maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp

1864 lines
69 KiB
C++
Raw Blame History

//===-- ARMISelDAGToDAG.cpp - A dag to dag inst selector for ARM ----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines an instruction selector for the ARM target.
//
//===----------------------------------------------------------------------===//
#include "ARM.h"
#include "ARMAddressingModes.h"
#include "ARMConstantPoolValue.h"
#include "ARMISelLowering.h"
#include "ARMTargetMachine.h"
#include "llvm/CallingConv.h"
#include "llvm/Constants.h"
#include "llvm/DerivedTypes.h"
#include "llvm/Function.h"
#include "llvm/Intrinsics.h"
#include "llvm/LLVMContext.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/CodeGen/SelectionDAGISel.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
//===--------------------------------------------------------------------===//
/// ARMDAGToDAGISel - ARM specific code to select ARM machine
/// instructions for SelectionDAG operations.
///
namespace {
class ARMDAGToDAGISel : public SelectionDAGISel {
ARMBaseTargetMachine &TM;
/// Subtarget - Keep a pointer to the ARMSubtarget around so that we can
/// make the right decision when generating code for different targets.
const ARMSubtarget *Subtarget;
public:
explicit ARMDAGToDAGISel(ARMBaseTargetMachine &tm,
CodeGenOpt::Level OptLevel)
: SelectionDAGISel(tm, OptLevel), TM(tm),
Subtarget(&TM.getSubtarget<ARMSubtarget>()) {
}
virtual const char *getPassName() const {
return "ARM Instruction Selection";
}
/// getI32Imm - Return a target constant of type i32 with the specified
/// value.
inline SDValue getI32Imm(unsigned Imm) {
return CurDAG->getTargetConstant(Imm, MVT::i32);
}
SDNode *Select(SDValue Op);
virtual void InstructionSelect();
bool SelectShifterOperandReg(SDValue Op, SDValue N, SDValue &A,
SDValue &B, SDValue &C);
bool SelectAddrMode2(SDValue Op, SDValue N, SDValue &Base,
SDValue &Offset, SDValue &Opc);
bool SelectAddrMode2Offset(SDValue Op, SDValue N,
SDValue &Offset, SDValue &Opc);
bool SelectAddrMode3(SDValue Op, SDValue N, SDValue &Base,
SDValue &Offset, SDValue &Opc);
bool SelectAddrMode3Offset(SDValue Op, SDValue N,
SDValue &Offset, SDValue &Opc);
bool SelectAddrMode4(SDValue Op, SDValue N, SDValue &Addr,
SDValue &Mode);
bool SelectAddrMode5(SDValue Op, SDValue N, SDValue &Base,
SDValue &Offset);
bool SelectAddrMode6(SDValue Op, SDValue N, SDValue &Addr, SDValue &Update,
SDValue &Opc);
bool SelectAddrModePC(SDValue Op, SDValue N, SDValue &Offset,
SDValue &Label);
bool SelectThumbAddrModeRR(SDValue Op, SDValue N, SDValue &Base,
SDValue &Offset);
bool SelectThumbAddrModeRI5(SDValue Op, SDValue N, unsigned Scale,
SDValue &Base, SDValue &OffImm,
SDValue &Offset);
bool SelectThumbAddrModeS1(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffImm, SDValue &Offset);
bool SelectThumbAddrModeS2(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffImm, SDValue &Offset);
bool SelectThumbAddrModeS4(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffImm, SDValue &Offset);
bool SelectThumbAddrModeSP(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffImm);
bool SelectT2ShifterOperandReg(SDValue Op, SDValue N,
SDValue &BaseReg, SDValue &Opc);
bool SelectT2AddrModeImm12(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffImm);
bool SelectT2AddrModeImm8(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffImm);
bool SelectT2AddrModeImm8Offset(SDValue Op, SDValue N,
SDValue &OffImm);
bool SelectT2AddrModeImm8s4(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffImm);
bool SelectT2AddrModeSoReg(SDValue Op, SDValue N, SDValue &Base,
SDValue &OffReg, SDValue &ShImm);
// Include the pieces autogenerated from the target description.
#include "ARMGenDAGISel.inc"
private:
/// SelectARMIndexedLoad - Indexed (pre/post inc/dec) load matching code for
/// ARM.
SDNode *SelectARMIndexedLoad(SDValue Op);
SDNode *SelectT2IndexedLoad(SDValue Op);
/// SelectDYN_ALLOC - Select dynamic alloc for Thumb.
SDNode *SelectDYN_ALLOC(SDValue Op);
/// SelectVLD - Select NEON load intrinsics. NumVecs should
/// be 2, 3 or 4. The opcode arrays specify the instructions used for
/// loads of D registers and even subregs and odd subregs of Q registers.
/// For NumVecs == 2, QOpcodes1 is not used.
SDNode *SelectVLD(SDValue Op, unsigned NumVecs, unsigned *DOpcodes,
unsigned *QOpcodes0, unsigned *QOpcodes1);
/// SelectVST - Select NEON store intrinsics. NumVecs should
/// be 2, 3 or 4. The opcode arrays specify the instructions used for
/// stores of D registers and even subregs and odd subregs of Q registers.
/// For NumVecs == 2, QOpcodes1 is not used.
SDNode *SelectVST(SDValue Op, unsigned NumVecs, unsigned *DOpcodes,
unsigned *QOpcodes0, unsigned *QOpcodes1);
/// SelectVLDSTLane - Select NEON load/store lane intrinsics. NumVecs should
/// be 2, 3 or 4. The opcode arrays specify the instructions used for
/// load/store of D registers and even subregs and odd subregs of Q registers.
SDNode *SelectVLDSTLane(SDValue Op, bool IsLoad, unsigned NumVecs,
unsigned *DOpcodes, unsigned *QOpcodes0,
unsigned *QOpcodes1);
/// SelectV6T2BitfieldExtractOp - Select SBFX/UBFX instructions for ARM.
SDNode *SelectV6T2BitfieldExtractOp(SDValue Op, unsigned Opc);
/// SelectInlineAsmMemoryOperand - Implement addressing mode selection for
/// inline asm expressions.
virtual bool SelectInlineAsmMemoryOperand(const SDValue &Op,
char ConstraintCode,
std::vector<SDValue> &OutOps);
/// PairDRegs - Insert a pair of double registers into an implicit def to
/// form a quad register.
SDNode *PairDRegs(EVT VT, SDValue V0, SDValue V1);
};
}
/// isInt32Immediate - This method tests to see if the node is a 32-bit constant
/// operand. If so Imm will receive the 32-bit value.
static bool isInt32Immediate(SDNode *N, unsigned &Imm) {
if (N->getOpcode() == ISD::Constant && N->getValueType(0) == MVT::i32) {
Imm = cast<ConstantSDNode>(N)->getZExtValue();
return true;
}
return false;
}
// isInt32Immediate - This method tests to see if a constant operand.
// If so Imm will receive the 32 bit value.
static bool isInt32Immediate(SDValue N, unsigned &Imm) {
return isInt32Immediate(N.getNode(), Imm);
}
// isOpcWithIntImmediate - This method tests to see if the node is a specific
// opcode and that it has a immediate integer right operand.
// If so Imm will receive the 32 bit value.
static bool isOpcWithIntImmediate(SDNode *N, unsigned Opc, unsigned& Imm) {
return N->getOpcode() == Opc &&
isInt32Immediate(N->getOperand(1).getNode(), Imm);
}
void ARMDAGToDAGISel::InstructionSelect() {
DEBUG(BB->dump());
SelectRoot(*CurDAG);
CurDAG->RemoveDeadNodes();
}
bool ARMDAGToDAGISel::SelectShifterOperandReg(SDValue Op,
SDValue N,
SDValue &BaseReg,
SDValue &ShReg,
SDValue &Opc) {
ARM_AM::ShiftOpc ShOpcVal = ARM_AM::getShiftOpcForNode(N);
// Don't match base register only case. That is matched to a separate
// lower complexity pattern with explicit register operand.
if (ShOpcVal == ARM_AM::no_shift) return false;
BaseReg = N.getOperand(0);
unsigned ShImmVal = 0;
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
ShReg = CurDAG->getRegister(0, MVT::i32);
ShImmVal = RHS->getZExtValue() & 31;
} else {
ShReg = N.getOperand(1);
}
Opc = CurDAG->getTargetConstant(ARM_AM::getSORegOpc(ShOpcVal, ShImmVal),
MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrMode2(SDValue Op, SDValue N,
SDValue &Base, SDValue &Offset,
SDValue &Opc) {
if (N.getOpcode() == ISD::MUL) {
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
// X * [3,5,9] -> X + X * [2,4,8] etc.
int RHSC = (int)RHS->getZExtValue();
if (RHSC & 1) {
RHSC = RHSC & ~1;
ARM_AM::AddrOpc AddSub = ARM_AM::add;
if (RHSC < 0) {
AddSub = ARM_AM::sub;
RHSC = - RHSC;
}
if (isPowerOf2_32(RHSC)) {
unsigned ShAmt = Log2_32(RHSC);
Base = Offset = N.getOperand(0);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM2Opc(AddSub, ShAmt,
ARM_AM::lsl),
MVT::i32);
return true;
}
}
}
}
if (N.getOpcode() != ISD::ADD && N.getOpcode() != ISD::SUB) {
Base = N;
if (N.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(N)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
} else if (N.getOpcode() == ARMISD::Wrapper) {
Base = N.getOperand(0);
}
Offset = CurDAG->getRegister(0, MVT::i32);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM2Opc(ARM_AM::add, 0,
ARM_AM::no_shift),
MVT::i32);
return true;
}
// Match simple R +/- imm12 operands.
if (N.getOpcode() == ISD::ADD)
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if ((RHSC >= 0 && RHSC < 0x1000) ||
(RHSC < 0 && RHSC > -0x1000)) { // 12 bits.
Base = N.getOperand(0);
if (Base.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(Base)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
}
Offset = CurDAG->getRegister(0, MVT::i32);
ARM_AM::AddrOpc AddSub = ARM_AM::add;
if (RHSC < 0) {
AddSub = ARM_AM::sub;
RHSC = - RHSC;
}
Opc = CurDAG->getTargetConstant(ARM_AM::getAM2Opc(AddSub, RHSC,
ARM_AM::no_shift),
MVT::i32);
return true;
}
}
// Otherwise this is R +/- [possibly shifted] R
ARM_AM::AddrOpc AddSub = N.getOpcode() == ISD::ADD ? ARM_AM::add:ARM_AM::sub;
ARM_AM::ShiftOpc ShOpcVal = ARM_AM::getShiftOpcForNode(N.getOperand(1));
unsigned ShAmt = 0;
Base = N.getOperand(0);
Offset = N.getOperand(1);
if (ShOpcVal != ARM_AM::no_shift) {
// Check to see if the RHS of the shift is a constant, if not, we can't fold
// it.
if (ConstantSDNode *Sh =
dyn_cast<ConstantSDNode>(N.getOperand(1).getOperand(1))) {
ShAmt = Sh->getZExtValue();
Offset = N.getOperand(1).getOperand(0);
} else {
ShOpcVal = ARM_AM::no_shift;
}
}
// Try matching (R shl C) + (R).
if (N.getOpcode() == ISD::ADD && ShOpcVal == ARM_AM::no_shift) {
ShOpcVal = ARM_AM::getShiftOpcForNode(N.getOperand(0));
if (ShOpcVal != ARM_AM::no_shift) {
// Check to see if the RHS of the shift is a constant, if not, we can't
// fold it.
if (ConstantSDNode *Sh =
dyn_cast<ConstantSDNode>(N.getOperand(0).getOperand(1))) {
ShAmt = Sh->getZExtValue();
Offset = N.getOperand(0).getOperand(0);
Base = N.getOperand(1);
} else {
ShOpcVal = ARM_AM::no_shift;
}
}
}
Opc = CurDAG->getTargetConstant(ARM_AM::getAM2Opc(AddSub, ShAmt, ShOpcVal),
MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrMode2Offset(SDValue Op, SDValue N,
SDValue &Offset, SDValue &Opc) {
unsigned Opcode = Op.getOpcode();
ISD::MemIndexedMode AM = (Opcode == ISD::LOAD)
? cast<LoadSDNode>(Op)->getAddressingMode()
: cast<StoreSDNode>(Op)->getAddressingMode();
ARM_AM::AddrOpc AddSub = (AM == ISD::PRE_INC || AM == ISD::POST_INC)
? ARM_AM::add : ARM_AM::sub;
if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(N)) {
int Val = (int)C->getZExtValue();
if (Val >= 0 && Val < 0x1000) { // 12 bits.
Offset = CurDAG->getRegister(0, MVT::i32);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM2Opc(AddSub, Val,
ARM_AM::no_shift),
MVT::i32);
return true;
}
}
Offset = N;
ARM_AM::ShiftOpc ShOpcVal = ARM_AM::getShiftOpcForNode(N);
unsigned ShAmt = 0;
if (ShOpcVal != ARM_AM::no_shift) {
// Check to see if the RHS of the shift is a constant, if not, we can't fold
// it.
if (ConstantSDNode *Sh = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
ShAmt = Sh->getZExtValue();
Offset = N.getOperand(0);
} else {
ShOpcVal = ARM_AM::no_shift;
}
}
Opc = CurDAG->getTargetConstant(ARM_AM::getAM2Opc(AddSub, ShAmt, ShOpcVal),
MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrMode3(SDValue Op, SDValue N,
SDValue &Base, SDValue &Offset,
SDValue &Opc) {
if (N.getOpcode() == ISD::SUB) {
// X - C is canonicalize to X + -C, no need to handle it here.
Base = N.getOperand(0);
Offset = N.getOperand(1);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM3Opc(ARM_AM::sub, 0),MVT::i32);
return true;
}
if (N.getOpcode() != ISD::ADD) {
Base = N;
if (N.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(N)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
}
Offset = CurDAG->getRegister(0, MVT::i32);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM3Opc(ARM_AM::add, 0),MVT::i32);
return true;
}
// If the RHS is +/- imm8, fold into addr mode.
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if ((RHSC >= 0 && RHSC < 256) ||
(RHSC < 0 && RHSC > -256)) { // note -256 itself isn't allowed.
Base = N.getOperand(0);
if (Base.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(Base)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
}
Offset = CurDAG->getRegister(0, MVT::i32);
ARM_AM::AddrOpc AddSub = ARM_AM::add;
if (RHSC < 0) {
AddSub = ARM_AM::sub;
RHSC = - RHSC;
}
Opc = CurDAG->getTargetConstant(ARM_AM::getAM3Opc(AddSub, RHSC),MVT::i32);
return true;
}
}
Base = N.getOperand(0);
Offset = N.getOperand(1);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM3Opc(ARM_AM::add, 0), MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrMode3Offset(SDValue Op, SDValue N,
SDValue &Offset, SDValue &Opc) {
unsigned Opcode = Op.getOpcode();
ISD::MemIndexedMode AM = (Opcode == ISD::LOAD)
? cast<LoadSDNode>(Op)->getAddressingMode()
: cast<StoreSDNode>(Op)->getAddressingMode();
ARM_AM::AddrOpc AddSub = (AM == ISD::PRE_INC || AM == ISD::POST_INC)
? ARM_AM::add : ARM_AM::sub;
if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(N)) {
int Val = (int)C->getZExtValue();
if (Val >= 0 && Val < 256) {
Offset = CurDAG->getRegister(0, MVT::i32);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM3Opc(AddSub, Val), MVT::i32);
return true;
}
}
Offset = N;
Opc = CurDAG->getTargetConstant(ARM_AM::getAM3Opc(AddSub, 0), MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrMode4(SDValue Op, SDValue N,
SDValue &Addr, SDValue &Mode) {
Addr = N;
Mode = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrMode5(SDValue Op, SDValue N,
SDValue &Base, SDValue &Offset) {
if (N.getOpcode() != ISD::ADD) {
Base = N;
if (N.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(N)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
} else if (N.getOpcode() == ARMISD::Wrapper) {
Base = N.getOperand(0);
}
Offset = CurDAG->getTargetConstant(ARM_AM::getAM5Opc(ARM_AM::add, 0),
MVT::i32);
return true;
}
// If the RHS is +/- imm8, fold into addr mode.
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if ((RHSC & 3) == 0) { // The constant is implicitly multiplied by 4.
RHSC >>= 2;
if ((RHSC >= 0 && RHSC < 256) ||
(RHSC < 0 && RHSC > -256)) { // note -256 itself isn't allowed.
Base = N.getOperand(0);
if (Base.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(Base)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
}
ARM_AM::AddrOpc AddSub = ARM_AM::add;
if (RHSC < 0) {
AddSub = ARM_AM::sub;
RHSC = - RHSC;
}
Offset = CurDAG->getTargetConstant(ARM_AM::getAM5Opc(AddSub, RHSC),
MVT::i32);
return true;
}
}
}
Base = N;
Offset = CurDAG->getTargetConstant(ARM_AM::getAM5Opc(ARM_AM::add, 0),
MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrMode6(SDValue Op, SDValue N,
SDValue &Addr, SDValue &Update,
SDValue &Opc) {
Addr = N;
// Default to no writeback.
Update = CurDAG->getRegister(0, MVT::i32);
Opc = CurDAG->getTargetConstant(ARM_AM::getAM6Opc(false), MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectAddrModePC(SDValue Op, SDValue N,
SDValue &Offset, SDValue &Label) {
if (N.getOpcode() == ARMISD::PIC_ADD && N.hasOneUse()) {
Offset = N.getOperand(0);
SDValue N1 = N.getOperand(1);
Label = CurDAG->getTargetConstant(cast<ConstantSDNode>(N1)->getZExtValue(),
MVT::i32);
return true;
}
return false;
}
bool ARMDAGToDAGISel::SelectThumbAddrModeRR(SDValue Op, SDValue N,
SDValue &Base, SDValue &Offset){
// FIXME dl should come from the parent load or store, not the address
DebugLoc dl = Op.getDebugLoc();
if (N.getOpcode() != ISD::ADD) {
ConstantSDNode *NC = dyn_cast<ConstantSDNode>(N);
if (!NC || NC->getZExtValue() != 0)
return false;
Base = Offset = N;
return true;
}
Base = N.getOperand(0);
Offset = N.getOperand(1);
return true;
}
bool
ARMDAGToDAGISel::SelectThumbAddrModeRI5(SDValue Op, SDValue N,
unsigned Scale, SDValue &Base,
SDValue &OffImm, SDValue &Offset) {
if (Scale == 4) {
SDValue TmpBase, TmpOffImm;
if (SelectThumbAddrModeSP(Op, N, TmpBase, TmpOffImm))
return false; // We want to select tLDRspi / tSTRspi instead.
if (N.getOpcode() == ARMISD::Wrapper &&
N.getOperand(0).getOpcode() == ISD::TargetConstantPool)
return false; // We want to select tLDRpci instead.
}
if (N.getOpcode() != ISD::ADD) {
Base = (N.getOpcode() == ARMISD::Wrapper) ? N.getOperand(0) : N;
Offset = CurDAG->getRegister(0, MVT::i32);
OffImm = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
// Thumb does not have [sp, r] address mode.
RegisterSDNode *LHSR = dyn_cast<RegisterSDNode>(N.getOperand(0));
RegisterSDNode *RHSR = dyn_cast<RegisterSDNode>(N.getOperand(1));
if ((LHSR && LHSR->getReg() == ARM::SP) ||
(RHSR && RHSR->getReg() == ARM::SP)) {
Base = N;
Offset = CurDAG->getRegister(0, MVT::i32);
OffImm = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
// If the RHS is + imm5 * scale, fold into addr mode.
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if ((RHSC & (Scale-1)) == 0) { // The constant is implicitly multiplied.
RHSC /= Scale;
if (RHSC >= 0 && RHSC < 32) {
Base = N.getOperand(0);
Offset = CurDAG->getRegister(0, MVT::i32);
OffImm = CurDAG->getTargetConstant(RHSC, MVT::i32);
return true;
}
}
}
Base = N.getOperand(0);
Offset = N.getOperand(1);
OffImm = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectThumbAddrModeS1(SDValue Op, SDValue N,
SDValue &Base, SDValue &OffImm,
SDValue &Offset) {
return SelectThumbAddrModeRI5(Op, N, 1, Base, OffImm, Offset);
}
bool ARMDAGToDAGISel::SelectThumbAddrModeS2(SDValue Op, SDValue N,
SDValue &Base, SDValue &OffImm,
SDValue &Offset) {
return SelectThumbAddrModeRI5(Op, N, 2, Base, OffImm, Offset);
}
bool ARMDAGToDAGISel::SelectThumbAddrModeS4(SDValue Op, SDValue N,
SDValue &Base, SDValue &OffImm,
SDValue &Offset) {
return SelectThumbAddrModeRI5(Op, N, 4, Base, OffImm, Offset);
}
bool ARMDAGToDAGISel::SelectThumbAddrModeSP(SDValue Op, SDValue N,
SDValue &Base, SDValue &OffImm) {
if (N.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(N)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
OffImm = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
if (N.getOpcode() != ISD::ADD)
return false;
RegisterSDNode *LHSR = dyn_cast<RegisterSDNode>(N.getOperand(0));
if (N.getOperand(0).getOpcode() == ISD::FrameIndex ||
(LHSR && LHSR->getReg() == ARM::SP)) {
// If the RHS is + imm8 * scale, fold into addr mode.
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if ((RHSC & 3) == 0) { // The constant is implicitly multiplied.
RHSC >>= 2;
if (RHSC >= 0 && RHSC < 256) {
Base = N.getOperand(0);
if (Base.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(Base)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
}
OffImm = CurDAG->getTargetConstant(RHSC, MVT::i32);
return true;
}
}
}
}
return false;
}
bool ARMDAGToDAGISel::SelectT2ShifterOperandReg(SDValue Op, SDValue N,
SDValue &BaseReg,
SDValue &Opc) {
ARM_AM::ShiftOpc ShOpcVal = ARM_AM::getShiftOpcForNode(N);
// Don't match base register only case. That is matched to a separate
// lower complexity pattern with explicit register operand.
if (ShOpcVal == ARM_AM::no_shift) return false;
BaseReg = N.getOperand(0);
unsigned ShImmVal = 0;
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
ShImmVal = RHS->getZExtValue() & 31;
Opc = getI32Imm(ARM_AM::getSORegOpc(ShOpcVal, ShImmVal));
return true;
}
return false;
}
bool ARMDAGToDAGISel::SelectT2AddrModeImm12(SDValue Op, SDValue N,
SDValue &Base, SDValue &OffImm) {
// Match simple R + imm12 operands.
// Base only.
if (N.getOpcode() != ISD::ADD && N.getOpcode() != ISD::SUB) {
if (N.getOpcode() == ISD::FrameIndex) {
// Match frame index...
int FI = cast<FrameIndexSDNode>(N)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
OffImm = CurDAG->getTargetConstant(0, MVT::i32);
return true;
} else if (N.getOpcode() == ARMISD::Wrapper) {
Base = N.getOperand(0);
if (Base.getOpcode() == ISD::TargetConstantPool)
return false; // We want to select t2LDRpci instead.
} else
Base = N;
OffImm = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
if (SelectT2AddrModeImm8(Op, N, Base, OffImm))
// Let t2LDRi8 handle (R - imm8).
return false;
int RHSC = (int)RHS->getZExtValue();
if (N.getOpcode() == ISD::SUB)
RHSC = -RHSC;
if (RHSC >= 0 && RHSC < 0x1000) { // 12 bits (unsigned)
Base = N.getOperand(0);
if (Base.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(Base)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
}
OffImm = CurDAG->getTargetConstant(RHSC, MVT::i32);
return true;
}
}
// Base only.
Base = N;
OffImm = CurDAG->getTargetConstant(0, MVT::i32);
return true;
}
bool ARMDAGToDAGISel::SelectT2AddrModeImm8(SDValue Op, SDValue N,
SDValue &Base, SDValue &OffImm) {
// Match simple R - imm8 operands.
if (N.getOpcode() == ISD::ADD || N.getOpcode() == ISD::SUB) {
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getSExtValue();
if (N.getOpcode() == ISD::SUB)
RHSC = -RHSC;
if ((RHSC >= -255) && (RHSC < 0)) { // 8 bits (always negative)
Base = N.getOperand(0);
if (Base.getOpcode() == ISD::FrameIndex) {
int FI = cast<FrameIndexSDNode>(Base)->getIndex();
Base = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
}
OffImm = CurDAG->getTargetConstant(RHSC, MVT::i32);
return true;
}
}
}
return false;
}
bool ARMDAGToDAGISel::SelectT2AddrModeImm8Offset(SDValue Op, SDValue N,
SDValue &OffImm){
unsigned Opcode = Op.getOpcode();
ISD::MemIndexedMode AM = (Opcode == ISD::LOAD)
? cast<LoadSDNode>(Op)->getAddressingMode()
: cast<StoreSDNode>(Op)->getAddressingMode();
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N)) {
int RHSC = (int)RHS->getZExtValue();
if (RHSC >= 0 && RHSC < 0x100) { // 8 bits.
OffImm = ((AM == ISD::PRE_INC) || (AM == ISD::POST_INC))
? CurDAG->getTargetConstant(RHSC, MVT::i32)
: CurDAG->getTargetConstant(-RHSC, MVT::i32);
return true;
}
}
return false;
}
bool ARMDAGToDAGISel::SelectT2AddrModeImm8s4(SDValue Op, SDValue N,
SDValue &Base, SDValue &OffImm) {
if (N.getOpcode() == ISD::ADD) {
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if (((RHSC & 0x3) == 0) &&
((RHSC >= 0 && RHSC < 0x400) || (RHSC < 0 && RHSC > -0x400))) { // 8 bits.
Base = N.getOperand(0);
OffImm = CurDAG->getTargetConstant(RHSC, MVT::i32);
return true;
}
}
} else if (N.getOpcode() == ISD::SUB) {
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if (((RHSC & 0x3) == 0) && (RHSC >= 0 && RHSC < 0x400)) { // 8 bits.
Base = N.getOperand(0);
OffImm = CurDAG->getTargetConstant(-RHSC, MVT::i32);
return true;
}
}
}
return false;
}
bool ARMDAGToDAGISel::SelectT2AddrModeSoReg(SDValue Op, SDValue N,
SDValue &Base,
SDValue &OffReg, SDValue &ShImm) {
// (R - imm8) should be handled by t2LDRi8. The rest are handled by t2LDRi12.
if (N.getOpcode() != ISD::ADD)
return false;
// Leave (R + imm12) for t2LDRi12, (R - imm8) for t2LDRi8.
if (ConstantSDNode *RHS = dyn_cast<ConstantSDNode>(N.getOperand(1))) {
int RHSC = (int)RHS->getZExtValue();
if (RHSC >= 0 && RHSC < 0x1000) // 12 bits (unsigned)
return false;
else if (RHSC < 0 && RHSC >= -255) // 8 bits
return false;
}
// Look for (R + R) or (R + (R << [1,2,3])).
unsigned ShAmt = 0;
Base = N.getOperand(0);
OffReg = N.getOperand(1);
// Swap if it is ((R << c) + R).
ARM_AM::ShiftOpc ShOpcVal = ARM_AM::getShiftOpcForNode(OffReg);
if (ShOpcVal != ARM_AM::lsl) {
ShOpcVal = ARM_AM::getShiftOpcForNode(Base);
if (ShOpcVal == ARM_AM::lsl)
std::swap(Base, OffReg);
}
if (ShOpcVal == ARM_AM::lsl) {
// Check to see if the RHS of the shift is a constant, if not, we can't fold
// it.
if (ConstantSDNode *Sh = dyn_cast<ConstantSDNode>(OffReg.getOperand(1))) {
ShAmt = Sh->getZExtValue();
if (ShAmt >= 4) {
ShAmt = 0;
ShOpcVal = ARM_AM::no_shift;
} else
OffReg = OffReg.getOperand(0);
} else {
ShOpcVal = ARM_AM::no_shift;
}
}
ShImm = CurDAG->getTargetConstant(ShAmt, MVT::i32);
return true;
}
//===--------------------------------------------------------------------===//
/// getAL - Returns a ARMCC::AL immediate node.
static inline SDValue getAL(SelectionDAG *CurDAG) {
return CurDAG->getTargetConstant((uint64_t)ARMCC::AL, MVT::i32);
}
SDNode *ARMDAGToDAGISel::SelectARMIndexedLoad(SDValue Op) {
LoadSDNode *LD = cast<LoadSDNode>(Op);
ISD::MemIndexedMode AM = LD->getAddressingMode();
if (AM == ISD::UNINDEXED)
return NULL;
EVT LoadedVT = LD->getMemoryVT();
SDValue Offset, AMOpc;
bool isPre = (AM == ISD::PRE_INC) || (AM == ISD::PRE_DEC);
unsigned Opcode = 0;
bool Match = false;
if (LoadedVT == MVT::i32 &&
SelectAddrMode2Offset(Op, LD->getOffset(), Offset, AMOpc)) {
Opcode = isPre ? ARM::LDR_PRE : ARM::LDR_POST;
Match = true;
} else if (LoadedVT == MVT::i16 &&
SelectAddrMode3Offset(Op, LD->getOffset(), Offset, AMOpc)) {
Match = true;
Opcode = (LD->getExtensionType() == ISD::SEXTLOAD)
? (isPre ? ARM::LDRSH_PRE : ARM::LDRSH_POST)
: (isPre ? ARM::LDRH_PRE : ARM::LDRH_POST);
} else if (LoadedVT == MVT::i8 || LoadedVT == MVT::i1) {
if (LD->getExtensionType() == ISD::SEXTLOAD) {
if (SelectAddrMode3Offset(Op, LD->getOffset(), Offset, AMOpc)) {
Match = true;
Opcode = isPre ? ARM::LDRSB_PRE : ARM::LDRSB_POST;
}
} else {
if (SelectAddrMode2Offset(Op, LD->getOffset(), Offset, AMOpc)) {
Match = true;
Opcode = isPre ? ARM::LDRB_PRE : ARM::LDRB_POST;
}
}
}
if (Match) {
SDValue Chain = LD->getChain();
SDValue Base = LD->getBasePtr();
SDValue Ops[]= { Base, Offset, AMOpc, getAL(CurDAG),
CurDAG->getRegister(0, MVT::i32), Chain };
return CurDAG->getMachineNode(Opcode, Op.getDebugLoc(), MVT::i32, MVT::i32,
MVT::Other, Ops, 6);
}
return NULL;
}
SDNode *ARMDAGToDAGISel::SelectT2IndexedLoad(SDValue Op) {
LoadSDNode *LD = cast<LoadSDNode>(Op);
ISD::MemIndexedMode AM = LD->getAddressingMode();
if (AM == ISD::UNINDEXED)
return NULL;
EVT LoadedVT = LD->getMemoryVT();
bool isSExtLd = LD->getExtensionType() == ISD::SEXTLOAD;
SDValue Offset;
bool isPre = (AM == ISD::PRE_INC) || (AM == ISD::PRE_DEC);
unsigned Opcode = 0;
bool Match = false;
if (SelectT2AddrModeImm8Offset(Op, LD->getOffset(), Offset)) {
switch (LoadedVT.getSimpleVT().SimpleTy) {
case MVT::i32:
Opcode = isPre ? ARM::t2LDR_PRE : ARM::t2LDR_POST;
break;
case MVT::i16:
if (isSExtLd)
Opcode = isPre ? ARM::t2LDRSH_PRE : ARM::t2LDRSH_POST;
else
Opcode = isPre ? ARM::t2LDRH_PRE : ARM::t2LDRH_POST;
break;
case MVT::i8:
case MVT::i1:
if (isSExtLd)
Opcode = isPre ? ARM::t2LDRSB_PRE : ARM::t2LDRSB_POST;
else
Opcode = isPre ? ARM::t2LDRB_PRE : ARM::t2LDRB_POST;
break;
default:
return NULL;
}
Match = true;
}
if (Match) {
SDValue Chain = LD->getChain();
SDValue Base = LD->getBasePtr();
SDValue Ops[]= { Base, Offset, getAL(CurDAG),
CurDAG->getRegister(0, MVT::i32), Chain };
return CurDAG->getMachineNode(Opcode, Op.getDebugLoc(), MVT::i32, MVT::i32,
MVT::Other, Ops, 5);
}
return NULL;
}
SDNode *ARMDAGToDAGISel::SelectDYN_ALLOC(SDValue Op) {
SDNode *N = Op.getNode();
DebugLoc dl = N->getDebugLoc();
EVT VT = Op.getValueType();
SDValue Chain = Op.getOperand(0);
SDValue Size = Op.getOperand(1);
SDValue Align = Op.getOperand(2);
SDValue SP = CurDAG->getRegister(ARM::SP, MVT::i32);
int32_t AlignVal = cast<ConstantSDNode>(Align)->getSExtValue();
if (AlignVal < 0)
// We need to align the stack. Use Thumb1 tAND which is the only thumb
// instruction that can read and write SP. This matches to a pseudo
// instruction that has a chain to ensure the result is written back to
// the stack pointer.
SP = SDValue(CurDAG->getMachineNode(ARM::tANDsp, dl, VT, SP, Align), 0);
bool isC = isa<ConstantSDNode>(Size);
uint32_t C = isC ? cast<ConstantSDNode>(Size)->getZExtValue() : ~0UL;
// Handle the most common case for both Thumb1 and Thumb2:
// tSUBspi - immediate is between 0 ... 508 inclusive.
if (C <= 508 && ((C & 3) == 0))
// FIXME: tSUBspi encode scale 4 implicitly.
return CurDAG->SelectNodeTo(N, ARM::tSUBspi_, VT, MVT::Other, SP,
CurDAG->getTargetConstant(C/4, MVT::i32),
Chain);
if (Subtarget->isThumb1Only()) {
// Use tADDspr since Thumb1 does not have a sub r, sp, r. ARMISelLowering
// should have negated the size operand already. FIXME: We can't insert
// new target independent node at this stage so we are forced to negate
// it earlier. Is there a better solution?
return CurDAG->SelectNodeTo(N, ARM::tADDspr_, VT, MVT::Other, SP, Size,
Chain);
} else if (Subtarget->isThumb2()) {
if (isC && Predicate_t2_so_imm(Size.getNode())) {
// t2SUBrSPi
SDValue Ops[] = { SP, CurDAG->getTargetConstant(C, MVT::i32), Chain };
return CurDAG->SelectNodeTo(N, ARM::t2SUBrSPi_, VT, MVT::Other, Ops, 3);
} else if (isC && Predicate_imm0_4095(Size.getNode())) {
// t2SUBrSPi12
SDValue Ops[] = { SP, CurDAG->getTargetConstant(C, MVT::i32), Chain };
return CurDAG->SelectNodeTo(N, ARM::t2SUBrSPi12_, VT, MVT::Other, Ops, 3);
} else {
// t2SUBrSPs
SDValue Ops[] = { SP, Size,
getI32Imm(ARM_AM::getSORegOpc(ARM_AM::lsl,0)), Chain };
return CurDAG->SelectNodeTo(N, ARM::t2SUBrSPs_, VT, MVT::Other, Ops, 4);
}
}
// FIXME: Add ADD / SUB sp instructions for ARM.
return 0;
}
/// PairDRegs - Insert a pair of double registers into an implicit def to
/// form a quad register.
SDNode *ARMDAGToDAGISel::PairDRegs(EVT VT, SDValue V0, SDValue V1) {
DebugLoc dl = V0.getNode()->getDebugLoc();
SDValue Undef =
SDValue(CurDAG->getMachineNode(TargetInstrInfo::IMPLICIT_DEF, dl, VT), 0);
SDValue SubReg0 = CurDAG->getTargetConstant(ARM::DSUBREG_0, MVT::i32);
SDValue SubReg1 = CurDAG->getTargetConstant(ARM::DSUBREG_1, MVT::i32);
SDNode *Pair = CurDAG->getMachineNode(TargetInstrInfo::INSERT_SUBREG, dl,
VT, Undef, V0, SubReg0);
return CurDAG->getMachineNode(TargetInstrInfo::INSERT_SUBREG, dl,
VT, SDValue(Pair, 0), V1, SubReg1);
}
/// GetNEONSubregVT - Given a type for a 128-bit NEON vector, return the type
/// for a 64-bit subregister of the vector.
static EVT GetNEONSubregVT(EVT VT) {
switch (VT.getSimpleVT().SimpleTy) {
default: llvm_unreachable("unhandled NEON type");
case MVT::v16i8: return MVT::v8i8;
case MVT::v8i16: return MVT::v4i16;
case MVT::v4f32: return MVT::v2f32;
case MVT::v4i32: return MVT::v2i32;
case MVT::v2i64: return MVT::v1i64;
}
}
SDNode *ARMDAGToDAGISel::SelectVLD(SDValue Op, unsigned NumVecs,
unsigned *DOpcodes, unsigned *QOpcodes0,
unsigned *QOpcodes1) {
assert(NumVecs >=2 && NumVecs <= 4 && "VLD NumVecs out-of-range");
SDNode *N = Op.getNode();
DebugLoc dl = N->getDebugLoc();
SDValue MemAddr, MemUpdate, MemOpc;
if (!SelectAddrMode6(Op, N->getOperand(2), MemAddr, MemUpdate, MemOpc))
return NULL;
SDValue Chain = N->getOperand(0);
EVT VT = N->getValueType(0);
bool is64BitVector = VT.is64BitVector();
unsigned OpcodeIndex;
switch (VT.getSimpleVT().SimpleTy) {
default: llvm_unreachable("unhandled vld type");
// Double-register operations:
case MVT::v8i8: OpcodeIndex = 0; break;
case MVT::v4i16: OpcodeIndex = 1; break;
case MVT::v2f32:
case MVT::v2i32: OpcodeIndex = 2; break;
case MVT::v1i64: OpcodeIndex = 3; break;
// Quad-register operations:
case MVT::v16i8: OpcodeIndex = 0; break;
case MVT::v8i16: OpcodeIndex = 1; break;
case MVT::v4f32:
case MVT::v4i32: OpcodeIndex = 2; break;
}
if (is64BitVector) {
unsigned Opc = DOpcodes[OpcodeIndex];
const SDValue Ops[] = { MemAddr, MemUpdate, MemOpc, Chain };
std::vector<EVT> ResTys(NumVecs, VT);
ResTys.push_back(MVT::Other);
return CurDAG->getMachineNode(Opc, dl, ResTys, Ops, 4);
}
EVT RegVT = GetNEONSubregVT(VT);
if (NumVecs == 2) {
// Quad registers are directly supported for VLD2,
// loading 2 pairs of D regs.
unsigned Opc = QOpcodes0[OpcodeIndex];
const SDValue Ops[] = { MemAddr, MemUpdate, MemOpc, Chain };
std::vector<EVT> ResTys(4, VT);
ResTys.push_back(MVT::Other);
SDNode *VLd = CurDAG->getMachineNode(Opc, dl, ResTys, Ops, 4);
Chain = SDValue(VLd, 4);
// Combine the even and odd subregs to produce the result.
for (unsigned Vec = 0; Vec < NumVecs; ++Vec) {
SDNode *Q = PairDRegs(VT, SDValue(VLd, 2*Vec), SDValue(VLd, 2*Vec+1));
ReplaceUses(SDValue(N, Vec), SDValue(Q, 0));
}
} else {
// Otherwise, quad registers are loaded with two separate instructions,
// where one loads the even registers and the other loads the odd registers.
// Enable writeback to the address register.
MemOpc = CurDAG->getTargetConstant(ARM_AM::getAM6Opc(true), MVT::i32);
std::vector<EVT> ResTys(NumVecs, RegVT);
ResTys.push_back(MemAddr.getValueType());
ResTys.push_back(MVT::Other);
// Load the even subregs.
unsigned Opc = QOpcodes0[OpcodeIndex];
const SDValue OpsA[] = { MemAddr, MemUpdate, MemOpc, Chain };
SDNode *VLdA = CurDAG->getMachineNode(Opc, dl, ResTys, OpsA, 4);
Chain = SDValue(VLdA, NumVecs+1);
// Load the odd subregs.
Opc = QOpcodes1[OpcodeIndex];
const SDValue OpsB[] = { SDValue(VLdA, NumVecs), MemUpdate, MemOpc, Chain };
SDNode *VLdB = CurDAG->getMachineNode(Opc, dl, ResTys, OpsB, 4);
Chain = SDValue(VLdB, NumVecs+1);
// Combine the even and odd subregs to produce the result.
for (unsigned Vec = 0; Vec < NumVecs; ++Vec) {
SDNode *Q = PairDRegs(VT, SDValue(VLdA, Vec), SDValue(VLdB, Vec));
ReplaceUses(SDValue(N, Vec), SDValue(Q, 0));
}
}
ReplaceUses(SDValue(N, NumVecs), Chain);
return NULL;
}
SDNode *ARMDAGToDAGISel::SelectVST(SDValue Op, unsigned NumVecs,
unsigned *DOpcodes, unsigned *QOpcodes0,
unsigned *QOpcodes1) {
assert(NumVecs >=2 && NumVecs <= 4 && "VST NumVecs out-of-range");
SDNode *N = Op.getNode();
DebugLoc dl = N->getDebugLoc();
SDValue MemAddr, MemUpdate, MemOpc;
if (!SelectAddrMode6(Op, N->getOperand(2), MemAddr, MemUpdate, MemOpc))
return NULL;
SDValue Chain = N->getOperand(0);
EVT VT = N->getOperand(3).getValueType();
bool is64BitVector = VT.is64BitVector();
unsigned OpcodeIndex;
switch (VT.getSimpleVT().SimpleTy) {
default: llvm_unreachable("unhandled vst type");
// Double-register operations:
case MVT::v8i8: OpcodeIndex = 0; break;
case MVT::v4i16: OpcodeIndex = 1; break;
case MVT::v2f32:
case MVT::v2i32: OpcodeIndex = 2; break;
case MVT::v1i64: OpcodeIndex = 3; break;
// Quad-register operations:
case MVT::v16i8: OpcodeIndex = 0; break;
case MVT::v8i16: OpcodeIndex = 1; break;
case MVT::v4f32:
case MVT::v4i32: OpcodeIndex = 2; break;
}
SmallVector<SDValue, 8> Ops;
Ops.push_back(MemAddr);
Ops.push_back(MemUpdate);
Ops.push_back(MemOpc);
if (is64BitVector) {
unsigned Opc = DOpcodes[OpcodeIndex];
for (unsigned Vec = 0; Vec < NumVecs; ++Vec)
Ops.push_back(N->getOperand(Vec+3));
Ops.push_back(Chain);
return CurDAG->getMachineNode(Opc, dl, MVT::Other, Ops.data(), NumVecs+4);
}
EVT RegVT = GetNEONSubregVT(VT);
if (NumVecs == 2) {
// Quad registers are directly supported for VST2,
// storing 2 pairs of D regs.
unsigned Opc = QOpcodes0[OpcodeIndex];
for (unsigned Vec = 0; Vec < NumVecs; ++Vec) {
Ops.push_back(CurDAG->getTargetExtractSubreg(ARM::DSUBREG_0, dl, RegVT,
N->getOperand(Vec+3)));
Ops.push_back(CurDAG->getTargetExtractSubreg(ARM::DSUBREG_1, dl, RegVT,
N->getOperand(Vec+3)));
}
Ops.push_back(Chain);
return CurDAG->getMachineNode(Opc, dl, MVT::Other, Ops.data(), 8);
}
// Otherwise, quad registers are stored with two separate instructions,
// where one stores the even registers and the other stores the odd registers.
// Enable writeback to the address register.
MemOpc = CurDAG->getTargetConstant(ARM_AM::getAM6Opc(true), MVT::i32);
// Store the even subregs.
for (unsigned Vec = 0; Vec < NumVecs; ++Vec)
Ops.push_back(CurDAG->getTargetExtractSubreg(ARM::DSUBREG_0, dl, RegVT,
N->getOperand(Vec+3)));
Ops.push_back(Chain);
unsigned Opc = QOpcodes0[OpcodeIndex];
SDNode *VStA = CurDAG->getMachineNode(Opc, dl, MemAddr.getValueType(),
MVT::Other, Ops.data(), NumVecs+4);
Chain = SDValue(VStA, 1);
// Store the odd subregs.
Ops[0] = SDValue(VStA, 0); // MemAddr
for (unsigned Vec = 0; Vec < NumVecs; ++Vec)
Ops[Vec+3] = CurDAG->getTargetExtractSubreg(ARM::DSUBREG_1, dl, RegVT,
N->getOperand(Vec+3));
Ops[NumVecs+3] = Chain;
Opc = QOpcodes1[OpcodeIndex];
SDNode *VStB = CurDAG->getMachineNode(Opc, dl, MemAddr.getValueType(),
MVT::Other, Ops.data(), NumVecs+4);
Chain = SDValue(VStB, 1);
ReplaceUses(SDValue(N, 0), Chain);
return NULL;
}
SDNode *ARMDAGToDAGISel::SelectVLDSTLane(SDValue Op, bool IsLoad,
unsigned NumVecs, unsigned *DOpcodes,
unsigned *QOpcodes0,
unsigned *QOpcodes1) {
assert(NumVecs >=2 && NumVecs <= 4 && "VLDSTLane NumVecs out-of-range");
SDNode *N = Op.getNode();
DebugLoc dl = N->getDebugLoc();
SDValue MemAddr, MemUpdate, MemOpc;
if (!SelectAddrMode6(Op, N->getOperand(2), MemAddr, MemUpdate, MemOpc))
return NULL;
SDValue Chain = N->getOperand(0);
unsigned Lane =
cast<ConstantSDNode>(N->getOperand(NumVecs+3))->getZExtValue();
EVT VT = IsLoad ? N->getValueType(0) : N->getOperand(3).getValueType();
bool is64BitVector = VT.is64BitVector();
// Quad registers are handled by load/store of subregs. Find the subreg info.
unsigned NumElts = 0;
int SubregIdx = 0;
EVT RegVT = VT;
if (!is64BitVector) {
RegVT = GetNEONSubregVT(VT);
NumElts = RegVT.getVectorNumElements();
SubregIdx = (Lane < NumElts) ? ARM::DSUBREG_0 : ARM::DSUBREG_1;
}
unsigned OpcodeIndex;
switch (VT.getSimpleVT().SimpleTy) {
default: llvm_unreachable("unhandled vld/vst lane type");
// Double-register operations:
case MVT::v8i8: OpcodeIndex = 0; break;
case MVT::v4i16: OpcodeIndex = 1; break;
case MVT::v2f32:
case MVT::v2i32: OpcodeIndex = 2; break;
// Quad-register operations:
case MVT::v8i16: OpcodeIndex = 0; break;
case MVT::v4f32:
case MVT::v4i32: OpcodeIndex = 1; break;
}
SmallVector<SDValue, 9> Ops;
Ops.push_back(MemAddr);
Ops.push_back(MemUpdate);
Ops.push_back(MemOpc);
unsigned Opc = 0;
if (is64BitVector) {
Opc = DOpcodes[OpcodeIndex];
for (unsigned Vec = 0; Vec < NumVecs; ++Vec)
Ops.push_back(N->getOperand(Vec+3));
} else {
// Check if this is loading the even or odd subreg of a Q register.
if (Lane < NumElts) {
Opc = QOpcodes0[OpcodeIndex];
} else {
Lane -= NumElts;
Opc = QOpcodes1[OpcodeIndex];
}
// Extract the subregs of the input vector.
for (unsigned Vec = 0; Vec < NumVecs; ++Vec)
Ops.push_back(CurDAG->getTargetExtractSubreg(SubregIdx, dl, RegVT,
N->getOperand(Vec+3)));
}
Ops.push_back(getI32Imm(Lane));
Ops.push_back(Chain);
if (!IsLoad)
return CurDAG->getMachineNode(Opc, dl, MVT::Other, Ops.data(), NumVecs+5);
std::vector<EVT> ResTys(NumVecs, RegVT);
ResTys.push_back(MVT::Other);
SDNode *VLdLn =
CurDAG->getMachineNode(Opc, dl, ResTys, Ops.data(), NumVecs+5);
// For a 64-bit vector load to D registers, nothing more needs to be done.
if (is64BitVector)
return VLdLn;
// For 128-bit vectors, take the 64-bit results of the load and insert them
// as subregs into the result.
for (unsigned Vec = 0; Vec < NumVecs; ++Vec) {
SDValue QuadVec = CurDAG->getTargetInsertSubreg(SubregIdx, dl, VT,
N->getOperand(Vec+3),
SDValue(VLdLn, Vec));
ReplaceUses(SDValue(N, Vec), QuadVec);
}
Chain = SDValue(VLdLn, NumVecs);
ReplaceUses(SDValue(N, NumVecs), Chain);
return NULL;
}
SDNode *ARMDAGToDAGISel::SelectV6T2BitfieldExtractOp(SDValue Op,
unsigned Opc) {
if (!Subtarget->hasV6T2Ops())
return NULL;
unsigned Shl_imm = 0;
if (isOpcWithIntImmediate(Op.getOperand(0).getNode(), ISD::SHL, Shl_imm)){
assert(Shl_imm > 0 && Shl_imm < 32 && "bad amount in shift node!");
unsigned Srl_imm = 0;
if (isInt32Immediate(Op.getOperand(1), Srl_imm)) {
assert(Srl_imm > 0 && Srl_imm < 32 && "bad amount in shift node!");
unsigned Width = 32 - Srl_imm;
int LSB = Srl_imm - Shl_imm;
if ((LSB + Width) > 32)
return NULL;
SDValue Reg0 = CurDAG->getRegister(0, MVT::i32);
SDValue Ops[] = { Op.getOperand(0).getOperand(0),
CurDAG->getTargetConstant(LSB, MVT::i32),
CurDAG->getTargetConstant(Width, MVT::i32),
getAL(CurDAG), Reg0 };
return CurDAG->SelectNodeTo(Op.getNode(), Opc, MVT::i32, Ops, 5);
}
}
return NULL;
}
SDNode *ARMDAGToDAGISel::Select(SDValue Op) {
SDNode *N = Op.getNode();
DebugLoc dl = N->getDebugLoc();
if (N->isMachineOpcode())
return NULL; // Already selected.
switch (N->getOpcode()) {
default: break;
case ISD::Constant: {
unsigned Val = cast<ConstantSDNode>(N)->getZExtValue();
bool UseCP = true;
if (Subtarget->hasThumb2())
// Thumb2-aware targets have the MOVT instruction, so all immediates can
// be done with MOV + MOVT, at worst.
UseCP = 0;
else {
if (Subtarget->isThumb()) {
UseCP = (Val > 255 && // MOV
~Val > 255 && // MOV + MVN
!ARM_AM::isThumbImmShiftedVal(Val)); // MOV + LSL
} else
UseCP = (ARM_AM::getSOImmVal(Val) == -1 && // MOV
ARM_AM::getSOImmVal(~Val) == -1 && // MVN
!ARM_AM::isSOImmTwoPartVal(Val)); // two instrs.
}
if (UseCP) {
SDValue CPIdx =
CurDAG->getTargetConstantPool(ConstantInt::get(
Type::getInt32Ty(*CurDAG->getContext()), Val),
TLI.getPointerTy());
SDNode *ResNode;
if (Subtarget->isThumb1Only()) {
SDValue Pred = CurDAG->getTargetConstant(0xEULL, MVT::i32);
SDValue PredReg = CurDAG->getRegister(0, MVT::i32);
SDValue Ops[] = { CPIdx, Pred, PredReg, CurDAG->getEntryNode() };
ResNode = CurDAG->getMachineNode(ARM::tLDRcp, dl, MVT::i32, MVT::Other,
Ops, 4);
} else {
SDValue Ops[] = {
CPIdx,
CurDAG->getRegister(0, MVT::i32),
CurDAG->getTargetConstant(0, MVT::i32),
getAL(CurDAG),
CurDAG->getRegister(0, MVT::i32),
CurDAG->getEntryNode()
};
ResNode=CurDAG->getMachineNode(ARM::LDRcp, dl, MVT::i32, MVT::Other,
Ops, 6);
}
ReplaceUses(Op, SDValue(ResNode, 0));
return NULL;
}
// Other cases are autogenerated.
break;
}
case ISD::FrameIndex: {
// Selects to ADDri FI, 0 which in turn will become ADDri SP, imm.
int FI = cast<FrameIndexSDNode>(N)->getIndex();
SDValue TFI = CurDAG->getTargetFrameIndex(FI, TLI.getPointerTy());
if (Subtarget->isThumb1Only()) {
return CurDAG->SelectNodeTo(N, ARM::tADDrSPi, MVT::i32, TFI,
CurDAG->getTargetConstant(0, MVT::i32));
} else {
unsigned Opc = ((Subtarget->isThumb() && Subtarget->hasThumb2()) ?
ARM::t2ADDri : ARM::ADDri);
SDValue Ops[] = { TFI, CurDAG->getTargetConstant(0, MVT::i32),
getAL(CurDAG), CurDAG->getRegister(0, MVT::i32),
CurDAG->getRegister(0, MVT::i32) };
return CurDAG->SelectNodeTo(N, Opc, MVT::i32, Ops, 5);
}
}
case ARMISD::DYN_ALLOC:
return SelectDYN_ALLOC(Op);
case ISD::SRL:
if (SDNode *I = SelectV6T2BitfieldExtractOp(Op,
Subtarget->isThumb() ? ARM::t2UBFX : ARM::UBFX))
return I;
break;
case ISD::SRA:
if (SDNode *I = SelectV6T2BitfieldExtractOp(Op,
Subtarget->isThumb() ? ARM::t2SBFX : ARM::SBFX))
return I;
break;
case ISD::MUL:
if (Subtarget->isThumb1Only())
break;
if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(Op.getOperand(1))) {
unsigned RHSV = C->getZExtValue();
if (!RHSV) break;
if (isPowerOf2_32(RHSV-1)) { // 2^n+1?
unsigned ShImm = Log2_32(RHSV-1);
if (ShImm >= 32)
break;
SDValue V = Op.getOperand(0);
ShImm = ARM_AM::getSORegOpc(ARM_AM::lsl, ShImm);
SDValue ShImmOp = CurDAG->getTargetConstant(ShImm, MVT::i32);
SDValue Reg0 = CurDAG->getRegister(0, MVT::i32);
if (Subtarget->isThumb()) {
SDValue Ops[] = { V, V, ShImmOp, getAL(CurDAG), Reg0, Reg0 };
return CurDAG->SelectNodeTo(N, ARM::t2ADDrs, MVT::i32, Ops, 6);
} else {
SDValue Ops[] = { V, V, Reg0, ShImmOp, getAL(CurDAG), Reg0, Reg0 };
return CurDAG->SelectNodeTo(N, ARM::ADDrs, MVT::i32, Ops, 7);
}
}
if (isPowerOf2_32(RHSV+1)) { // 2^n-1?
unsigned ShImm = Log2_32(RHSV+1);
if (ShImm >= 32)
break;
SDValue V = Op.getOperand(0);
ShImm = ARM_AM::getSORegOpc(ARM_AM::lsl, ShImm);
SDValue ShImmOp = CurDAG->getTargetConstant(ShImm, MVT::i32);
SDValue Reg0 = CurDAG->getRegister(0, MVT::i32);
if (Subtarget->isThumb()) {
SDValue Ops[] = { V, V, ShImmOp, getAL(CurDAG), Reg0 };
return CurDAG->SelectNodeTo(N, ARM::t2RSBrs, MVT::i32, Ops, 5);
} else {
SDValue Ops[] = { V, V, Reg0, ShImmOp, getAL(CurDAG), Reg0, Reg0 };
return CurDAG->SelectNodeTo(N, ARM::RSBrs, MVT::i32, Ops, 7);
}
}
}
break;
case ISD::AND: {
// (and (or x, c2), c1) and top 16-bits of c1 and c2 match, lower 16-bits
// of c1 are 0xffff, and lower 16-bit of c2 are 0. That is, the top 16-bits
// are entirely contributed by c2 and lower 16-bits are entirely contributed
// by x. That's equal to (or (and x, 0xffff), (and c1, 0xffff0000)).
// Select it to: "movt x, ((c1 & 0xffff) >> 16)
EVT VT = Op.getValueType();
if (VT != MVT::i32)
break;
unsigned Opc = (Subtarget->isThumb() && Subtarget->hasThumb2())
? ARM::t2MOVTi16
: (Subtarget->hasV6T2Ops() ? ARM::MOVTi16 : 0);
if (!Opc)
break;
SDValue N0 = Op.getOperand(0), N1 = Op.getOperand(1);
ConstantSDNode *N1C = dyn_cast<ConstantSDNode>(N1);
if (!N1C)
break;
if (N0.getOpcode() == ISD::OR && N0.getNode()->hasOneUse()) {
SDValue N2 = N0.getOperand(1);
ConstantSDNode *N2C = dyn_cast<ConstantSDNode>(N2);
if (!N2C)
break;
unsigned N1CVal = N1C->getZExtValue();
unsigned N2CVal = N2C->getZExtValue();
if ((N1CVal & 0xffff0000U) == (N2CVal & 0xffff0000U) &&
(N1CVal & 0xffffU) == 0xffffU &&
(N2CVal & 0xffffU) == 0x0U) {
SDValue Imm16 = CurDAG->getTargetConstant((N2CVal & 0xFFFF0000U) >> 16,
MVT::i32);
SDValue Ops[] = { N0.getOperand(0), Imm16,
getAL(CurDAG), CurDAG->getRegister(0, MVT::i32) };
return CurDAG->getMachineNode(Opc, dl, VT, Ops, 4);
}
}
break;
}
case ARMISD::FMRRD:
return CurDAG->getMachineNode(ARM::FMRRD, dl, MVT::i32, MVT::i32,
Op.getOperand(0), getAL(CurDAG),
CurDAG->getRegister(0, MVT::i32));
case ISD::UMUL_LOHI: {
if (Subtarget->isThumb1Only())
break;
if (Subtarget->isThumb()) {
SDValue Ops[] = { Op.getOperand(0), Op.getOperand(1),
getAL(CurDAG), CurDAG->getRegister(0, MVT::i32),
CurDAG->getRegister(0, MVT::i32) };
return CurDAG->getMachineNode(ARM::t2UMULL, dl, MVT::i32, MVT::i32, Ops,4);
} else {
SDValue Ops[] = { Op.getOperand(0), Op.getOperand(1),
getAL(CurDAG), CurDAG->getRegister(0, MVT::i32),
CurDAG->getRegister(0, MVT::i32) };
return CurDAG->getMachineNode(ARM::UMULL, dl, MVT::i32, MVT::i32, Ops, 5);
}
}
case ISD::SMUL_LOHI: {
if (Subtarget->isThumb1Only())
break;
if (Subtarget->isThumb()) {
SDValue Ops[] = { Op.getOperand(0), Op.getOperand(1),
getAL(CurDAG), CurDAG->getRegister(0, MVT::i32) };
return CurDAG->getMachineNode(ARM::t2SMULL, dl, MVT::i32, MVT::i32, Ops,4);
} else {
SDValue Ops[] = { Op.getOperand(0), Op.getOperand(1),
getAL(CurDAG), CurDAG->getRegister(0, MVT::i32),
CurDAG->getRegister(0, MVT::i32) };
return CurDAG->getMachineNode(ARM::SMULL, dl, MVT::i32, MVT::i32, Ops, 5);
}
}
case ISD::LOAD: {
SDNode *ResNode = 0;
if (Subtarget->isThumb() && Subtarget->hasThumb2())
ResNode = SelectT2IndexedLoad(Op);
else
ResNode = SelectARMIndexedLoad(Op);
if (ResNode)
return ResNode;
// Other cases are autogenerated.
break;
}
case ARMISD::BRCOND: {
// Pattern: (ARMbrcond:void (bb:Other):$dst, (imm:i32):$cc)
// Emits: (Bcc:void (bb:Other):$dst, (imm:i32):$cc)
// Pattern complexity = 6 cost = 1 size = 0
// Pattern: (ARMbrcond:void (bb:Other):$dst, (imm:i32):$cc)
// Emits: (tBcc:void (bb:Other):$dst, (imm:i32):$cc)
// Pattern complexity = 6 cost = 1 size = 0
// Pattern: (ARMbrcond:void (bb:Other):$dst, (imm:i32):$cc)
// Emits: (t2Bcc:void (bb:Other):$dst, (imm:i32):$cc)
// Pattern complexity = 6 cost = 1 size = 0
unsigned Opc = Subtarget->isThumb() ?
((Subtarget->hasThumb2()) ? ARM::t2Bcc : ARM::tBcc) : ARM::Bcc;
SDValue Chain = Op.getOperand(0);
SDValue N1 = Op.getOperand(1);
SDValue N2 = Op.getOperand(2);
SDValue N3 = Op.getOperand(3);
SDValue InFlag = Op.getOperand(4);
assert(N1.getOpcode() == ISD::BasicBlock);
assert(N2.getOpcode() == ISD::Constant);
assert(N3.getOpcode() == ISD::Register);
SDValue Tmp2 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N2)->getZExtValue()),
MVT::i32);
SDValue Ops[] = { N1, Tmp2, N3, Chain, InFlag };
SDNode *ResNode = CurDAG->getMachineNode(Opc, dl, MVT::Other,
MVT::Flag, Ops, 5);
Chain = SDValue(ResNode, 0);
if (Op.getNode()->getNumValues() == 2) {
InFlag = SDValue(ResNode, 1);
ReplaceUses(SDValue(Op.getNode(), 1), InFlag);
}
ReplaceUses(SDValue(Op.getNode(), 0), SDValue(Chain.getNode(), Chain.getResNo()));
return NULL;
}
case ARMISD::CMOV: {
EVT VT = Op.getValueType();
SDValue N0 = Op.getOperand(0);
SDValue N1 = Op.getOperand(1);
SDValue N2 = Op.getOperand(2);
SDValue N3 = Op.getOperand(3);
SDValue InFlag = Op.getOperand(4);
assert(N2.getOpcode() == ISD::Constant);
assert(N3.getOpcode() == ISD::Register);
if (!Subtarget->isThumb1Only() && VT == MVT::i32) {
// Pattern: (ARMcmov:i32 GPR:i32:$false, so_reg:i32:$true, (imm:i32):$cc)
// Emits: (MOVCCs:i32 GPR:i32:$false, so_reg:i32:$true, (imm:i32):$cc)
// Pattern complexity = 18 cost = 1 size = 0
SDValue CPTmp0;
SDValue CPTmp1;
SDValue CPTmp2;
if (Subtarget->isThumb()) {
if (SelectT2ShifterOperandReg(Op, N1, CPTmp0, CPTmp1)) {
unsigned SOVal = cast<ConstantSDNode>(CPTmp1)->getZExtValue();
unsigned SOShOp = ARM_AM::getSORegShOp(SOVal);
unsigned Opc = 0;
switch (SOShOp) {
case ARM_AM::lsl: Opc = ARM::t2MOVCClsl; break;
case ARM_AM::lsr: Opc = ARM::t2MOVCClsr; break;
case ARM_AM::asr: Opc = ARM::t2MOVCCasr; break;
case ARM_AM::ror: Opc = ARM::t2MOVCCror; break;
default:
llvm_unreachable("Unknown so_reg opcode!");
break;
}
SDValue SOShImm =
CurDAG->getTargetConstant(ARM_AM::getSORegOffset(SOVal), MVT::i32);
SDValue Tmp2 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N2)->getZExtValue()),
MVT::i32);
SDValue Ops[] = { N0, CPTmp0, SOShImm, Tmp2, N3, InFlag };
return CurDAG->SelectNodeTo(Op.getNode(), Opc, MVT::i32,Ops, 6);
}
} else {
if (SelectShifterOperandReg(Op, N1, CPTmp0, CPTmp1, CPTmp2)) {
SDValue Tmp2 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N2)->getZExtValue()),
MVT::i32);
SDValue Ops[] = { N0, CPTmp0, CPTmp1, CPTmp2, Tmp2, N3, InFlag };
return CurDAG->SelectNodeTo(Op.getNode(),
ARM::MOVCCs, MVT::i32, Ops, 7);
}
}
// Pattern: (ARMcmov:i32 GPR:i32:$false,
// (imm:i32)<<P:Predicate_so_imm>>:$true,
// (imm:i32):$cc)
// Emits: (MOVCCi:i32 GPR:i32:$false,
// (so_imm:i32 (imm:i32):$true), (imm:i32):$cc)
// Pattern complexity = 10 cost = 1 size = 0
if (N3.getOpcode() == ISD::Constant) {
if (Subtarget->isThumb()) {
if (Predicate_t2_so_imm(N3.getNode())) {
SDValue Tmp1 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N1)->getZExtValue()),
MVT::i32);
SDValue Tmp2 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N2)->getZExtValue()),
MVT::i32);
SDValue Ops[] = { N0, Tmp1, Tmp2, N3, InFlag };
return CurDAG->SelectNodeTo(Op.getNode(),
ARM::t2MOVCCi, MVT::i32, Ops, 5);
}
} else {
if (Predicate_so_imm(N3.getNode())) {
SDValue Tmp1 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N1)->getZExtValue()),
MVT::i32);
SDValue Tmp2 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N2)->getZExtValue()),
MVT::i32);
SDValue Ops[] = { N0, Tmp1, Tmp2, N3, InFlag };
return CurDAG->SelectNodeTo(Op.getNode(),
ARM::MOVCCi, MVT::i32, Ops, 5);
}
}
}
}
// Pattern: (ARMcmov:i32 GPR:i32:$false, GPR:i32:$true, (imm:i32):$cc)
// Emits: (MOVCCr:i32 GPR:i32:$false, GPR:i32:$true, (imm:i32):$cc)
// Pattern complexity = 6 cost = 1 size = 0
//
// Pattern: (ARMcmov:i32 GPR:i32:$false, GPR:i32:$true, (imm:i32):$cc)
// Emits: (tMOVCCr:i32 GPR:i32:$false, GPR:i32:$true, (imm:i32):$cc)
// Pattern complexity = 6 cost = 11 size = 0
//
// Also FCPYScc and FCPYDcc.
SDValue Tmp2 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N2)->getZExtValue()),
MVT::i32);
SDValue Ops[] = { N0, N1, Tmp2, N3, InFlag };
unsigned Opc = 0;
switch (VT.getSimpleVT().SimpleTy) {
default: assert(false && "Illegal conditional move type!");
break;
case MVT::i32:
Opc = Subtarget->isThumb()
? (Subtarget->hasThumb2() ? ARM::t2MOVCCr : ARM::tMOVCCr_pseudo)
: ARM::MOVCCr;
break;
case MVT::f32:
Opc = ARM::FCPYScc;
break;
case MVT::f64:
Opc = ARM::FCPYDcc;
break;
}
return CurDAG->SelectNodeTo(Op.getNode(), Opc, VT, Ops, 5);
}
case ARMISD::CNEG: {
EVT VT = Op.getValueType();
SDValue N0 = Op.getOperand(0);
SDValue N1 = Op.getOperand(1);
SDValue N2 = Op.getOperand(2);
SDValue N3 = Op.getOperand(3);
SDValue InFlag = Op.getOperand(4);
assert(N2.getOpcode() == ISD::Constant);
assert(N3.getOpcode() == ISD::Register);
SDValue Tmp2 = CurDAG->getTargetConstant(((unsigned)
cast<ConstantSDNode>(N2)->getZExtValue()),
MVT::i32);
SDValue Ops[] = { N0, N1, Tmp2, N3, InFlag };
unsigned Opc = 0;
switch (VT.getSimpleVT().SimpleTy) {
default: assert(false && "Illegal conditional move type!");
break;
case MVT::f32:
Opc = ARM::FNEGScc;
break;
case MVT::f64:
Opc = ARM::FNEGDcc;
break;
}
return CurDAG->SelectNodeTo(Op.getNode(), Opc, VT, Ops, 5);
}
case ARMISD::VZIP: {
unsigned Opc = 0;
EVT VT = N->getValueType(0);
switch (VT.getSimpleVT().SimpleTy) {
default: return NULL;
case MVT::v8i8: Opc = ARM::VZIPd8; break;
case MVT::v4i16: Opc = ARM::VZIPd16; break;
case MVT::v2f32:
case MVT::v2i32: Opc = ARM::VZIPd32; break;
case MVT::v16i8: Opc = ARM::VZIPq8; break;
case MVT::v8i16: Opc = ARM::VZIPq16; break;
case MVT::v4f32:
case MVT::v4i32: Opc = ARM::VZIPq32; break;
}
return CurDAG->getMachineNode(Opc, dl, VT, VT,
N->getOperand(0), N->getOperand(1));
}
case ARMISD::VUZP: {
unsigned Opc = 0;
EVT VT = N->getValueType(0);
switch (VT.getSimpleVT().SimpleTy) {
default: return NULL;
case MVT::v8i8: Opc = ARM::VUZPd8; break;
case MVT::v4i16: Opc = ARM::VUZPd16; break;
case MVT::v2f32:
case MVT::v2i32: Opc = ARM::VUZPd32; break;
case MVT::v16i8: Opc = ARM::VUZPq8; break;
case MVT::v8i16: Opc = ARM::VUZPq16; break;
case MVT::v4f32:
case MVT::v4i32: Opc = ARM::VUZPq32; break;
}
return CurDAG->getMachineNode(Opc, dl, VT, VT,
N->getOperand(0), N->getOperand(1));
}
case ARMISD::VTRN: {
unsigned Opc = 0;
EVT VT = N->getValueType(0);
switch (VT.getSimpleVT().SimpleTy) {
default: return NULL;
case MVT::v8i8: Opc = ARM::VTRNd8; break;
case MVT::v4i16: Opc = ARM::VTRNd16; break;
case MVT::v2f32:
case MVT::v2i32: Opc = ARM::VTRNd32; break;
case MVT::v16i8: Opc = ARM::VTRNq8; break;
case MVT::v8i16: Opc = ARM::VTRNq16; break;
case MVT::v4f32:
case MVT::v4i32: Opc = ARM::VTRNq32; break;
}
return CurDAG->getMachineNode(Opc, dl, VT, VT,
N->getOperand(0), N->getOperand(1));
}
case ISD::INTRINSIC_VOID:
case ISD::INTRINSIC_W_CHAIN: {
unsigned IntNo = cast<ConstantSDNode>(N->getOperand(1))->getZExtValue();
switch (IntNo) {
default:
break;
case Intrinsic::arm_neon_vld2: {
unsigned DOpcodes[] = { ARM::VLD2d8, ARM::VLD2d16,
ARM::VLD2d32, ARM::VLD2d64 };
unsigned QOpcodes[] = { ARM::VLD2q8, ARM::VLD2q16, ARM::VLD2q32 };
return SelectVLD(Op, 2, DOpcodes, QOpcodes, 0);
}
case Intrinsic::arm_neon_vld3: {
unsigned DOpcodes[] = { ARM::VLD3d8, ARM::VLD3d16,
ARM::VLD3d32, ARM::VLD3d64 };
unsigned QOpcodes0[] = { ARM::VLD3q8a, ARM::VLD3q16a, ARM::VLD3q32a };
unsigned QOpcodes1[] = { ARM::VLD3q8b, ARM::VLD3q16b, ARM::VLD3q32b };
return SelectVLD(Op, 3, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vld4: {
unsigned DOpcodes[] = { ARM::VLD4d8, ARM::VLD4d16,
ARM::VLD4d32, ARM::VLD4d64 };
unsigned QOpcodes0[] = { ARM::VLD4q8a, ARM::VLD4q16a, ARM::VLD4q32a };
unsigned QOpcodes1[] = { ARM::VLD4q8b, ARM::VLD4q16b, ARM::VLD4q32b };
return SelectVLD(Op, 4, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vld2lane: {
unsigned DOpcodes[] = { ARM::VLD2LNd8, ARM::VLD2LNd16, ARM::VLD2LNd32 };
unsigned QOpcodes0[] = { ARM::VLD2LNq16a, ARM::VLD2LNq32a };
unsigned QOpcodes1[] = { ARM::VLD2LNq16b, ARM::VLD2LNq32b };
return SelectVLDSTLane(Op, true, 2, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vld3lane: {
unsigned DOpcodes[] = { ARM::VLD3LNd8, ARM::VLD3LNd16, ARM::VLD3LNd32 };
unsigned QOpcodes0[] = { ARM::VLD3LNq16a, ARM::VLD3LNq32a };
unsigned QOpcodes1[] = { ARM::VLD3LNq16b, ARM::VLD3LNq32b };
return SelectVLDSTLane(Op, true, 3, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vld4lane: {
unsigned DOpcodes[] = { ARM::VLD4LNd8, ARM::VLD4LNd16, ARM::VLD4LNd32 };
unsigned QOpcodes0[] = { ARM::VLD4LNq16a, ARM::VLD4LNq32a };
unsigned QOpcodes1[] = { ARM::VLD4LNq16b, ARM::VLD4LNq32b };
return SelectVLDSTLane(Op, true, 4, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vst2: {
unsigned DOpcodes[] = { ARM::VST2d8, ARM::VST2d16,
ARM::VST2d32, ARM::VST2d64 };
unsigned QOpcodes[] = { ARM::VST2q8, ARM::VST2q16, ARM::VST2q32 };
return SelectVST(Op, 2, DOpcodes, QOpcodes, 0);
}
case Intrinsic::arm_neon_vst3: {
unsigned DOpcodes[] = { ARM::VST3d8, ARM::VST3d16,
ARM::VST3d32, ARM::VST3d64 };
unsigned QOpcodes0[] = { ARM::VST3q8a, ARM::VST3q16a, ARM::VST3q32a };
unsigned QOpcodes1[] = { ARM::VST3q8b, ARM::VST3q16b, ARM::VST3q32b };
return SelectVST(Op, 3, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vst4: {
unsigned DOpcodes[] = { ARM::VST4d8, ARM::VST4d16,
ARM::VST4d32, ARM::VST4d64 };
unsigned QOpcodes0[] = { ARM::VST4q8a, ARM::VST4q16a, ARM::VST4q32a };
unsigned QOpcodes1[] = { ARM::VST4q8b, ARM::VST4q16b, ARM::VST4q32b };
return SelectVST(Op, 4, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vst2lane: {
unsigned DOpcodes[] = { ARM::VST2LNd8, ARM::VST2LNd16, ARM::VST2LNd32 };
unsigned QOpcodes0[] = { ARM::VST2LNq16a, ARM::VST2LNq32a };
unsigned QOpcodes1[] = { ARM::VST2LNq16b, ARM::VST2LNq32b };
return SelectVLDSTLane(Op, false, 2, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vst3lane: {
unsigned DOpcodes[] = { ARM::VST3LNd8, ARM::VST3LNd16, ARM::VST3LNd32 };
unsigned QOpcodes0[] = { ARM::VST3LNq16a, ARM::VST3LNq32a };
unsigned QOpcodes1[] = { ARM::VST3LNq16b, ARM::VST3LNq32b };
return SelectVLDSTLane(Op, false, 3, DOpcodes, QOpcodes0, QOpcodes1);
}
case Intrinsic::arm_neon_vst4lane: {
unsigned DOpcodes[] = { ARM::VST4LNd8, ARM::VST4LNd16, ARM::VST4LNd32 };
unsigned QOpcodes0[] = { ARM::VST4LNq16a, ARM::VST4LNq32a };
unsigned QOpcodes1[] = { ARM::VST4LNq16b, ARM::VST4LNq32b };
return SelectVLDSTLane(Op, false, 4, DOpcodes, QOpcodes0, QOpcodes1);
}
}
}
}
return SelectCode(Op);
}
bool ARMDAGToDAGISel::
SelectInlineAsmMemoryOperand(const SDValue &Op, char ConstraintCode,
std::vector<SDValue> &OutOps) {
assert(ConstraintCode == 'm' && "unexpected asm memory constraint");
// Require the address to be in a register. That is safe for all ARM
// variants and it is hard to do anything much smarter without knowing
// how the operand is used.
OutOps.push_back(Op);
return false;
}
/// createARMISelDag - This pass converts a legalized DAG into a
/// ARM-specific DAG, ready for instruction scheduling.
///
FunctionPass *llvm::createARMISelDag(ARMBaseTargetMachine &TM,
CodeGenOpt::Level OptLevel) {
return new ARMDAGToDAGISel(TM, OptLevel);
}
Reference in New Issue View Git Blame Copy Permalink