aboutsummaryrefslogtreecommitdiff
path: root/lib/Target/ARM/ARMBaseInstrInfo.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'lib/Target/ARM/ARMBaseInstrInfo.cpp')
-rw-r--r--lib/Target/ARM/ARMBaseInstrInfo.cpp259
1 files changed, 201 insertions, 58 deletions
diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index 8c1727724a9e..b1c2031c7d7b 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -331,7 +331,7 @@ bool ARMBaseInstrInfo::analyzeBranch(MachineBasicBlock &MBB,
bool CantAnalyze = false;
// Skip over DEBUG values and predicated nonterminators.
- while (I->isDebugValue() || !I->isTerminator()) {
+ while (I->isDebugInstr() || !I->isTerminator()) {
if (I == MBB.begin())
return false;
--I;
@@ -935,6 +935,25 @@ void ARMBaseInstrInfo::copyPhysReg(MachineBasicBlock &MBB,
Mov->addRegisterKilled(SrcReg, TRI);
}
+bool ARMBaseInstrInfo::isCopyInstr(const MachineInstr &MI,
+ const MachineOperand *&Src,
+ const MachineOperand *&Dest) const {
+ // VMOVRRD is also a copy instruction but it requires
+ // special way of handling. It is more complex copy version
+ // and since that we are not considering it. For recognition
+ // of such instruction isExtractSubregLike MI interface fuction
+ // could be used.
+ // VORRq is considered as a move only if two inputs are
+ // the same register.
+ if (!MI.isMoveReg() ||
+ (MI.getOpcode() == ARM::VORRq &&
+ MI.getOperand(1).getReg() != MI.getOperand(2).getReg()))
+ return false;
+ Dest = &MI.getOperand(0);
+ Src = &MI.getOperand(1);
+ return true;
+}
+
const MachineInstrBuilder &
ARMBaseInstrInfo::AddDReg(MachineInstrBuilder &MIB, unsigned Reg,
unsigned SubIdx, unsigned State,
@@ -963,6 +982,17 @@ storeRegToStackSlot(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
MFI.getObjectSize(FI), Align);
switch (TRI->getSpillSize(*RC)) {
+ case 2:
+ if (ARM::HPRRegClass.hasSubClassEq(RC)) {
+ BuildMI(MBB, I, DL, get(ARM::VSTRH))
+ .addReg(SrcReg, getKillRegState(isKill))
+ .addFrameIndex(FI)
+ .addImm(0)
+ .addMemOperand(MMO)
+ .add(predOps(ARMCC::AL));
+ } else
+ llvm_unreachable("Unknown reg class!");
+ break;
case 4:
if (ARM::GPRRegClass.hasSubClassEq(RC)) {
BuildMI(MBB, I, DL, get(ARM::STRi12))
@@ -1161,6 +1191,16 @@ loadRegFromStackSlot(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
MFI.getObjectSize(FI), Align);
switch (TRI->getSpillSize(*RC)) {
+ case 2:
+ if (ARM::HPRRegClass.hasSubClassEq(RC)) {
+ BuildMI(MBB, I, DL, get(ARM::VLDRH), DestReg)
+ .addFrameIndex(FI)
+ .addImm(0)
+ .addMemOperand(MMO)
+ .add(predOps(ARMCC::AL));
+ } else
+ llvm_unreachable("Unknown reg class!");
+ break;
case 4:
if (ARM::GPRRegClass.hasSubClassEq(RC)) {
BuildMI(MBB, I, DL, get(ARM::LDRi12), DestReg)
@@ -1168,7 +1208,6 @@ loadRegFromStackSlot(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
.addImm(0)
.addMemOperand(MMO)
.add(predOps(ARMCC::AL));
-
} else if (ARM::SPRRegClass.hasSubClassEq(RC)) {
BuildMI(MBB, I, DL, get(ARM::VLDRS), DestReg)
.addFrameIndex(FI)
@@ -1321,7 +1360,13 @@ unsigned ARMBaseInstrInfo::isLoadFromStackSlot(const MachineInstr &MI,
}
break;
case ARM::VLD1q64:
+ case ARM::VLD1d8TPseudo:
+ case ARM::VLD1d16TPseudo:
+ case ARM::VLD1d32TPseudo:
case ARM::VLD1d64TPseudo:
+ case ARM::VLD1d8QPseudo:
+ case ARM::VLD1d16QPseudo:
+ case ARM::VLD1d32QPseudo:
case ARM::VLD1d64QPseudo:
if (MI.getOperand(1).isFI() && MI.getOperand(0).getSubReg() == 0) {
FrameIndex = MI.getOperand(1).getIndex();
@@ -1345,7 +1390,7 @@ unsigned ARMBaseInstrInfo::isLoadFromStackSlotPostFE(const MachineInstr &MI,
return MI.mayLoad() && hasLoadFromStackSlot(MI, Dummy, FrameIndex);
}
-/// \brief Expands MEMCPY to either LDMIA/STMIA or LDMIA_UPD/STMID_UPD
+/// Expands MEMCPY to either LDMIA/STMIA or LDMIA_UPD/STMID_UPD
/// depending on whether the result is used.
void ARMBaseInstrInfo::expandMEMCPY(MachineBasicBlock::iterator MI) const {
bool isThumb1 = Subtarget.isThumb1Only();
@@ -1358,7 +1403,6 @@ void ARMBaseInstrInfo::expandMEMCPY(MachineBasicBlock::iterator MI) const {
MachineInstrBuilder LDM, STM;
if (isThumb1 || !MI->getOperand(1).isDead()) {
MachineOperand LDWb(MI->getOperand(1));
- LDWb.setIsRenamable(false);
LDM = BuildMI(*BB, MI, dl, TII->get(isThumb2 ? ARM::t2LDMIA_UPD
: isThumb1 ? ARM::tLDMIA_UPD
: ARM::LDMIA_UPD))
@@ -1369,7 +1413,6 @@ void ARMBaseInstrInfo::expandMEMCPY(MachineBasicBlock::iterator MI) const {
if (isThumb1 || !MI->getOperand(0).isDead()) {
MachineOperand STWb(MI->getOperand(0));
- STWb.setIsRenamable(false);
STM = BuildMI(*BB, MI, dl, TII->get(isThumb2 ? ARM::t2STMIA_UPD
: isThumb1 ? ARM::tSTMIA_UPD
: ARM::STMIA_UPD))
@@ -1379,11 +1422,9 @@ void ARMBaseInstrInfo::expandMEMCPY(MachineBasicBlock::iterator MI) const {
}
MachineOperand LDBase(MI->getOperand(3));
- LDBase.setIsRenamable(false);
LDM.add(LDBase).add(predOps(ARMCC::AL));
MachineOperand STBase(MI->getOperand(2));
- STBase.setIsRenamable(false);
STM.add(STBase).add(predOps(ARMCC::AL));
// Sort the scratch registers into ascending order.
@@ -1391,12 +1432,12 @@ void ARMBaseInstrInfo::expandMEMCPY(MachineBasicBlock::iterator MI) const {
SmallVector<unsigned, 6> ScratchRegs;
for(unsigned I = 5; I < MI->getNumOperands(); ++I)
ScratchRegs.push_back(MI->getOperand(I).getReg());
- std::sort(ScratchRegs.begin(), ScratchRegs.end(),
- [&TRI](const unsigned &Reg1,
- const unsigned &Reg2) -> bool {
- return TRI.getEncodingValue(Reg1) <
- TRI.getEncodingValue(Reg2);
- });
+ llvm::sort(ScratchRegs.begin(), ScratchRegs.end(),
+ [&TRI](const unsigned &Reg1,
+ const unsigned &Reg2) -> bool {
+ return TRI.getEncodingValue(Reg1) <
+ TRI.getEncodingValue(Reg2);
+ });
for (const auto &Reg : ScratchRegs) {
LDM.addReg(Reg, RegState::Define);
@@ -1453,7 +1494,7 @@ bool ARMBaseInstrInfo::expandPostRAPseudo(MachineInstr &MI) const {
return false;
// All clear, widen the COPY.
- DEBUG(dbgs() << "widening: " << MI);
+ LLVM_DEBUG(dbgs() << "widening: " << MI);
MachineInstrBuilder MIB(*MI.getParent()->getParent(), MI);
// Get rid of the old implicit-def of DstRegD. Leave it if it defines a Q-reg
@@ -1482,7 +1523,7 @@ bool ARMBaseInstrInfo::expandPostRAPseudo(MachineInstr &MI) const {
MI.addRegisterKilled(SrcRegS, TRI, true);
}
- DEBUG(dbgs() << "replaced by: " << MI);
+ LLVM_DEBUG(dbgs() << "replaced by: " << MI);
return true;
}
@@ -1659,7 +1700,7 @@ bool ARMBaseInstrInfo::produceSameValue(const MachineInstr &MI0,
}
for (unsigned i = 3, e = MI0.getNumOperands(); i != e; ++i) {
- // %12 = PICLDR %11, 0, pred:14, pred:%noreg
+ // %12 = PICLDR %11, 0, 14, %noreg
const MachineOperand &MO0 = MI0.getOperand(i);
const MachineOperand &MO1 = MI1.getOperand(i);
if (!MO0.isIdenticalTo(MO1))
@@ -1799,7 +1840,7 @@ bool ARMBaseInstrInfo::isSchedulingBoundary(const MachineInstr &MI,
// considered a scheduling hazard, which is wrong. It should be the actual
// instruction preceding the dbg_value instruction(s), just like it is
// when debug info is not present.
- if (MI.isDebugValue())
+ if (MI.isDebugInstr())
return false;
// Terminators and labels can't be scheduled around.
@@ -1813,8 +1854,8 @@ bool ARMBaseInstrInfo::isSchedulingBoundary(const MachineInstr &MI,
// to the t2IT instruction. The added compile time and complexity does not
// seem worth it.
MachineBasicBlock::const_iterator I = MI;
- // Make sure to skip any dbg_value instructions
- while (++I != MBB->end() && I->isDebugValue())
+ // Make sure to skip any debug instructions
+ while (++I != MBB->end() && I->isDebugInstr())
;
if (I != MBB->end() && I->getOpcode() == ARM::t2IT)
return true;
@@ -2277,9 +2318,9 @@ bool llvm::tryFoldSPUpdateIntoPushPop(const ARMSubtarget &Subtarget,
--CurRegEnc) {
unsigned CurReg = RegClass->getRegister(CurRegEnc);
if (!IsPop) {
- // Pushing any register is completely harmless, mark the
- // register involved as undef since we don't care about it in
- // the slightest.
+ // Pushing any register is completely harmless, mark the register involved
+ // as undef since we don't care about its value and must not restore it
+ // during stack unwinding.
RegList.push_back(MachineOperand::CreateReg(CurReg, false, false,
false, false, true));
--RegsNeeded;
@@ -2409,6 +2450,14 @@ bool llvm::rewriteARMFrameIndex(MachineInstr &MI, unsigned FrameRegIdx,
NumBits = 8;
Scale = 4;
break;
+ case ARMII::AddrMode5FP16:
+ ImmIdx = FrameRegIdx+1;
+ InstrOffs = ARM_AM::getAM5Offset(MI.getOperand(ImmIdx).getImm());
+ if (ARM_AM::getAM5Op(MI.getOperand(ImmIdx).getImm()) == ARM_AM::sub)
+ InstrOffs *= -1;
+ NumBits = 8;
+ Scale = 2;
+ break;
default:
llvm_unreachable("Unsupported addressing mode!");
}
@@ -2534,14 +2583,28 @@ inline static ARMCC::CondCodes getSwappedCondition(ARMCC::CondCodes CC) {
}
}
+/// getCmpToAddCondition - assume the flags are set by CMP(a,b), return
+/// the condition code if we modify the instructions such that flags are
+/// set by ADD(a,b,X).
+inline static ARMCC::CondCodes getCmpToAddCondition(ARMCC::CondCodes CC) {
+ switch (CC) {
+ default: return ARMCC::AL;
+ case ARMCC::HS: return ARMCC::LO;
+ case ARMCC::LO: return ARMCC::HS;
+ case ARMCC::VS: return ARMCC::VS;
+ case ARMCC::VC: return ARMCC::VC;
+ }
+}
+
/// isRedundantFlagInstr - check whether the first instruction, whose only
/// purpose is to update flags, can be made redundant.
/// CMPrr can be made redundant by SUBrr if the operands are the same.
/// CMPri can be made redundant by SUBri if the operands are the same.
+/// CMPrr(r0, r1) can be made redundant by ADDr[ri](r0, r1, X).
/// This function can be extended later on.
-inline static bool isRedundantFlagInstr(MachineInstr *CmpI, unsigned SrcReg,
- unsigned SrcReg2, int ImmValue,
- MachineInstr *OI) {
+inline static bool isRedundantFlagInstr(const MachineInstr *CmpI,
+ unsigned SrcReg, unsigned SrcReg2,
+ int ImmValue, const MachineInstr *OI) {
if ((CmpI->getOpcode() == ARM::CMPrr ||
CmpI->getOpcode() == ARM::t2CMPrr) &&
(OI->getOpcode() == ARM::SUBrr ||
@@ -2559,6 +2622,14 @@ inline static bool isRedundantFlagInstr(MachineInstr *CmpI, unsigned SrcReg,
OI->getOperand(1).getReg() == SrcReg &&
OI->getOperand(2).getImm() == ImmValue)
return true;
+
+ if ((CmpI->getOpcode() == ARM::CMPrr || CmpI->getOpcode() == ARM::t2CMPrr) &&
+ (OI->getOpcode() == ARM::ADDrr || OI->getOpcode() == ARM::t2ADDrr ||
+ OI->getOpcode() == ARM::ADDri || OI->getOpcode() == ARM::t2ADDri) &&
+ OI->getOperand(0).isReg() && OI->getOperand(1).isReg() &&
+ OI->getOperand(0).getReg() == SrcReg &&
+ OI->getOperand(1).getReg() == SrcReg2)
+ return true;
return false;
}
@@ -2661,17 +2732,18 @@ bool ARMBaseInstrInfo::optimizeCompareInstr(
if (I == B) return false;
// There are two possible candidates which can be changed to set CPSR:
- // One is MI, the other is a SUB instruction.
- // For CMPrr(r1,r2), we are looking for SUB(r1,r2) or SUB(r2,r1).
+ // One is MI, the other is a SUB or ADD instruction.
+ // For CMPrr(r1,r2), we are looking for SUB(r1,r2), SUB(r2,r1), or
+ // ADDr[ri](r1, r2, X).
// For CMPri(r1, CmpValue), we are looking for SUBri(r1, CmpValue).
- MachineInstr *Sub = nullptr;
+ MachineInstr *SubAdd = nullptr;
if (SrcReg2 != 0)
// MI is not a candidate for CMPrr.
MI = nullptr;
else if (MI->getParent() != CmpInstr.getParent() || CmpValue != 0) {
// Conservatively refuse to convert an instruction which isn't in the same
// BB as the comparison.
- // For CMPri w/ CmpValue != 0, a Sub may still be a candidate.
+ // For CMPri w/ CmpValue != 0, a SubAdd may still be a candidate.
// Thus we cannot return here.
if (CmpInstr.getOpcode() == ARM::CMPri ||
CmpInstr.getOpcode() == ARM::t2CMPri)
@@ -2716,11 +2788,20 @@ bool ARMBaseInstrInfo::optimizeCompareInstr(
}
// Check that CPSR isn't set between the comparison instruction and the one we
- // want to change. At the same time, search for Sub.
+ // want to change. At the same time, search for SubAdd.
const TargetRegisterInfo *TRI = &getRegisterInfo();
- --I;
- for (; I != E; --I) {
- const MachineInstr &Instr = *I;
+ do {
+ const MachineInstr &Instr = *--I;
+
+ // Check whether CmpInstr can be made redundant by the current instruction.
+ if (isRedundantFlagInstr(&CmpInstr, SrcReg, SrcReg2, CmpValue, &Instr)) {
+ SubAdd = &*I;
+ break;
+ }
+
+ // Allow E (which was initially MI) to be SubAdd but do not search before E.
+ if (I == E)
+ break;
if (Instr.modifiesRegister(ARM::CPSR, TRI) ||
Instr.readsRegister(ARM::CPSR, TRI))
@@ -2728,23 +2809,14 @@ bool ARMBaseInstrInfo::optimizeCompareInstr(
// change. We can't do this transformation.
return false;
- // Check whether CmpInstr can be made redundant by the current instruction.
- if (isRedundantFlagInstr(&CmpInstr, SrcReg, SrcReg2, CmpValue, &*I)) {
- Sub = &*I;
- break;
- }
-
- if (I == B)
- // The 'and' is below the comparison instruction.
- return false;
- }
+ } while (I != B);
// Return false if no candidates exist.
- if (!MI && !Sub)
+ if (!MI && !SubAdd)
return false;
// The single candidate is called MI.
- if (!MI) MI = Sub;
+ if (!MI) MI = SubAdd;
// We can't use a predicated instruction - it doesn't always write the flags.
if (isPredicated(*MI))
@@ -2802,25 +2874,31 @@ bool ARMBaseInstrInfo::optimizeCompareInstr(
break;
}
- if (Sub) {
- ARMCC::CondCodes NewCC = getSwappedCondition(CC);
- if (NewCC == ARMCC::AL)
- return false;
+ if (SubAdd) {
// If we have SUB(r1, r2) and CMP(r2, r1), the condition code based
// on CMP needs to be updated to be based on SUB.
+ // If we have ADD(r1, r2, X) and CMP(r1, r2), the condition code also
+ // needs to be modified.
// Push the condition code operands to OperandsToUpdate.
// If it is safe to remove CmpInstr, the condition code of these
// operands will be modified.
- if (SrcReg2 != 0 && Sub->getOperand(1).getReg() == SrcReg2 &&
- Sub->getOperand(2).getReg() == SrcReg) {
+ unsigned Opc = SubAdd->getOpcode();
+ bool IsSub = Opc == ARM::SUBrr || Opc == ARM::t2SUBrr ||
+ Opc == ARM::SUBri || Opc == ARM::t2SUBri;
+ if (!IsSub || (SrcReg2 != 0 && SubAdd->getOperand(1).getReg() == SrcReg2 &&
+ SubAdd->getOperand(2).getReg() == SrcReg)) {
// VSel doesn't support condition code update.
if (IsInstrVSel)
return false;
+ // Ensure we can swap the condition.
+ ARMCC::CondCodes NewCC = (IsSub ? getSwappedCondition(CC) : getCmpToAddCondition(CC));
+ if (NewCC == ARMCC::AL)
+ return false;
OperandsToUpdate.push_back(
std::make_pair(&((*I).getOperand(IO - 1)), NewCC));
}
} else {
- // No Sub, so this is x = <op> y, z; cmp x, 0.
+ // No SubAdd, so this is x = <op> y, z; cmp x, 0.
switch (CC) {
case ARMCC::EQ: // Z
case ARMCC::NE: // Z
@@ -2874,6 +2952,23 @@ bool ARMBaseInstrInfo::optimizeCompareInstr(
return true;
}
+bool ARMBaseInstrInfo::shouldSink(const MachineInstr &MI) const {
+ // Do not sink MI if it might be used to optimize a redundant compare.
+ // We heuristically only look at the instruction immediately following MI to
+ // avoid potentially searching the entire basic block.
+ if (isPredicated(MI))
+ return true;
+ MachineBasicBlock::const_iterator Next = &MI;
+ ++Next;
+ unsigned SrcReg, SrcReg2;
+ int CmpMask, CmpValue;
+ if (Next != MI.getParent()->end() &&
+ analyzeCompare(*Next, SrcReg, SrcReg2, CmpMask, CmpValue) &&
+ isRedundantFlagInstr(&*Next, SrcReg, SrcReg2, CmpValue, &MI))
+ return false;
+ return true;
+}
+
bool ARMBaseInstrInfo::FoldImmediate(MachineInstr &UseMI, MachineInstr &DefMI,
unsigned Reg,
MachineRegisterInfo *MRI) const {
@@ -3467,8 +3562,8 @@ bool ARMBaseInstrInfo::isLDMBaseRegInList(const MachineInstr &MI) const {
}
unsigned
ARMBaseInstrInfo::getLDMVariableDefsSize(const MachineInstr &MI) const {
- // ins GPR:$Rn, pred:$p (2xOp), reglist:$regs, variable_ops
- // (outs GPR:$wb), (ins GPR:$Rn, pred:$p (2xOp), reglist:$regs, variable_ops)
+ // ins GPR:$Rn, $p (2xOp), reglist:$regs, variable_ops
+ // (outs GPR:$wb), (ins GPR:$Rn, $p (2xOp), reglist:$regs, variable_ops)
return MI.getNumOperands() + 1 - MI.getDesc().getNumOperands();
}
@@ -4142,8 +4237,12 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
case ARM::VLD3d8Pseudo:
case ARM::VLD3d16Pseudo:
case ARM::VLD3d32Pseudo:
+ case ARM::VLD1d8TPseudo:
+ case ARM::VLD1d16TPseudo:
+ case ARM::VLD1d32TPseudo:
case ARM::VLD1d64TPseudo:
case ARM::VLD1d64TPseudoWB_fixed:
+ case ARM::VLD1d64TPseudoWB_register:
case ARM::VLD3d8Pseudo_UPD:
case ARM::VLD3d16Pseudo_UPD:
case ARM::VLD3d32Pseudo_UPD:
@@ -4159,8 +4258,28 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
case ARM::VLD4d8Pseudo:
case ARM::VLD4d16Pseudo:
case ARM::VLD4d32Pseudo:
+ case ARM::VLD1d8QPseudo:
+ case ARM::VLD1d16QPseudo:
+ case ARM::VLD1d32QPseudo:
case ARM::VLD1d64QPseudo:
case ARM::VLD1d64QPseudoWB_fixed:
+ case ARM::VLD1d64QPseudoWB_register:
+ case ARM::VLD1q8HighQPseudo:
+ case ARM::VLD1q8LowQPseudo_UPD:
+ case ARM::VLD1q8HighTPseudo:
+ case ARM::VLD1q8LowTPseudo_UPD:
+ case ARM::VLD1q16HighQPseudo:
+ case ARM::VLD1q16LowQPseudo_UPD:
+ case ARM::VLD1q16HighTPseudo:
+ case ARM::VLD1q16LowTPseudo_UPD:
+ case ARM::VLD1q32HighQPseudo:
+ case ARM::VLD1q32LowQPseudo_UPD:
+ case ARM::VLD1q32HighTPseudo:
+ case ARM::VLD1q32LowTPseudo_UPD:
+ case ARM::VLD1q64HighQPseudo:
+ case ARM::VLD1q64LowQPseudo_UPD:
+ case ARM::VLD1q64HighTPseudo:
+ case ARM::VLD1q64LowTPseudo_UPD:
case ARM::VLD4d8Pseudo_UPD:
case ARM::VLD4d16Pseudo_UPD:
case ARM::VLD4d32Pseudo_UPD:
@@ -4191,12 +4310,30 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
case ARM::VLD2DUPd8wb_register:
case ARM::VLD2DUPd16wb_register:
case ARM::VLD2DUPd32wb_register:
+ case ARM::VLD2DUPq8EvenPseudo:
+ case ARM::VLD2DUPq8OddPseudo:
+ case ARM::VLD2DUPq16EvenPseudo:
+ case ARM::VLD2DUPq16OddPseudo:
+ case ARM::VLD2DUPq32EvenPseudo:
+ case ARM::VLD2DUPq32OddPseudo:
+ case ARM::VLD3DUPq8EvenPseudo:
+ case ARM::VLD3DUPq8OddPseudo:
+ case ARM::VLD3DUPq16EvenPseudo:
+ case ARM::VLD3DUPq16OddPseudo:
+ case ARM::VLD3DUPq32EvenPseudo:
+ case ARM::VLD3DUPq32OddPseudo:
case ARM::VLD4DUPd8Pseudo:
case ARM::VLD4DUPd16Pseudo:
case ARM::VLD4DUPd32Pseudo:
case ARM::VLD4DUPd8Pseudo_UPD:
case ARM::VLD4DUPd16Pseudo_UPD:
case ARM::VLD4DUPd32Pseudo_UPD:
+ case ARM::VLD4DUPq8EvenPseudo:
+ case ARM::VLD4DUPq8OddPseudo:
+ case ARM::VLD4DUPq16EvenPseudo:
+ case ARM::VLD4DUPq16OddPseudo:
+ case ARM::VLD4DUPq32EvenPseudo:
+ case ARM::VLD4DUPq32OddPseudo:
case ARM::VLD1LNq8Pseudo:
case ARM::VLD1LNq16Pseudo:
case ARM::VLD1LNq32Pseudo:
@@ -4864,12 +5001,14 @@ bool ARMBaseInstrInfo::getRegSequenceLikeInputs(
// Populate the InputRegs accordingly.
// rY
const MachineOperand *MOReg = &MI.getOperand(1);
- InputRegs.push_back(
- RegSubRegPairAndIdx(MOReg->getReg(), MOReg->getSubReg(), ARM::ssub_0));
+ if (!MOReg->isUndef())
+ InputRegs.push_back(RegSubRegPairAndIdx(MOReg->getReg(),
+ MOReg->getSubReg(), ARM::ssub_0));
// rZ
MOReg = &MI.getOperand(2);
- InputRegs.push_back(
- RegSubRegPairAndIdx(MOReg->getReg(), MOReg->getSubReg(), ARM::ssub_1));
+ if (!MOReg->isUndef())
+ InputRegs.push_back(RegSubRegPairAndIdx(MOReg->getReg(),
+ MOReg->getSubReg(), ARM::ssub_1));
return true;
}
llvm_unreachable("Target dependent opcode missing");
@@ -4888,6 +5027,8 @@ bool ARMBaseInstrInfo::getExtractSubregLikeInputs(
// rX = EXTRACT_SUBREG dZ, ssub_0
// rY = EXTRACT_SUBREG dZ, ssub_1
const MachineOperand &MOReg = MI.getOperand(2);
+ if (MOReg.isUndef())
+ return false;
InputReg.Reg = MOReg.getReg();
InputReg.SubReg = MOReg.getSubReg();
InputReg.SubIdx = DefIdx == 0 ? ARM::ssub_0 : ARM::ssub_1;
@@ -4907,6 +5048,8 @@ bool ARMBaseInstrInfo::getInsertSubregLikeInputs(
// dX = VSETLNi32 dY, rZ, imm
const MachineOperand &MOBaseReg = MI.getOperand(1);
const MachineOperand &MOInsertedReg = MI.getOperand(2);
+ if (MOInsertedReg.isUndef())
+ return false;
const MachineOperand &MOIndex = MI.getOperand(3);
BaseReg.Reg = MOBaseReg.getReg();
BaseReg.SubReg = MOBaseReg.getSubReg();