOpcode(I->getOpcode()))
return 0;
// Remove the branch.
I->eraseFromParent();
I = MBB.end();
if (I == MBB.begin()) {
if (BytesRemoved)
*BytesRemoved = 4;
return 1;
}
--I;
if (!isCondBranchOpcode(I->getOpcode())) {
if (BytesRemoved)
*BytesRemoved = 4;
return 1;
}
// Remove the branch.
I->eraseFromParent();
if (BytesRemoved)
*BytesRemoved = 8;
return 2;
}
void AArch64InstrInfo::instantiateCondBranch(
MachineBasicBlock &MBB, const DebugLoc &DL, MachineBasicBlock *TBB,
ArrayRef<MachineOperand> Cond) const {
if (Cond[0].getImm() != -1) {
// Regular Bcc
BuildMI(&MBB, DL, get(AArch64::Bcc)).addImm(Cond[0].getImm()).addMBB(TBB);
} else {
// Folded compare-and-branch
// Note that we use addOperand instead of addReg to keep the flags.
const MachineInstrBuilder MIB =
BuildMI(&MBB, DL, get(Cond[1].getImm())).add(Cond[2]);
if (Cond.size() > 3)
MIB.addImm(Cond[3].getImm());
MIB.addMBB(TBB);
}
}
unsigned AArch64InstrInfo::insertBranch(
MachineBasicBlock &MBB, MachineBasicBlock *TBB, MachineBasicBlock *FBB,
ArrayRef<MachineOperand> Cond, const DebugLoc &DL, int *BytesAdded) const {
// Shouldn't be a fall through.
assert(TBB && "insertBranch must not be told to insert a fallthrough");
if (!FBB) {
if (Cond.empty()) // Unconditional branch?
BuildMI(&MBB, DL, get(AArch64::B)).addMBB(TBB);
else
instantiateCondBranch(MBB, DL, TBB, Cond);
if (BytesAdded)
*BytesAdded = 4;
return 1;
}
// Two-way conditional branch.
instantiateCondBranch(MBB, DL, TBB, Cond);
BuildMI(&MBB, DL, get(AArch64::B)).addMBB(FBB);
if (BytesAdded)
*BytesAdded = 8;
return 2;
}
// Find the original register that VReg is copied from.
static unsigned removeCopies(const MachineRegisterInfo &MRI, unsigned VReg) {
while (Register::isVirtualRegister(VReg)) {
const MachineInstr *DefMI = MRI.getVRegDef(VReg);
if (!DefMI->isFullCopy())
return VReg;
VReg = DefMI->getOperand(1).getReg();
}
return VReg;
}
// Determine if VReg is defined by an instruction that can be folded into a
// csel instruction. If so, return the folded opcode, and the replacement
// register.
static unsigned canFoldIntoCSel(const MachineRegisterInfo &MRI, unsigned VReg,
unsigned *NewVReg = nullptr) {
VReg = removeCopies(MRI, VReg);
if (!Register::isVirtualRegister(VReg))
return 0;
bool Is64Bit = AArch64::GPR64allRegClass.hasSubClassEq(MRI.getRegClass(VReg));
const MachineInstr *DefMI = MRI.getVRegDef(VReg);
unsigned Opc = 0;
unsigned SrcOpNum = 0;
switch (DefMI->getOpcode()) {
case AArch64::ADDSXri:
case AArch64::ADDSWri:
// if NZCV is used, do not fold.
if (DefMI->findRegisterDefOperandIdx(AArch64::NZCV, true) == -1)
return 0;
// fall-through to ADDXri and ADDWri.
[[fallthrough]];
case AArch64::ADDXri:
case AArch64::ADDWri:
// add x, 1 -> csinc.
if (!DefMI->getOperand(2).isImm() || DefMI->getOperand(2).getImm() != 1 ||
DefMI->getOperand(3).getImm() != 0)
return 0;
SrcOpNum = 1;
Opc = Is64Bit ? AArch64::CSINCXr : AArch64::CSINCWr;
break;
case AArch64::ORNXrr:
case AArch64::ORNWrr: {
// not x -> csinv, represented as orn dst, xzr, src.
unsigned ZReg = removeCopies(MRI, DefMI->getOperand(1).getReg());
if (ZReg != AArch64::XZR && ZReg != AArch64::WZR)
return 0;
SrcOpNum = 2;
Opc = Is64Bit ? AArch64::CSINVXr : AArch64::CSINVWr;
break;
}
case AArch64::SUBSXrr:
case AArch64::SUBSWrr:
// if NZCV is used, do not fold.
if (DefMI->findRegisterDefOperandIdx(AArch64::NZCV, true) == -1)
return 0;
// fall-through to SUBXrr and SUBWrr.
[[fallthrough]];
case AArch64::SUBXrr:
case AArch64::SUBWrr: {
// neg x -> csneg, represented as sub dst, xzr, src.
unsigned ZReg = removeCopies(MRI, DefMI->getOperand(1).getReg());
if (ZReg != AArch64::XZR && ZReg != AArch64::WZR)
return 0;
SrcOpNum = 2;
Opc = Is64Bit ? AArch64::CSNEGXr : AArch64::CSNEGWr;
break;
}
default:
return 0;
}
assert(Opc && SrcOpNum && "Missing parameters");
if (NewVReg)
*NewVReg = DefMI->getOperand(SrcOpNum).getReg();
return Opc;
}
bool AArch64InstrInfo::canInsertSelect(const MachineBasicBlock &MBB,
ArrayRef<MachineOperand> Cond,
Register DstReg, Register TrueReg,
Register FalseReg, int &CondCycles,
int &TrueCycles,
int &FalseCycles) const {
// Check register classes.
const MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
const TargetRegisterClass *RC =
RI.getCommonSubClass(MRI.getRegClass(TrueReg), MRI.getRegClass(FalseReg));
if (!RC)
return false;
// Also need to check the dest regclass, in case we're trying to optimize
// something like:
// %1(gpr) = PHI %2(fpr), bb1, %(fpr), bb2
if (!RI.getCommonSubClass(RC, MRI.getRegClass(DstReg)))
return false;
// Expanding cbz/tbz requires an extra cycle of latency on the condition.
unsigned ExtraCondLat = Cond.size() != 1;
// GPRs are handled by csel.
// FIXME: Fold in x+1, -x, and ~x when applicable.
if (AArch64::GPR64allRegClass.hasSubClassEq(RC) ||
AArch64::GPR32allRegClass.hasSubClassEq(RC)) {
// Single-cycle csel, csinc, csinv, and csneg.
CondCycles = 1 + ExtraCondLat;
TrueCycles = FalseCycles = 1;
if (canFoldIntoCSel(MRI, TrueReg))
TrueCycles = 0;
else if (canFoldIntoCSel(MRI, FalseReg))
FalseCycles = 0;
return true;
}
// Scalar floating point is handled by fcsel.
// FIXME: Form fabs, fmin, and fmax when applicable.
if (AArch64::FPR64RegClass.hasSubClassEq(RC) ||
AArch64::FPR32RegClass.hasSubClassEq(RC)) {
CondCycles = 5 + ExtraCondLat;
TrueCycles = FalseCycles = 2;
return true;
}
// Can't do vectors.
return false;
}
void AArch64InstrInfo::insertSelect(MachineBasicBlock &MBB,
MachineBasicBlock::iterator I,
const DebugLoc &DL, Register DstReg,
ArrayRef<MachineOperand> Cond,
Register TrueReg, Register FalseReg) const {
MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
// Parse the condition code, see parseCondBranch() above.
AArch64CC::CondCode CC;
switch (Cond.size()) {
default:
llvm_unreachable("Unknown condition opcode in Cond");
case 1: // b.cc
CC = AArch64CC::CondCode(Cond[0].getImm());
break;
case 3: { // cbz/cbnz
// We must insert a compare against 0.
bool Is64Bit;
switch (Cond[1].getImm()) {
default:
llvm_unreachable("Unknown branch opcode in Cond");
case AArch64::CBZW:
Is64Bit = false;
CC = AArch64CC::EQ;
break;
case AArch64::CBZX:
Is64Bit = true;
CC = AArch64CC::EQ;
break;
case AArch64::CBNZW:
Is64Bit = false;
CC = AArch64CC::NE;
break;
case AArch64::CBNZX:
Is64Bit = true;
CC = AArch64CC::NE;
break;
}
Register SrcReg = Cond[2].getReg();
if (Is64Bit) {
// cmp reg, #0 is actually subs xzr, reg, #0.
MRI.constrainRegClass(SrcReg, &AArch64::GPR64spRegClass);
BuildMI(MBB, I, DL, get(AArch64::SUBSXri), AArch64::XZR)
.addReg(SrcReg)
.addImm(0)
.addImm(0);
} else {
MRI.constrainRegClass(SrcReg, &AArch64::GPR32spRegClass);
BuildMI(MBB, I, DL, get(AArch64::SUBSWri), AArch64::WZR)
.addReg(SrcReg)
.addImm(0)
.addImm(0);
}
break;
}
case 4: { // tbz/tbnz
// We must insert a tst instruction.
switch (Cond[1].getImm()) {
default:
llvm_unreachable("Unknown branch opcode in Cond");
case AArch64::TBZW:
case AArch64::TBZX:
CC = AArch64CC::EQ;
break;
case AArch64::TBNZW:
case AArch64::TBNZX:
CC = AArch64CC::NE;
break;
}
// cmp reg, #foo is actually ands xzr, reg, #1<<foo.
if (Cond[1].getImm() == AArch64::TBZW || Cond[1].getImm() == AArch64::TBNZW)
BuildMI(MBB, I, DL, get(AArch64::ANDSWri), AArch64::WZR)
.addReg(Cond[2].getReg())
.addImm(
AArch64_AM::encodeLogicalImmediate(1ull << Cond[3].getImm(), 32));
else
BuildMI(MBB, I, DL, get(AArch64::ANDSXri), AArch64::XZR)
.addReg(Cond[2].getReg())
.addImm(
AArch64_AM::encodeLogicalImmediate(1ull << Cond[3].getImm(), 64));
break;
}
}
unsigned Opc = 0;
const TargetRegisterClass *RC = nullptr;
bool TryFold = false;
if (MRI.constrainRegClass(DstReg, &AArch64::GPR64RegClass)) {
RC = &AArch64::GPR64RegClass;
Opc = AArch64::CSELXr;
TryFold = true;
} else if (MRI.constrainRegClass(DstReg, &AArch64::GPR32RegClass)) {
RC = &AArch64::GPR32RegClass;
Opc = AArch64::CSELWr;
TryFold = true;
} else if (MRI.constrainRegClass(DstReg, &AArch64::FPR64RegClass)) {
RC = &AArch64::FPR64RegClass;
Opc = AArch64::FCSELDrrr;
} else if (MRI.constrainRegClass(DstReg, &AArch64::FPR32RegClass)) {
RC = &AArch64::FPR32RegClass;
Opc = AArch64::FCSELSrrr;
}
assert(RC && "Unsupported regclass");
// Try folding simple instructions into the csel.
if (TryFold) {
unsigned NewVReg = 0;
unsigned FoldedOpc = canFoldIntoCSel(MRI, TrueReg, &NewVReg);
if (FoldedOpc) {
// The folded opcodes csinc, csinc and csneg apply the operation to
// FalseReg, so we need to invert the condition.
CC = AArch64CC::getInvertedCondCode(CC);
TrueReg = FalseReg;
} else
FoldedOpc = canFoldIntoCSel(MRI, FalseReg, &NewVReg);
// Fold the operation. Leave any dead instructions for DCE to clean up.
if (FoldedOpc) {
FalseReg = NewVReg;
Opc = FoldedOpc;
// The extends the live range of NewVReg.
MRI.clearKillFlags(NewVReg);
}
}
// Pull all virtual register into the appropriate class.
MRI.constrainRegClass(TrueReg, RC);
MRI.constrainRegClass(FalseReg, RC);
// Insert the csel.
BuildMI(MBB, I, DL, get(Opc), DstReg)
.addReg(TrueReg)
.addReg(FalseReg)
.addImm(CC);
}
// Return true if Imm can be loaded into a register by a "cheap" sequence of
// instructions. For now, "cheap" means at most two instructions.
static bool isCheapImmediate(const MachineInstr &MI, unsigned BitSize) {
if (BitSize == 32)
return true;
assert(BitSize == 64 && "Only bit sizes of 32 or 64 allowed");
uint64_t Imm = static_cast<uint64_t>(MI.getOperand(1).getImm());
SmallVector<AArch64_IMM::ImmInsnModel, 4> Is;
AArch64_IMM::expandMOVImm(Imm, BitSize, Is);
return Is.size() <= 2;
}
// FIXME: this implementation should be micro-architecture dependent, so a
// micro-architecture target hook should be introduced here in future.
bool AArch64InstrInfo::isAsCheapAsAMove(const MachineInstr &MI) const {
if (Subtarget.hasExynosCheapAsMoveHandling()) {
if (isExynosCheapAsMove(MI))
return true;
return MI.isAsCheapAsAMove();
}
switch (MI.getOpcode()) {
default:
return MI.isAsCheapAsAMove();
case AArch64::ADDWrs:
case AArch64::ADDXrs:
case AArch64::SUBWrs:
case AArch64::SUBXrs:
return Subtarget.hasALULSLFast() && MI.getOperand(3).getImm() <= 4;
// If MOVi32imm or MOVi64imm can be expanded into ORRWri or
// ORRXri, it is as cheap as MOV.
// Likewise if it can be expanded to MOVZ/MOVN/MOVK.
case AArch64::MOVi32imm:
return isCheapImmediate(MI, 32);
case AArch64::MOVi64imm:
return isCheapImmediate(MI, 64);
}
}
bool AArch64InstrInfo::isFalkorShiftExtFast(const MachineInstr &MI) {
switch (MI.getOpcode()) {
default:
return false;
case AArch64::ADDWrs:
case AArch64::ADDXrs:
case AArch64::ADDSWrs:
case AArch64::ADDSXrs: {
unsigned Imm = MI.getOperand(3).getImm();
unsigned ShiftVal = AArch64_AM::getShiftValue(Imm);
if (ShiftVal == 0)
return true;
return AArch64_AM::getShiftType(Imm) == AArch64_AM::LSL && ShiftVal <= 5;
}
case AArch64::ADDWrx:
case AArch64::ADDXrx:
case AArch64::ADDXrx64:
case AArch64::ADDSWrx:
case AArch64::ADDSXrx:
case AArch64::ADDSXrx64: {
unsigned Imm = MI.getOperand(3).getImm();
switch (AArch64_AM::getArithExtendType(Imm)) {
default:
return false;
case AArch64_AM::UXTB:
case AArch64_AM::UXTH:
case AArch64_AM::UXTW:
case AArch64_AM::UXTX:
return AArch64_AM::getArithShiftValue(Imm) <= 4;
}
}
case AArch64::SUBWrs:
case AArch64::SUBSWrs: {
unsigned Imm = MI.getOperand(3).getImm();
unsigned ShiftVal = AArch64_AM::getShiftValue(Imm);
return ShiftVal == 0 ||
(AArch64_AM::getShiftType(Imm) == AArch64_AM::ASR && ShiftVal == 31);
}
case AArch64::SUBXrs:
case AArch64::SUBSXrs: {
unsigned Imm = MI.getOperand(3).getImm();
unsigned ShiftVal = AArch64_AM::getShiftValue(Imm);
return ShiftVal == 0 ||
(AArch64_AM::getShiftType(Imm) == AArch64_AM::ASR && ShiftVal == 63);
}
case AArch64::SUBWrx:
case AArch64::SUBXrx:
case AArch64::SUBXrx64:
case AArch64::SUBSWrx:
case AArch64::SUBSXrx:
case AArch64::SUBSXrx64: {
unsigned Imm = MI.getOperand(3).getImm();
switch (AArch64_AM::getArithExtendType(Imm)) {
default:
return false;
case AArch64_AM::UXTB:
case AArch64_AM::UXTH:
case AArch64_AM::UXTW:
case AArch64_AM::UXTX:
return AArch64_AM::getArithShiftValue(Imm) == 0;
}
}
case AArch64::LDRBBroW:
case AArch64::LDRBBroX:
case AArch64::LDRBroW:
case AArch64::LDRBroX:
case AArch64::LDRDroW:
case AArch64::LDRDroX:
case AArch64::LDRHHroW:
case AArch64::LDRHHroX:
case AArch64::LDRHroW:
case AArch64::LDRHroX:
case AArch64::LDRQroW:
case AArch64::LDRQroX:
case AArch64::LDRSBWroW:
case AArch64::LDRSBWroX:
case AArch64::LDRSBXroW:
case AArch64::LDRSBXroX:
case AArch64::LDRSHWroW:
case AArch64::LDRSHWroX:
case AArch64::LDRSHXroW:
case AArch64::LDRSHXroX:
case AArch64::LDRSWroW:
case AArch64::LDRSWroX:
case AArch64::LDRSroW:
case AArch64::LDRSroX:
case AArch64::LDRWroW:
case AArch64::LDRWroX:
case AArch64::LDRXroW:
case AArch64::LDRXroX:
case AArch64::PRFMroW:
case AArch64::PRFMroX:
case AArch64::STRBBroW:
case AArch64::STRBBroX:
case AArch64::STRBroW:
case AArch64::STRBroX:
case AArch64::STRDroW:
case AArch64::STRDroX:
case AArch64::STRHHroW:
case AArch64::STRHHroX:
case AArch64::STRHroW:
case AArch64::STRHroX:
case AArch64::STRQroW:
case AArch64::STRQroX:
case AArch64::STRSroW:
case AArch64::STRSroX:
case AArch64::STRWroW:
case AArch64::STRWroX:
case AArch64::STRXroW:
case AArch64::STRXroX: {
unsigned IsSigned = MI.getOperand(3).getImm();
return !IsSigned;
}
}
}
bool AArch64InstrInfo::isSEHInstruction(const MachineInstr &MI) {
unsigned Opc = MI.getOpcode();
switch (Opc) {
default:
return false;
case AArch64::SEH_StackAlloc:
case AArch64::SEH_SaveFPLR:
case AArch64::SEH_SaveFPLR_X:
case AArch64::SEH_SaveReg:
case AArch64::SEH_SaveReg_X:
case AArch64::SEH_SaveRegP:
case AArch64::SEH_SaveRegP_X:
case AArch64::SEH_SaveFReg:
case AArch64::SEH_SaveFReg_X:
case AArch64::SEH_SaveFRegP:
case AArch64::SEH_SaveFRegP_X:
case AArch64::SEH_SetFP:
case AArch64::SEH_AddFP:
case AArch64::SEH_Nop:
case AArch64::SEH_PrologEnd:
case AArch64::SEH_EpilogStart:
case AArch64::SEH_EpilogEnd:
case AArch64::SEH_PACSignLR:
return true;
}
}
bool AArch64InstrInfo::isCoalescableExtInstr(const MachineInstr &MI,
Register &SrcReg, Register &DstReg,
unsigned &SubIdx) const {
switch (MI.getOpcode()) {
default:
return false;
case AArch64::SBFMXri: // aka sxtw
case AArch64::UBFMXri: // aka uxtw
// Check for the 32 -> 64 bit extension case, these instructions can do
// much more.
if (MI.getOperand(2).getImm() != 0 || MI.getOperand(3).getImm() != 31)
return false;
// This is a signed or unsigned 32 -> 64 bit extension.
SrcReg = MI.getOperand(1).getReg();
DstReg = MI.getOperand(0).getReg();
SubIdx = AArch64::sub_32;
return true;
}
}
bool AArch64InstrInfo::areMemAccessesTriviallyDisjoint(
const MachineInstr &MIa, const MachineInstr &MIb) const {
const TargetRegisterInfo *TRI = &getRegisterInfo();
const MachineOperand *BaseOpA = nullptr, *BaseOpB = nullptr;
int64_t OffsetA = 0, OffsetB = 0;
unsigned WidthA = 0, WidthB = 0;
bool OffsetAIsScalable = false, OffsetBIsScalable = false;
assert(MIa.mayLoadOrStore() && "MIa must be a load or store.");
assert(MIb.mayLoadOrStore() && "MIb must be a load or store.");
if (MIa.hasUnmodeledSideEffects() || MIb.hasUnmodeledSideEffects() ||
MIa.hasOrderedMemoryRef() || MIb.hasOrderedMemoryRef())
return false;
// Retrieve the base, offset from the base and width. Width
// is the size of memory that is being loaded/stored (e.g. 1, 2, 4, 8). If
// base are identical, and the offset of a lower memory access +
// the width doesn't overlap the offset of a higher memory access,
// then the memory accesses are different.
// If OffsetAIsScalable and OffsetBIsScalable are both true, they
// are assumed to have the same scale (vscale).
if (getMemOperandWithOffsetWidth(MIa, BaseOpA, OffsetA, OffsetAIsScalable,
WidthA, TRI) &&
getMemOperandWithOffsetWidth(MIb, BaseOpB, OffsetB, OffsetBIsScalable,
WidthB, TRI)) {
if (BaseOpA->isIdenticalTo(*BaseOpB) &&
OffsetAIsScalable == OffsetBIsScalable) {
int LowOffset = OffsetA < OffsetB ? OffsetA : OffsetB;
int HighOffset = OffsetA < OffsetB ? OffsetB : OffsetA;
int LowWidth = (LowOffset == OffsetA) ? WidthA : WidthB;
if (LowOffset + LowWidth <= HighOffset)
return true;
}
}
return false;
}
bool AArch64InstrInfo::isSchedulingBoundary(const MachineInstr &MI,
const MachineBasicBlock *MBB,
const MachineFunction &MF) const {
if (TargetInstrInfo::isSchedulingBoundary(MI, MBB, MF))
return true;
switch (MI.getOpcode()) {
case AArch64::HINT:
// CSDB hints are scheduling barriers.
if (MI.getOperand(0).getImm() == 0x14)
return true;
break;
case AArch64::DSB:
case AArch64::ISB:
// DSB and ISB also are scheduling barriers.
return true;
case AArch64::MSRpstatesvcrImm1:
// SMSTART and SMSTOP are also scheduling barriers.
return true;
default:;
}
if (isSEHInstruction(MI))
return true;
auto Next = std::next(MI.getIterator());
return Next != MBB->end() && Next->isCFIInstruction();
}
/// analyzeCompare - For a comparison instruction, return the source registers
/// in SrcReg and SrcReg2, and the value it compares against in CmpValue.
/// Return true if the comparison instruction can be analyzed.
bool AArch64InstrInfo::analyzeCompare(const MachineInstr &MI, Register &SrcReg,
Register &SrcReg2, int64_t &CmpMask,
int64_t &CmpValue) const {
// The first operand can be a frame index where we'd normally expect a
// register.
assert(MI.getNumOperands() >= 2 && "All AArch64 cmps should have 2 operands");
if (!MI.getOperand(1).isReg())
return false;
switch (MI.getOpcode()) {
default:
break;
case AArch64::PTEST_PP:
case AArch64::PTEST_PP_ANY:
SrcReg = MI.getOperand(0).getReg();
SrcReg2 = MI.getOperand(1).getReg();
// Not sure about the mask and value for now...
CmpMask = ~0;
CmpValue = 0;
return true;
case AArch64::SUBSWrr:
case AArch64::SUBSWrs:
case AArch64::SUBSWrx:
case AArch64::SUBSXrr:
case AArch64::SUBSXrs:
case AArch64::SUBSXrx:
case AArch64::ADDSWrr:
case AArch64::ADDSWrs:
case AArch64::ADDSWrx:
case AArch64::ADDSXrr:
case AArch64::ADDSXrs:
case AArch64::ADDSXrx:
// Replace SUBSWrr with SUBWrr if NZCV is not used.
SrcReg = MI.getOperand(1).getReg();
SrcReg2 = MI.getOperand(2).getReg();
CmpMask = ~0;
CmpValue = 0;
return true;
case AArch64::SUBSWri:
case AArch64::ADDSWri:
case AArch64::SUBSXri:
case AArch64::ADDSXri:
SrcReg = MI.getOperand(1).getReg();
SrcReg2 = 0;
CmpMask = ~0;
CmpValue = MI.getOperand(2).getImm();
return true;
case AArch64::ANDSWri:
case AArch64::ANDSXri:
// ANDS does not use the same encoding scheme as the others xxxS
// instructions.
SrcReg = MI.getOperand(1).getReg();
SrcReg2 = 0;
CmpMask = ~0;
CmpValue = AArch64_AM::decodeLogicalImmediate(
MI.getOperand(2).getImm(),
MI.getOpcode() == AArch64::ANDSWri ? 32 : 64);
return true;
}
return false;
}
static bool UpdateOperandRegClass(MachineInstr &Instr) {
MachineBasicBlock *MBB = Instr.getParent();
assert(MBB && "Can't get MachineBasicBlock here");
MachineFunction *MF = MBB->getParent();
assert(MF && "Can't get MachineFunction here");
const TargetInstrInfo *TII = MF->getSubtarget().getInstrInfo();
const TargetRegisterInfo *TRI = MF->getSubtarget().getRegisterInfo();
MachineRegisterInfo *MRI = &MF->getRegInfo();
for (unsigned OpIdx = 0, EndIdx = Instr.getNumOperands(); OpIdx < EndIdx;
++OpIdx) {
MachineOperand &MO = Instr.getOperand(OpIdx);
const TargetRegisterClass *OpRegCstraints =
Instr.getRegClassConstraint(OpIdx, TII, TRI);
// If there's no constraint, there's nothing to do.
if (!OpRegCstraints)
continue;
// If the operand is a frame index, there's nothing to do here.
// A frame index operand will resolve correctly during PEI.
if (MO.isFI())
continue;
assert(MO.isReg() &&
"Operand has register constraints without being a register!");
Register Reg = MO.getReg();
if (Reg.isPhysical()) {
if (!OpRegCstraints->contains(Reg))
return false;
} else if (!OpRegCstraints->hasSubClassEq(MRI->getRegClass(Reg)) &&
!MRI->constrainRegClass(Reg, OpRegCstraints))
return false;
}
return true;
}
/// Return the opcode that does not set flags when possible - otherwise
/// return the original opcode. The caller is responsible to do the actual
/// substitution and legality checking.
static unsigned convertToNonFlagSettingOpc(const MachineInstr &MI) {
// Don't convert all compare instructions, because for some the zero register
// encoding becomes the sp register.
bool MIDefinesZeroReg = false;
if (MI.definesRegister(AArch64::WZR) || MI.definesRegister(AArch64::XZR))
MIDefinesZeroReg = true;
switch (MI.getOpcode()) {
default:
return MI.getOpcode();
case AArch64::ADDSWrr:
return AArch64::ADDWrr;
case AArch64::ADDSWri:
return MIDefinesZeroReg ? AArch64::ADDSWri : AArch64::ADDWri;
case AArch64::ADDSWrs:
return MIDefinesZeroReg ? AArch64::ADDSWrs : AArch64::ADDWrs;
case AArch64::ADDSWrx:
return AArch64::ADDWrx;
case AArch64::ADDSXrr:
return AArch64::ADDXrr;
case AArch64::ADDSXri:
return MIDefinesZeroReg ? AArch64::ADDSXri : AArch64::ADDXri;
case AArch64::ADDSXrs:
return MIDefinesZeroReg ? AArch64::ADDSXrs : AArch64::ADDXrs;
case AArch64::ADDSXrx:
return AArch64::ADDXrx;
case AArch64::SUBSWrr:
return AArch64::SUBWrr;
case AArch64::SUBSWri:
return MIDefinesZeroReg ? AArch64::SUBSWri : AArch64::SUBWri;
case AArch64::SUBSWrs:
return MIDefinesZeroReg ? AArch64::SUBSWrs : AArch64::SUBWrs;
case AArch64::SUBSWrx:
return AArch64::SUBWrx;
case AArch64::SUBSXrr:
return AArch64::SUBXrr;
case AArch64::SUBSXri:
return MIDefinesZeroReg ? AArch64::SUBSXri : AArch64::SUBXri;
case AArch64::SUBSXrs:
return MIDefinesZeroReg ? AArch64::SUBSXrs : AArch64::SUBXrs;
case AArch64::SUBSXrx:
return AArch64::SUBXrx;
}
}
enum AccessKind { AK_Write = 0x01, AK_Read = 0x10, AK_All = 0x11 };
/// True when condition flags are accessed (either by writing or reading)
/// on the instruction trace starting at From and ending at To.
///
/// Note: If From and To are from different blocks it's assumed CC are accessed
/// on the path.
static bool areCFlagsAccessedBetweenInstrs(
MachineBasicBlock::iterator From, MachineBasicBlock::iterator To,
const TargetRegisterInfo *TRI, const AccessKind AccessToCheck = AK_All) {
// Early exit if To is at the beginning of the BB.
if (To == To->getParent()->begin())
return true;
// Check whether the instructions are in the same basic block
// If not, assume the condition flags might get modified somewhere.
if (To->getParent() != From->getParent())
return true;
// From must be above To.
assert(std::any_of(
++To.getReverse(), To->getParent()->rend(),
[From](MachineInstr &MI) { return MI.getIterator() == From; }));
// We iterate backward starting at \p To until we hit \p From.
for (const MachineInstr &Instr :
instructionsWithoutDebug(++To.getReverse(), From.getReverse())) {
if (((AccessToCheck & AK_Write) &&
Instr.modifiesRegister(AArch64::NZCV, TRI)) ||
((AccessToCheck & AK_Read) && Instr.readsRegister(AArch64::NZCV, TRI)))
return true;
}
return false;
}
/// optimizePTestInstr - Attempt to remove a ptest of a predicate-generating
/// operation which could set the flags in an identical manner
bool AArch64InstrInfo::optimizePTestInstr(
MachineInstr *PTest, unsigned MaskReg, unsigned PredReg,
const MachineRegisterInfo *MRI) const {
auto *Mask = MRI->getUniqueVRegDef(MaskReg);
auto *Pred = MRI->getUniqueVRegDef(PredReg);
auto NewOp = Pred->getOpcode();
bool OpChanged = false;
unsigned MaskOpcode = Mask->getOpcode();
unsigned PredOpcode = Pred->getOpcode();
bool PredIsPTestLike = isPTestLikeOpcode(PredOpcode);
bool PredIsWhileLike = isWhileOpcode(PredOpcode);
if (isPTrueOpcode(MaskOpcode) && (PredIsPTestLike || PredIsWhileLike) &&
getElementSizeForOpcode(MaskOpcode) ==
getElementSizeForOpcode(PredOpcode) &&
Mask->getOperand(1).getImm() == 31) {
// For PTEST(PTRUE_ALL, WHILE), if the element size matches, the PTEST is
// redundant since WHILE performs an implicit PTEST with an all active
// mask. Must be an all active predicate of matching element size.
// For PTEST(PTRUE_ALL, PTEST_LIKE), the PTEST is redundant if the
// PTEST_LIKE instruction uses the same all active mask and the element
// size matches. If the PTEST has a condition of any then it is always
// redundant.
if (PredIsPTestLike) {
auto PTestLikeMask = MRI->getUniqueVRegDef(Pred->getOperand(1).getReg());
if (Mask != PTestLikeMask && PTest->getOpcode() != AArch64::PTEST_PP_ANY)
return false;
}
// Fallthough to simply remove the PTEST.
} else if ((Mask == Pred) && (PredIsPTestLike || PredIsWhileLike) &&
PTest->getOpcode() == AArch64::PTEST_PP_ANY) {
// For PTEST(PG, PG), PTEST is redundant when PG is the result of an
// instruction that sets the flags as PTEST would. This is only valid when
// the condition is any.
// Fallthough to simply remove the PTEST.
} else if (PredIsPTestLike) {
// For PTEST(PG, PTEST_LIKE(PG, ...)), the PTEST is redundant since the
// flags are set based on the same mask 'PG', but PTEST_LIKE must operate
// on 8-bit predicates like the PTEST. Otherwise, for instructions like
// compare that also support 16/32/64-bit predicates, the implicit PTEST
// performed by the compare could consider fewer lanes for these element
// sizes.
//
// For example, consider
//
// ptrue p0.b ; P0=1111-1111-1111-1111
// index z0.s, #0, #1 ; Z0=<0,1,2,3>
// index z1.s, #1, #1 ; Z1=<1,2,3,4>
// cmphi p1.s, p0/z, z1.s, z0.s ; P1=0001-0001-0001-0001
// ; ^ last active
// ptest p0, p1.b ; P1=0001-0001-0001-0001
// ; ^ last active
//
// where the compare generates a canonical all active 32-bit predicate
// (equivalent to 'ptrue p1.s, all'). The implicit PTEST sets the last
// active flag, whereas the PTEST instruction with the same mask doesn't.
// For PTEST_ANY this doesn't apply as the flags in this case would be
// identical regardless of element size.
auto PTestLikeMask = MRI->getUniqueVRegDef(Pred->getOperand(1).getReg());
uint64_t PredElementSize = getElementSizeForOpcode(PredOpcode);
if ((Mask != PTestLikeMask) ||
(PredElementSize != AArch64::ElementSizeB &&
PTest->getOpcode() != AArch64::PTEST_PP_ANY))
return false;
// Fallthough to simply remove the PTEST.
} else {
// If OP in PTEST(PG, OP(PG, ...)) has a flag-setting variant change the
// opcode so the PTEST becomes redundant.
switch (PredOpcode) {
case AArch64::AND_PPzPP:
case AArch64::BIC_PPzPP:
case AArch64::EOR_PPzPP:
case AArch64::NAND_PPzPP:
case AArch64::NOR_PPzPP:
case AArch64::ORN_PPzPP:
case AArch64::ORR_PPzPP:
case AArch64::BRKA_PPzP:
case AArch64::BRKPA_PPzPP:
case AArch64::BRKB_PPzP:
case AArch64::BRKPB_PPzPP:
case AArch64::RDFFR_PPz: {
// Check to see if our mask is the same. If not the resulting flag bits
// may be different and we can't remove the ptest.
auto *PredMask = MRI->getUniqueVRegDef(Pred->getOperand(1).getReg());
if (Mask != PredMask)
return false;
break;
}
case AArch64::BRKN_PPzP: {
// BRKN uses an all active implicit mask to set flags unlike the other
// flag-setting instructions.
// PTEST(PTRUE_B(31), BRKN(PG, A, B)) -> BRKNS(PG, A, B).
if ((MaskOpcode != AArch64::PTRUE_B) ||
(Mask->getOperand(1).getImm() != 31))
return false;
break;
}
case AArch64::PTRUE_B:
// PTEST(OP=PTRUE_B(A), OP) -> PTRUES_B(A)
break;
default:
// Bail out if we don't recognize the input
return false;
}
NewOp = convertToFlagSettingOpc(PredOpcode);
OpChanged = true;
}
const TargetRegisterInfo *TRI = &getRegisterInfo();
// If another instruction between Pred and PTest accesses flags, don't remove
// the ptest or update the earlier instruction to modify them.
if (areCFlagsAccessedBetweenInstrs(Pred, PTest, TRI))
return false;
// If we pass all the checks, it's safe to remove the PTEST and use the flags
// as they are prior to PTEST. Sometimes this requires the tested PTEST
// operand to be replaced with an equivalent instruction that also sets the
// flags.
Pred->setDesc(get(NewOp));
PTest->eraseFromParent();
if (OpChanged) {
bool succeeded = UpdateOperandRegClass(*Pred);
(void)succeeded;
assert(succeeded && "Operands have incompatible register classes!");
Pred->addRegisterDefined(AArch64::NZCV, TRI);
}
// Ensure that the flags def is live.
if (Pred->registerDefIsDead(AArch64::NZCV, TRI)) {
unsigned i = 0, e = Pred->getNumOperands();
for (; i != e; ++i) {
MachineOperand &MO = Pred->getOperand(i);
if (MO.isReg() && MO.isDef() && MO.getReg() == AArch64::NZCV) {
MO.setIsDead(false);
break;
}
}
}
return true;
}
/// Try to optimize a compare instruction. A compare instruction is an
/// instruction which produces AArch64::NZCV. It can be truly compare
/// instruction
/// when there are no uses of its destination register.
///
/// The following steps are tried in order:
/// 1. Convert CmpInstr into an unconditional version.
/// 2. Remove CmpInstr if above there is an instruction producing a needed
/// condition code or an instruction which can be converted into such an
/// instruction.
/// Only comparison with zero is supported.
bool AArch64InstrInfo::optimizeCompareInstr(
MachineInstr &CmpInstr, Register SrcReg, Register SrcReg2, int64_t CmpMask,
int64_t CmpValue, const MachineRegisterInfo *MRI) const {
assert(CmpInstr.getParent());
assert(MRI);
// Replace SUBSWrr with SUBWrr if NZCV is not used.
int DeadNZCVIdx = CmpInstr.findRegisterDefOperandIdx(AArch64::NZCV, true);
if (DeadNZCVIdx != -1) {
if (CmpInstr.definesRegister(AArch64::WZR) ||
CmpInstr.definesRegister(AArch64::XZR)) {
CmpInstr.eraseFromParent();
return true;
}
unsigned Opc = CmpInstr.getOpcode();
unsigned NewOpc = convertToNonFlagSettingOpc(CmpInstr);
if (NewOpc == Opc)
return false;
const MCInstrDesc &MCID = get(NewOpc);
CmpInstr.setDesc(MCID);
CmpInstr.removeOperand(DeadNZCVIdx);
bool succeeded = UpdateOperandRegClass(CmpInstr);
(void)succeeded;
assert(succeeded && "Some operands reg class are incompatible!");
return true;
}
if (CmpInstr.getOpcode() == AArch64::PTEST_PP ||
CmpInstr.getOpcode() == AArch64::PTEST_PP_ANY)
return optimizePTestInstr(&CmpInstr, SrcReg, SrcReg2, MRI);
if (SrcReg2 != 0)
return false;
// CmpInstr is a Compare instruction if destination register is not used.
if (!MRI->use_nodbg_empty(CmpInstr.getOperand(0).getReg()))
return false;
if (CmpValue == 0 && substituteCmpToZero(CmpInstr, SrcReg, *MRI))
return true;
return (CmpValue == 0 || CmpValue == 1) &&
removeCmpToZeroOrOne(CmpInstr, SrcReg, CmpValue, *MRI);
}
/// Get opcode of S version of Instr.
/// If Instr is S version its opcode is returned.
/// AArch64::INSTRUCTION_LIST_END is returned if Instr does not have S version
/// or we are not interested in it.
static unsigned sForm(MachineInstr &Instr) {
switch (Instr.getOpcode()) {
default:
return AArch64::INSTRUCTION_LIST_END;
case AArch64::ADDSWrr:
case AArch64::ADDSWri:
case AArch64::ADDSXrr:
case AArch64::ADDSXri:
case AArch64::SUBSWrr:
case AArch64::SUBSWri:
case AArch64::SUBSXrr:
case AArch64::SUBSXri:
return Instr.getOpcode();
case AArch64::ADDWrr:
return AArch64::ADDSWrr;
case AArch64::ADDWri:
return AArch64::ADDSWri;
case AArch64::ADDXrr:
return AArch64::ADDSXrr;
case AArch64::ADDXri:
return AArch64::ADDSXri;
case AArch64::ADCWr:
return AArch64::ADCSWr;
case AArch64::ADCXr:
return AArch64::ADCSXr;
case AArch64::SUBWrr:
return AArch64::SUBSWrr;
case AArch64::SUBWri:
return AArch64::SUBSWri;
case AArch64::SUBXrr:
return AArch64::SUBSXrr;
case AArch64::SUBXri:
return AArch64::SUBSXri;
case AArch64::SBCWr:
return AArch64::SBCSWr;
case AArch64::SBCXr:
return AArch64::SBCSXr;
case AArch64::ANDWri:
return AArch64::ANDSWri;
case AArch64::ANDXri:
return AArch64::ANDSXri;
}
}
/// Check if AArch64::NZCV should be alive in successors of MBB.
static bool areCFlagsAliveInSuccessors(const MachineBasicBlock *MBB) {
for (auto *BB : MBB->successors())
if (BB->isLiveIn(AArch64::NZCV))
return true;
return false;
}
/// \returns The condition code operand index for \p Instr if it is a branch
/// or select and -1 otherwise.
static int
findCondCodeUseOperandIdxForBranchOrSelect(const MachineInstr &Instr) {
switch (Instr.getOpcode()) {
default:
return -1;
case AArch64::Bcc: {
int Idx = Instr.findRegisterUseOperandIdx(AArch64::NZCV);
assert(Idx >= 2);
return Idx - 2;
}
case AArch64::CSINVWr:
case AArch64::CSINVXr:
case AArch64::CSINCWr:
case AArch64::CSINCXr:
case AArch64::CSELWr:
case AArch64::CSELXr:
case AArch64::CSNEGWr:
case AArch64::CSNEGXr:
case AArch64::FCSELSrrr:
case AArch64::FCSELDrrr: {
int Idx = Instr.findRegisterUseOperandIdx(AArch64::NZCV);
assert(Idx >= 1);
return Idx - 1;
}
}
}
/// Find a condition code used by the instruction.
/// Returns AArch64CC::Invalid if either the instruction does not use condition
/// codes or we don't optimize CmpInstr in the presence of such instructions.
static AArch64CC::CondCode findCondCodeUsedByInstr(const MachineInstr &Instr) {
int CCIdx = findCondCodeUseOperandIdxForBranchOrSelect(Instr);
return CCIdx >= 0 ? static_cast<AArch64CC::CondCode>(
Instr.getOperand(CCIdx).getImm())
: AArch64CC::Invalid;
}
static UsedNZCV getUsedNZCV(AArch64CC::CondCode CC) {
assert(CC != AArch64CC::Invalid);
UsedNZCV UsedFlags;
switch (CC) {
default:
break;
case AArch64CC::EQ: // Z set
case AArch64CC::NE: // Z clear
UsedFlags.Z = true;
break;
case AArch64CC::HI: // Z clear and C set
case AArch64CC::LS: // Z set or C clear
UsedFlags.Z = true;
[[fallthrough]];
case AArch64CC::HS: // C set
case AArch64CC::LO: // C clear
UsedFlags.C = true;
break;
case AArch64CC::MI: // N set
case AArch64CC::PL: // N clear
UsedFlags.N = true;
break;
case AArch64CC::VS: // V set
case AArch64CC::VC: // V clear
UsedFlags.V = true;
break;
case AArch64CC::GT: // Z clear, N and V the same
case AArch64CC::LE: // Z set, N and V differ
UsedFlags.Z = true;
[[fallthrough]];
case AArch64CC::GE: // N and V the same
case AArch64CC::LT: // N and V differ
UsedFlags.N = true;
UsedFlags.V = true;
break;
}
return UsedFlags;
}
/// \returns Conditions flags used after \p CmpInstr in its MachineBB if NZCV
/// flags are not alive in successors of the same \p CmpInstr and \p MI parent.
/// \returns std::nullopt otherwise.
///
/// Collect instructions using that flags in \p CCUseInstrs if provided.
std::optional<UsedNZCV>
llvm::examineCFlagsUse(MachineInstr &MI, MachineInstr &CmpInstr,
const TargetRegisterInfo &TRI,
SmallVectorImpl<MachineInstr *> *CCUseInstrs) {
MachineBasicBlock *CmpParent = CmpInstr.getParent();
if (MI.getParent() != CmpParent)
return std::nullopt;
if (areCFlagsAliveInSuccessors(CmpParent))
return std::nullopt;
UsedNZCV NZCVUsedAfterCmp;
for (MachineInstr &Instr : instructionsWithoutDebug(
std::next(CmpInstr.getIterator()), CmpParent->instr_end())) {
if (Instr.readsRegister(AArch64::NZCV, &TRI)) {
AArch64CC::CondCode CC = findCondCodeUsedByInstr(Instr);
if (CC == AArch64CC::Invalid) // Unsupported conditional instruction
return std::nullopt;
NZCVUsedAfterCmp |= getUsedNZCV(CC);
if (CCUseInstrs)
CCUseInstrs->push_back(&Instr);
}
if (Instr.modifiesRegister(AArch64::NZCV, &TRI))
break;
}
return NZCVUsedAfterCmp;
}
static bool isADDSRegImm(unsigned Opcode) {
return Opcode == AArch64::ADDSWri || Opcode == AArch64::ADDSXri;
}
static bool isSUBSRegImm(unsigned Opcode) {
return Opcode == AArch64::SUBSWri || Opcode == AArch64::SUBSXri;
}
/// Check if CmpInstr can be substituted by MI.
///
/// CmpInstr can be substituted:
/// - CmpInstr is either 'ADDS %vreg, 0' or 'SUBS %vreg, 0'
/// - and, MI and CmpInstr are from the same MachineBB
/// - and, condition flags are not alive in successors of the CmpInstr parent
/// - and, if MI opcode is the S form there must be no defs of flags between
/// MI and CmpInstr
/// or if MI opcode is not the S form there must be neither defs of flags
/// nor uses of flags between MI and CmpInstr.
/// - and, if C/V flags are not used after CmpInstr
/// or if N flag is used but MI produces poison value if signed overflow
/// occurs.
static bool canInstrSubstituteCmpInstr(MachineInstr &MI, MachineInstr &CmpInstr,
const TargetRegisterInfo &TRI) {
// NOTE this assertion guarantees that MI.getOpcode() is add or subtraction
// that may or may not set flags.
assert(sForm(MI) != AArch64::INSTRUCTION_LIST_END);
const unsigned CmpOpcode = CmpInstr.getOpcode();
if (!isADDSRegImm(CmpOpcode) && !isSUBSRegImm(CmpOpcode))
return false;
assert((CmpInstr.getOperand(2).isImm() &&
CmpInstr.getOperand(2).getImm() == 0) &&
"Caller guarantees that CmpInstr compares with constant 0");
std::optional<UsedNZCV> NZVCUsed = examineCFlagsUse(MI, CmpInstr, TRI);
if (!NZVCUsed || NZVCUsed->C)
return false;
// CmpInstr is either 'ADDS %vreg, 0' or 'SUBS %vreg, 0', and MI is either
// '%vreg = add ...' or '%vreg = sub ...'.
// Condition flag V is used to indicate signed overflow.
// 1) MI and CmpInstr set N and V to the same value.
// 2) If MI is add/sub with no-signed-wrap, it produces a poison value when
// signed overflow occurs, so CmpInstr could still be simplified away.
if (NZVCUsed->V && !MI.getFlag(MachineInstr::NoSWrap))
return false;
AccessKind AccessToCheck = AK_Write;
if (sForm(MI) != MI.getOpcode())
AccessToCheck = AK_All;
return !areCFlagsAccessedBetweenInstrs(&MI, &CmpInstr, &TRI, AccessToCheck);
}
/// Substitute an instruction comparing to zero with another instruction
/// which produces needed condition flags.
///
/// Return true on success.
bool AArch64InstrInfo::substituteCmpToZero(
MachineInstr &CmpInstr, unsigned SrcReg,
const MachineRegisterInfo &MRI) const {
// Get the unique definition of SrcReg.
MachineInstr *MI = MRI.getUniqueVRegDef(SrcReg);
if (!MI)
return false;
const TargetRegisterInfo &TRI = getRegisterInfo();
unsigned NewOpc = sForm(*MI);
if (NewOpc == AArch64::INSTRUCTION_LIST_END)
return false;
if (!canInstrSubstituteCmpInstr(*MI, CmpInstr, TRI))
return false;
// Update the instruction to set NZCV.
MI->setDesc(get(NewOpc));
CmpInstr.eraseFromParent();
bool succeeded = UpdateOperandRegClass(*MI);
(void)succeeded;
assert(succeeded && "Some operands reg class are incompatible!");
MI->addRegisterDefined(AArch64::NZCV, &TRI);
return true;
}
/// \returns True if \p CmpInstr can be removed.
///
/// \p IsInvertCC is true if, after removing \p CmpInstr, condition
/// codes used in \p CCUseInstrs must be inverted.
static bool canCmpInstrBeRemoved(MachineInstr &MI, MachineInstr &CmpInstr,
int CmpValue, const TargetRegisterInfo &TRI,
SmallVectorImpl<MachineInstr *> &CCUseInstrs,
bool &IsInvertCC) {
assert((CmpValue == 0 || CmpValue == 1) &&
"Only comparisons to 0 or 1 considered for removal!");
// MI is 'CSINCWr %vreg, wzr, wzr, <cc>' or 'CSINCXr %vreg, xzr, xzr, <cc>'
unsigned MIOpc = MI.getOpcode();
if (MIOpc == AArch64::CSINCWr) {
if (MI.getOperand(1).getReg() != AArch64::WZR ||
MI.getOperand(2).getReg() != AArch64::WZR)
return false;
} else if (MIOpc == AArch64::CSINCXr) {
if (MI.getOperand(1).getReg() != AArch64::XZR ||
MI.getOperand(2).getReg() != AArch64::XZR)
return false;
} else {
return false;
}
AArch64CC::CondCode MICC = findCondCodeUsedByInstr(MI);
if (MICC == AArch64CC::Invalid)
return false;
// NZCV needs to be defined
if (MI.findRegisterDefOperandIdx(AArch64::NZCV, true) != -1)
return false;
// CmpInstr is 'ADDS %vreg, 0' or 'SUBS %vreg, 0' or 'SUBS %vreg, 1'
const unsigned CmpOpcode = CmpInstr.getOpcode();
bool IsSubsRegImm = isSUBSRegImm(CmpOpcode);
if (CmpValue && !IsSubsRegImm)
return false;
if (!CmpValue && !IsSubsRegImm && !isADDSRegImm(CmpOpcode))
return false;
// MI conditions allowed: eq, ne, mi, pl
UsedNZCV MIUsedNZCV = getUsedNZCV(MICC);
if (MIUsedNZCV.C || MIUsedNZCV.V)
return false;
std::optional<UsedNZCV> NZCVUsedAfterCmp =
examineCFlagsUse(MI, CmpInstr, TRI, &CCUseInstrs);
// Condition flags are not used in CmpInstr basic block successors and only
// Z or N flags allowed to be used after CmpInstr within its basic block
if (!NZCVUsedAfterCmp || NZCVUsedAfterCmp->C || NZCVUsedAfterCmp->V)
return false;
// Z or N flag used after CmpInstr must correspond to the flag used in MI
if ((MIUsedNZCV.Z && NZCVUsedAfterCmp->N) ||
(MIUsedNZCV.N && NZCVUsedAfterCmp->Z))
return false;
// If CmpInstr is comparison to zero MI conditions are limited to eq, ne
if (MIUsedNZCV.N && !CmpValue)
return false;
// There must be no defs of flags between MI and CmpInstr
if (areCFlagsAccessedBetweenInstrs(&MI, &CmpInstr, &TRI, AK_Write))
return false;
// Condition code is inverted in the following cases:
// 1. MI condition is ne; CmpInstr is 'ADDS %vreg, 0' or 'SUBS %vreg, 0'
// 2. MI condition is eq, pl; CmpInstr is 'SUBS %vreg, 1'
IsInvertCC = (CmpValue && (MICC == AArch64CC::EQ || MICC == AArch64CC::PL)) ||
(!CmpValue && MICC == AArch64CC::NE);
return true;
}
/// Remove comparison in csinc-cmp sequence
///
/// Examples:
/// 1. \code
/// csinc w9, wzr, wzr, ne
/// cmp w9, #0
/// b.eq
/// \endcode
/// to
/// \code
/// csinc w9, wzr, wzr, ne
/// b.ne
/// \endcode
///
/// 2. \code
/// csinc x2, xzr, xzr, mi
/// cmp x2, #1
/// b.pl
/// \endcode
/// to
/// \code
/// csinc x2, xzr, xzr, mi
/// b.pl
/// \endcode
///
/// \param CmpInstr comparison instruction
/// \return True when comparison removed
bool AArch64InstrInfo::removeCmpToZeroOrOne(
MachineInstr &CmpInstr, unsigned SrcReg, int CmpValue,
const MachineRegisterInfo &MRI) const {
MachineInstr *MI = MRI.getUniqueVRegDef(SrcReg);
if (!MI)
return false;
const TargetRegisterInfo &TRI = getRegisterInfo();
SmallVector<MachineInstr *, 4> CCUseInstrs;
bool IsInvertCC = false;
if (!canCmpInstrBeRemoved(*MI, CmpInstr, CmpValue, TRI, CCUseInstrs,
IsInvertCC))
return false;
// Make transformation
CmpInstr.eraseFromParent();
if (IsInvertCC) {
// Invert condition codes in CmpInstr CC users
for (MachineInstr *CCUseInstr : CCUseInstrs) {
int Idx = findCondCodeUseOperandIdxForBranchOrSelect(*CCUseInstr);
assert(Idx >= 0 && "Unexpected instruction using CC.");
MachineOperand &CCOperand = CCUseInstr->getOperand(Idx);
AArch64CC::CondCode CCUse = AArch64CC::getInvertedCondCode(
static_cast<AArch64CC::CondCode>(CCOperand.getImm()));
CCOperand.setImm(CCUse);
}
}
return true;
}
bool AArch64InstrInfo::expandPostRAPseudo(MachineInstr &MI) const {
if (MI.getOpcode() != TargetOpcode::LOAD_STACK_GUARD &&
MI.getOpcode() != AArch64::CATCHRET)
return false;
MachineBasicBlock &MBB = *MI.getParent();
auto &Subtarget = MBB.getParent()->getSubtarget<AArch64Subtarget>();
auto TRI = Subtarget.getRegisterInfo();
DebugLoc DL = MI.getDebugLoc();
if (MI.getOpcode() == AArch64::CATCHRET) {
// Skip to the first instruction before the epilog.
const TargetInstrInfo *TII =
MBB.getParent()->getSubtarget().getInstrInfo();
MachineBasicBlock *TargetMBB = MI.getOperand(0).getMBB();
auto MBBI = MachineBasicBlock::iterator(MI);
MachineBasicBlock::iterator FirstEpilogSEH = std::prev(MBBI);
while (FirstEpilogSEH->getFlag(MachineInstr::FrameDestroy) &&
FirstEpilogSEH != MBB.begin())
FirstEpilogSEH = std::prev(FirstEpilogSEH);
if (FirstEpilogSEH != MBB.begin())
FirstEpilogSEH = std::next(FirstEpilogSEH);
BuildMI(MBB, FirstEpilogSEH, DL, TII->get(AArch64::ADRP))
.addReg(AArch64::X0, RegState::Define)
.addMBB(TargetMBB);
BuildMI(MBB, FirstEpilogSEH, DL, TII->get(AArch64::ADDXri))
.addReg(AArch64::X0, RegState::Define)
.addReg(AArch64::X0)
.addMBB(TargetMBB)
.addImm(0);
return true;
}
Register Reg = MI.getOperand(0).getReg();
Module &M = *MBB.getParent()->getFunction().getParent();
if (M.getStackProtectorGuard() == "sysreg") {
const AArch64SysReg::SysReg *SrcReg =
AArch64SysReg::lookupSysRegByName(M.getStackProtectorGuardReg());
if (!SrcReg)
report_fatal_error("Unknown SysReg for Stack Protector Guard Register");
// mrs xN, sysreg
BuildMI(MBB, MI, DL, get(AArch64::MRS))
.addDef(Reg, RegState::Renamable)
.addImm(SrcReg->Encoding);
int Offset = M.getStackProtectorGuardOffset();
if (Offset >= 0 && Offset <= 32760 && Offset % 8 == 0) {
// ldr xN, [xN, #offset]
BuildMI(MBB, MI, DL, get(AArch64::LDRXui))
.addDef(Reg)
.addUse(Reg, RegState::Kill)
.addImm(Offset / 8);
} else if (Offset >= -256 && Offset <= 255) {
// ldur xN, [xN, #offset]
BuildMI(MBB, MI, DL, get(AArch64::LDURXi))
.addDef(Reg)
.addUse(Reg, RegState::Kill)
.addImm(Offset);
} else if (Offset >= -4095 && Offset <= 4095) {
if (Offset > 0) {
// add xN, xN, #offset
BuildMI(MBB, MI, DL, get(AArch64::ADDXri))
.addDef(Reg)
.addUse(Reg, RegState::Kill)
.addImm(Offset)
.addImm(0);
} else {
// sub xN, xN, #offset
BuildMI(MBB, MI, DL, get(AArch64::SUBXri))
.addDef(Reg)
.addUse(Reg, RegState::Kill)
.addImm(-Offset)
.addImm(0);
}
// ldr xN, [xN]
BuildMI(MBB, MI, DL, get(AArch64::LDRXui))
.addDef(Reg)
.addUse(Reg, RegState::Kill)
.addImm(0);
} else {
// Cases that are larger than +/- 4095 and not a multiple of 8, or larger
// than 23760.
// It might be nice to use AArch64::MOVi32imm here, which would get
// expanded in PreSched2 after PostRA, but our lone scratch Reg already
// contains the MRS result. findScratchNonCalleeSaveRegister() in
// AArch64FrameLowering might help us find such a scratch register
// though. If we failed to find a scratch register, we could emit a
// stream of add instructions to build up the immediate. Or, we could try
// to insert a AArch64::MOVi32imm before register allocation so that we
// didn't need to scavenge for a scratch register.
report_fatal_error("Unable to encode Stack Protector Guard Offset");
}
MBB.erase(MI);
return true;
}
const GlobalValue *GV =
cast<GlobalValue>((*MI.memoperands_begin())->getValue());
const TargetMachine &TM = MBB.getParent()->getTarget();
unsigned OpFlags = Subtarget.ClassifyGlobalReference(GV, TM);
const unsigned char MO_NC = AArch64II::MO_NC;
if ((OpFlags & AArch64II::MO_GOT) != 0) {
BuildMI(MBB, MI, DL, get(AArch64::LOADgot), Reg)
.addGlobalAddress(GV, 0, OpFlags);
if (Subtarget.isTargetILP32()) {
unsigned Reg32 = TRI->getSubReg(Reg, AArch64::sub_32);
BuildMI(MBB, MI, DL, get(AArch64::LDRWui))
.addDef(Reg32, RegState::Dead)
.addUse(Reg, RegState::Kill)
.addImm(0)
.addMemOperand(*MI.memoperands_begin())
.addDef(Reg, RegState::Implicit);
} else {
BuildMI(MBB, MI, DL, get(AArch64::LDRXui), Reg)
.addReg(Reg, RegState::Kill)
.addImm(0)
.addMemOperand(*MI.memoperands_begin());
}
} else if (TM.getCodeModel() == CodeModel::Large) {
assert(!Subtarget.isTargetILP32() && "how can large exist in ILP32?");
BuildMI(MBB, MI, DL, get(AArch64::MOVZXi), Reg)
.addGlobalAddress(GV, 0, AArch64II::MO_G0 | MO_NC)
.addImm(0);
BuildMI(MBB, MI, DL, get(AArch64::MOVKXi), Reg)
.addReg(Reg, RegState::Kill)
.addGlobalAddress(GV, 0, AArch64II::MO_G1 | MO_NC)
.addImm(16);
BuildMI(MBB, MI, DL, get(AArch64::MOVKXi), Reg)
.addReg(Reg, RegState::Kill)
.addGlobalAddress(GV, 0, AArch64II::MO_G2 | MO_NC)
.addImm(32);
BuildMI(MBB, MI, DL, get(AArch64::MOVKXi), Reg)
.addReg(Reg, RegState::Kill)
.addGlobalAddress(GV, 0, AArch64II::MO_G3)
.addImm(48);
BuildMI(MBB, MI, DL, get(AArch64::LDRXui), Reg)
.addReg(Reg, RegState::Kill)
.addImm(0)
.addMemOperand(*MI.memoperands_begin());
} else if (TM.getCodeModel() == CodeModel::Tiny) {
BuildMI(MBB, MI, DL, get(AArch64::ADR), Reg)
.addGlobalAddress(GV, 0, OpFlags);
} else {
BuildMI(MBB, MI, DL, get(AArch64::ADRP), Reg)
.addGlobalAddress(GV, 0, OpFlags | AArch64II::MO_PAGE);
unsigned char LoFlags = OpFlags | AArch64II::MO_PAGEOFF | MO_NC;
if (Subtarget.isTargetILP32()) {
unsigned Reg32 = TRI->getSubReg(Reg, AArch64::sub_32);
BuildMI(MBB, MI, DL, get(AArch64::LDRWui))
.addDef(Reg32, RegState::Dead)
.addUse(Reg, RegState::Kill)
.addGlobalAddress(GV, 0, LoFlags)
.addMemOperand(*MI.memoperands_begin())
.addDef(Reg, RegState::Implicit);
} else {
BuildMI(MBB, MI, DL, get(AArch64::LDRXui), Reg)
.addReg(Reg, RegState::Kill)
.addGlobalAddress(GV, 0, LoFlags)
.addMemOperand(*MI.memoperands_begin());
}
}
MBB.erase(MI);
return true;
}
// Return true if this instruction simply sets its single destination register
// to zero. This is equivalent to a register rename of the zero-register.
bool AArch64InstrInfo::isGPRZero(const MachineInstr &MI) {
switch (MI.getOpcode()) {
default:
break;
case AArch64::MOVZWi:
case AArch64::MOVZXi: // movz Rd, #0 (LSL #0)
if (MI.getOperand(1).isImm() && MI.getOperand(1).getImm() == 0) {
assert(MI.getDesc().getNumOperands() == 3 &&
MI.getOperand(2).getImm() == 0 && "invalid MOVZi operands");
return true;
}
break;
case AArch64::ANDWri: // and Rd, Rzr, #imm
return MI.getOperand(1).getReg() == AArch64::WZR;
case AArch64::ANDXri:
return MI.getOperand(1).getReg() == AArch64::XZR;
case TargetOpcode::COPY:
return MI.getOperand(1).getReg() == AArch64::WZR;
}
return false;
}
// Return true if this instruction simply renames a general register without
// modifying bits.
bool AArch64InstrInfo::isGPRCopy(const MachineInstr &MI) {
switch (MI.getOpcode()) {
default:
break;
case TargetOpcode::COPY: {
// GPR32 copies will by lowered to ORRXrs
Register DstReg = MI.getOperand(0).getReg();
return (AArch64::GPR32RegClass.contains(DstReg) ||
AArch64::GPR64RegClass.contains(DstReg));
}
case AArch64::ORRXrs: // orr Xd, Xzr, Xm (LSL #0)
if (MI.getOperand(1).getReg() == AArch64::XZR) {
assert(MI.getDesc().getNumOperands() == 4 &&
MI.getOperand(3).getImm() == 0 && "invalid ORRrs operands");
return true;
}
break;
case AArch64::ADDXri: // add Xd, Xn, #0 (LSL #0)
if (MI.getOperand(2).getImm() == 0) {
assert(MI.getDesc().getNumOperands() == 4 &&
MI.getOperand(3).getImm() == 0 && "invalid ADDXri operands");
return true;
}
break;
}
return false;
}
// Return true if this instruction simply renames a general register without
// modifying bits.
bool AArch64InstrInfo::isFPRCopy(const MachineInstr &MI) {
switch (MI.getOpcode()) {
default:
break;
case TargetOpcode::COPY: {
Register DstReg = MI.getOperand(0).getReg();
return AArch64::FPR128RegClass.contains(DstReg);
}
case AArch64::ORRv16i8:
if (MI.getOperand(1).getReg() == MI.getOperand(2).getReg()) {
assert(MI.getDesc().getNumOperands() == 3 && MI.getOperand(0).isReg() &&
"invalid ORRv16i8 operands");
return true;
}
break;
}
return false;
}
unsigned AArch64InstrInfo::isLoadFromStackSlot(const MachineInstr &MI,
int &FrameIndex) const {
switch (MI.getOpcode()) {
default:
break;
case AArch64::LDRWui:
case AArch64::LDRXui:
case AArch64::LDRBui:
case AArch64::LDRHui:
case AArch64::LDRSui:
case AArch64::LDRDui:
case AArch64::LDRQui:
case AArch64::LDR_PXI:
if (MI.getOperand(0).getSubReg() == 0 && MI.getOperand(1).isFI() &&
MI.getOperand(2).isImm() && MI.getOperand(2).getImm() == 0) {
FrameIndex = MI.getOperand(1).getIndex();
return MI.getOperand(0).getReg();
}
break;
}
return 0;
}
unsigned AArch64InstrInfo::isStoreToStackSlot(const MachineInstr &MI,
int &FrameIndex) const {
switch (MI.getOpcode()) {
default:
break;
case AArch64::STRWui:
case AArch64::STRXui:
case AArch64::STRBui:
case AArch64::STRHui:
case AArch64::STRSui:
case AArch64::STRDui:
case AArch64::STRQui:
case AArch64::STR_PXI:
if (MI.getOperand(0).getSubReg() == 0 && MI.getOperand(1).isFI() &&
MI.getOperand(2).isImm() && MI.getOperand(2).getImm() == 0) {
FrameIndex = MI.getOperand(1).getIndex();
return MI.getOperand(0).getReg();
}
break;
}
return 0;
}
/// Check all MachineMemOperands for a hint to suppress pairing.
bool AArch64InstrInfo::isLdStPairSuppressed(const MachineInstr &MI) {
return llvm::any_of(MI.memoperands(), [](MachineMemOperand *MMO) {
return MMO->getFlags() & MOSuppressPair;
});
}
/// Set a flag on the first MachineMemOperand to suppress pairing.
void AArch64InstrInfo::suppressLdStPair(MachineInstr &MI) {
if (MI.memoperands_empty())
return;
(*MI.memoperands_begin())->setFlags(MOSuppressPair);
}
/// Check all MachineMemOperands for a hint that the load/store is strided.
bool AArch64InstrInfo::isStridedAccess(const MachineInstr &MI) {
return llvm::any_of(MI.memoperands(), [](MachineMemOperand *MMO) {
return MMO->getFlags() & MOStridedAccess;
});
}
bool AArch64InstrInfo::hasUnscaledLdStOffset(unsigned Opc) {
switch (Opc) {
default:
return false;
case AArch64::STURSi:
case AArch64::STRSpre:
case AArch64::STURDi:
case AArch64::STRDpre:
case AArch64::STURQi:
case AArch64::STRQpre:
case AArch64::STURBBi:
case AArch64::STURHHi:
case AArch64::STURWi:
case AArch64::STRWpre:
case AArch64::STURXi:
case AArch64::STRXpre:
case AArch64::LDURSi:
case AArch64::LDRSpre:
case AArch64::LDURDi:
case AArch64::LDRDpre:
case AArch64::LDURQi:
case AArch64::LDRQpre:
case AArch64::LDURWi:
case AArch64::LDRWpre:
case AArch64::LDURXi:
case AArch64::LDRXpre:
case AArch64::LDRSWpre:
case AArch64::LDURSWi:
case AArch64::LDURHHi:
case AArch64::LDURBBi:
case AArch64::LDURSBWi:
case AArch64::LDURSHWi:
return true;
}
}
std::optional<unsigned> AArch64InstrInfo::getUnscaledLdSt(unsigned Opc) {
switch (Opc) {
default: return {};
case AArch64::PRFMui: return AArch64::PRFUMi;
case AArch64::LDRXui: return AArch64::LDURXi;
case AArch64::LDRWui: return AArch64::LDURWi;
case AArch64::LDRBui: return AArch64::LDURBi;
case AArch64::LDRHui: return AArch64::LDURHi;
case AArch64::LDRSui: return AArch64::LDURSi;
case AArch64::LDRDui: return AArch64::LDURDi;
case AArch64::LDRQui: return AArch64::LDURQi;
case AArch64::LDRBBui: return AArch64::LDURBBi;
case AArch64::LDRHHui: return AArch64::LDURHHi;
case AArch64::LDRSBXui: return AArch64::LDURSBXi;
case AArch64::LDRSBWui: return AArch64::LDURSBWi;
case AArch64::LDRSHXui: return AArch64::LDURSHXi;
case AArch64::LDRSHWui: return AArch64::LDURSHWi;
case AArch64::LDRSWui: return AArch64::LDURSWi;
case AArch64::STRXui: return AArch64::STURXi;
case AArch64::STRWui: return AArch64::STURWi;
case AArch64::STRBui: return AArch64::STURBi;
case AArch64::STRHui: return AArch64::STURHi;
case AArch64::STRSui: return AArch64::STURSi;
case AArch64::STRDui: return AArch64::STURDi;
case AArch64::STRQui: return AArch64::STURQi;
case AArch64::STRBBui: return AArch64::STURBBi;
case AArch64::STRHHui: return AArch64::STURHHi;
}
}
unsigned AArch64InstrInfo::getLoadStoreImmIdx(unsigned Opc) {
switch (Opc) {
default:
return 2;
case AArch64::LDPXi:
case AArch64::LDPDi:
case AArch64::STPXi:
case AArch64::STPDi:
case AArch64::LDNPXi:
case AArch64::LDNPDi:
case AArch64::STNPXi:
case AArch64::STNPDi:
case AArch64::LDPQi:
case AArch64::STPQi:
case AArch64::LDNPQi:
case AArch64::STNPQi:
case AArch64::LDPWi:
case AArch64::LDPSi:
case AArch64::STPWi:
case AArch64::STPSi:
case AArch64::LDNPWi:
case AArch64::LDNPSi:
case AArch64::STNPWi:
case AArch64::STNPSi:
case AArch64::LDG:
case AArch64::STGPi:
case AArch64::LD1B_IMM:
case AArch64::LD1B_H_IMM:
case AArch64::LD1B_S_IMM:
case AArch64::LD1B_D_IMM:
case AArch64::LD1SB_H_IMM:
case AArch64::LD1SB_S_IMM:
case AArch64::LD1SB_D_IMM:
case AArch64::LD1H_IMM:
case AArch64::LD1H_S_IMM:
case AArch64::LD1H_D_IMM:
case AArch64::LD1SH_S_IMM:
case AArch64::LD1SH_D_IMM:
case AArch64::LD1W_IMM:
case AArch64::LD1W_D_IMM:
case AArch64::LD1SW_D_IMM:
case AArch64::LD1D_IMM:
case AArch64::LD2B_IMM:
case AArch64::LD2H_IMM:
case AArch64::LD2W_IMM:
case AArch64::LD2D_IMM:
case AArch64::LD3B_IMM:
case AArch64::LD3H_IMM:
case AArch64::LD3W_IMM:
case AArch64::LD3D_IMM:
case AArch64::LD4B_IMM:
case AArch64::LD4H_IMM:
case AArch64::LD4W_IMM:
case AArch64::LD4D_IMM:
case AArch64::ST1B_IMM:
case AArch64::ST1B_H_IMM:
case AArch64::ST1B_S_IMM:
case AArch64::ST1B_D_IMM:
case AArch64::ST1H_IMM:
case AArch64::ST1H_S_IMM:
case AArch64::ST1H_D_IMM:
case AArch64::ST1W_IMM:
case AArch64::ST1W_D_IMM:
case AArch64::ST1D_IMM:
case AArch64::ST2B_IMM:
case AArch64::ST2H_IMM:
case AArch64::ST2W_IMM:
case AArch64::ST2D_IMM:
case AArch64::ST3B_IMM:
case AArch64::ST3H_IMM:
case AArch64::ST3W_IMM:
case AArch64::ST3D_IMM:
case AArch64::ST4B_IMM:
case AArch64::ST4H_IMM:
case AArch64::ST4W_IMM:
case AArch64::ST4D_IMM:
case AArch64::LD1RB_IMM:
case AArch64::LD1RB_H_IMM:
case AArch64::LD1RB_S_IMM:
case AArch64::LD1RB_D_IMM:
case AArch64::LD1RSB_H_IMM:
case AArch64::LD1RSB_S_IMM:
case AArch64::LD1RSB_D_IMM:
case AArch64::LD1RH_IMM:
case AArch64::LD1RH_S_IMM:
case AArch64::LD1RH_D_IMM:
case AArch64::LD1RSH_S_IMM:
case AArch64::LD1RSH_D_IMM:
case AArch64::LD1RW_IMM:
case AArch64::LD1RW_D_IMM:
case AArch64::LD1RSW_IMM:
case AArch64::LD1RD_IMM:
case AArch64::LDNT1B_ZRI:
case AArch64::LDNT1H_ZRI:
case AArch64::LDNT1W_ZRI:
case AArch64::LDNT1D_ZRI:
case AArch64::STNT1B_ZRI:
case AArch64::STNT1H_ZRI:
case AArch64::STNT1W_ZRI:
case AArch64::STNT1D_ZRI:
case AArch64::LDNF1B_IMM:
case AArch64::LDNF1B_H_IMM:
case AArch64::LDNF1B_S_IMM:
case AArch64::LDNF1B_D_IMM:
case AArch64::LDNF1SB_H_IMM:
case AArch64::LDNF1SB_S_IMM:
case AArch64::LDNF1SB_D_IMM:
case AArch64::LDNF1H_IMM:
case AArch64::LDNF1H_S_IMM:
case AArch64::LDNF1H_D_IMM:
case AArch64::LDNF1SH_S_IMM:
case AArch64::LDNF1SH_D_IMM:
case AArch64::LDNF1W_IMM:
case AArch64::LDNF1W_D_IMM:
case AArch64::LDNF1SW_D_IMM:
case AArch64::LDNF1D_IMM:
return 3;
case AArch64::ADDG:
case AArch64::STGi:
case AArch64::LDR_PXI:
case AArch64::STR_PXI:
return 2;
}
}
bool AArch64InstrInfo::isPairableLdStInst(const MachineInstr &MI) {
switch (MI.getOpcode()) {
default:
return false;
// Scaled instructions.
case AArch64::STRSui:
case AArch64::STRDui:
case AArch64::STRQui:
case AArch64::STRXui:
case AArch64::STRWui:
case AArch64::LDRSui:
case AArch64::LDRDui:
case AArch64::LDRQui:
case AArch64::LDRXui:
case AArch64::LDRWui:
case AArch64::LDRSWui:
// Unscaled instructions.
case AArch64::STURSi:
case AArch64::STRSpre:
case AArch64::STURDi:
case AArch64::STRDpre:
case AArch64::STURQi:
case AArch64::STRQpre:
case AArch64::STURWi:
case AArch64::STRWpre:
case AArch64::STURXi:
case AArch64::STRXpre:
case AArch64::LDURSi:
case AArch64::LDRSpre:
case AArch64::LDURDi:
case AArch64::LDRDpre:
case AArch64::LDURQi:
case AArch64::LDRQpre:
case AArch64::LDURWi:
case AArch64::LDRWpre:
case AArch64::LDURXi:
case AArch64::LDRXpre:
case AArch64::LDURSWi:
case AArch64::LDRSWpre:
return true;
}
}
unsigned AArch64InstrInfo::convertToFlagSettingOpc(unsigned Opc) {
switch (Opc) {
default:
llvm_unreachable("Opcode has no flag setting equivalent!");
// 32-bit cases:
case AArch64::ADDWri:
return AArch64::ADDSWri;
case AArch64::ADDWrr:
return AArch64::ADDSWrr;
case AArch64::ADDWrs:
return AArch64::ADDSWrs;
case AArch64::ADDWrx:
return AArch64::ADDSWrx;
case AArch64::ANDWri:
return AArch64::ANDSWri;
case AArch64::ANDWrr:
return AArch64::ANDSWrr;
case AArch64::ANDWrs:
return AArch64::ANDSWrs;
case AArch64::BICWrr:
return AArch64::BICSWrr;
case AArch64::BICWrs:
return AArch64::BICSWrs;
case AArch64::SUBWri:
return AArch64::SUBSWri;
case AArch64::SUBWrr:
return AArch64::SUBSWrr;
case AArch64::SUBWrs:
return AArch64::SUBSWrs;
case AArch64::SUBWrx:
return AArch64::SUBSWrx;
// 64-bit cases:
case AArch64::ADDXri:
return AArch64::ADDSXri;
case AArch64::ADDXrr:
return AArch64::ADDSXrr;
case AArch64::ADDXrs:
return AArch64::ADDSXrs;
case AArch64::ADDXrx:
return AArch64::ADDSXrx;
case AArch64::ANDXri:
return AArch64::ANDSXri;
case AArch64::ANDXrr:
return AArch64::ANDSXrr;
case AArch64::ANDXrs:
return AArch64::ANDSXrs;
case AArch64::BICXrr:
return AArch64::BICSXrr;
case AArch64::BICXrs:
return AArch64::BICSXrs;
case AArch64::SUBXri:
return AArch64::SUBSXri;
case AArch64::SUBXrr:
return AArch64::SUBSXrr;
case AArch64::SUBXrs:
return AArch64::SUBSXrs;
case AArch64::SUBXrx:
return AArch64::SUBSXrx;
// SVE instructions:
case AArch64::AND_PPzPP:
return AArch64::ANDS_PPzPP;
case AArch64::BIC_PPzPP:
return AArch64::BICS_PPzPP;
case AArch64::EOR_PPzPP:
return AArch64::EORS_PPzPP;
case AArch64::NAND_PPzPP:
return AArch64::NANDS_PPzPP;
case AArch64::NOR_PPzPP:
return AArch64::NORS_PPzPP;
case AArch64::ORN_PPzPP:
return AArch64::ORNS_PPzPP;
case AArch64::ORR_PPzPP:
return AArch64::ORRS_PPzPP;
case AArch64::BRKA_PPzP:
return AArch64::BRKAS_PPzP;
case AArch64::BRKPA_PPzPP:
return AArch64::BRKPAS_PPzPP;
case AArch64::BRKB_PPzP:
return AArch64::BRKBS_PPzP;
case AArch64::BRKPB_PPzPP:
return AArch64::BRKPBS_PPzPP;
case AArch64::BRKN_PPzP:
return AArch64::BRKNS_PPzP;
case AArch64::RDFFR_PPz:
return AArch64::RDFFRS_PPz;
case AArch64::PTRUE_B:
return AArch64::PTRUES_B;
}
}
// Is this a candidate for ld/st merging or pairing? For example, we don't
// touch volatiles or load/stores that have a hint to avoid pair formation.
bool AArch64InstrInfo::isCandidateToMergeOrPair(const MachineInstr &MI) const {
bool IsPreLdSt = isPreLdSt(MI);
// If this is a volatile load/store, don't mess with it.
if (MI.hasOrderedMemoryRef())
return false;
// Make sure this is a reg/fi+imm (as opposed to an address reloc).
// For Pre-inc LD/ST, the operand is shifted by one.
assert((MI.getOperand(IsPreLdSt ? 2 : 1).isReg() ||
MI.getOperand(IsPreLdSt ? 2 : 1).isFI()) &&
"Expected a reg or frame index operand.");
// For Pre-indexed addressing quadword instructions, the third operand is the
// immediate value.
bool IsImmPreLdSt = IsPreLdSt && MI.getOperand(3).isImm();
if (!MI.getOperand(2).isImm() && !IsImmPreLdSt)
return false;
// Can't merge/pair if the instruction modifies the base register.
// e.g., ldr x0, [x0]
// This case will never occur with an FI base.
// However, if the instruction is an LDR<S,D,Q,W,X,SW>pre or
// STR<S,D,Q,W,X>pre, it can be merged.
// For example:
// ldr q0, [x11, #32]!
// ldr q1, [x11, #16]
// to
// ldp q0, q1, [x11, #32]!
if (MI.getOperand(1).isReg() && !IsPreLdSt) {
Register BaseReg = MI.getOperand(1).getReg();
const TargetRegisterInfo *TRI = &getRegisterInfo();
if (MI.modifiesRegister(BaseReg, TRI))
return false;
}
// Check if this load/store has a hint to avoid pair formation.
// MachineMemOperands hints are set by the AArch64StorePairSuppress pass.
if (isLdStPairSuppressed(MI))
return false;
// Do not pair any callee-save store/reload instructions in the
// prologue/epilogue if the CFI information encoded the operations as separate
// instructions, as that will cause the size of the actual prologue to mismatch
// with the prologue size recorded in the Windows CFI.
const MCAsmInfo *MAI = MI.getMF()->getTarget().getMCAsmInfo();
bool NeedsWinCFI = MAI->usesWindowsCFI() &&
MI.getMF()->getFunction().needsUnwindTableEntry();
if (NeedsWinCFI && (MI.getFlag(MachineInstr::FrameSetup) ||
MI.getFlag(MachineInstr::FrameDestroy)))
return false;
// On some CPUs quad load/store pairs are slower than two single load/stores.
if (Subtarget.isPaired128Slow()) {
switch (MI.getOpcode()) {
default:
break;
case AArch64::LDURQi:
case AArch64::STURQi:
case AArch64::LDRQui:
case AArch64::STRQui:
return false;
}
}
return true;
}
bool AArch64InstrInfo::getMemOperandsWithOffsetWidth(
const MachineInstr &LdSt, SmallVectorImpl<const MachineOperand *> &BaseOps,
int64_t &Offset, bool &OffsetIsScalable, unsigned &Width,
const TargetRegisterInfo *TRI) const {
if (!LdSt.mayLoadOrStore())
return false;
const MachineOperand *BaseOp;
if (!getMemOperandWithOffsetWidth(LdSt, BaseOp, Offset, OffsetIsScalable,
Width, TRI))
return false;
BaseOps.push_back(BaseOp);
return true;
}
std::optional<ExtAddrMode>
AArch64InstrInfo::getAddrModeFromMemoryOp(const MachineInstr &MemI,
const TargetRegisterInfo *TRI) const {
const MachineOperand *Base; // Filled with the base operand of MI.
int64_t Offset; // Filled with the offset of MI.
bool OffsetIsScalable;
if (!getMemOperandWithOffset(MemI, Base, Offset, OffsetIsScalable, TRI))
return std::nullopt;
if (!Base->isReg())
return std