{ X86::VTESTPSrr, X86::VTESTPSrm, 0 },
{ X86::VUCOMISDrr, X86::VUCOMISDrm, 0 },
{ X86::VUCOMISSrr, X86::VUCOMISSrm, 0 },
- { X86::VBROADCASTSSrr, X86::VBROADCASTSSrm, TB_NO_REVERSE },
// AVX 256-bit foldable instructions
{ X86::VCVTDQ2PDYrr, X86::VCVTDQ2PDYrm, 0 },
{ X86::VMOVUPSYrr, X86::VMOVUPSYrm, 0 },
{ X86::VPERMILPDYri, X86::VPERMILPDYmi, 0 },
{ X86::VPERMILPSYri, X86::VPERMILPSYmi, 0 },
+ { X86::VPTESTYrr, X86::VPTESTYrm, 0 },
{ X86::VRCPPSYr, X86::VRCPPSYm, 0 },
{ X86::VRCPPSYr_Int, X86::VRCPPSYm_Int, 0 },
{ X86::VROUNDYPDr, X86::VROUNDYPDm, 0 },
{ X86::VSQRTPSYr, X86::VSQRTPSYm, 0 },
{ X86::VTESTPDYrr, X86::VTESTPDYrm, 0 },
{ X86::VTESTPSYrr, X86::VTESTPSYrm, 0 },
- { X86::VBROADCASTSSYrr, X86::VBROADCASTSSYrm, TB_NO_REVERSE },
- { X86::VBROADCASTSDYrr, X86::VBROADCASTSDYrm, TB_NO_REVERSE },
// AVX2 foldable instructions
+ { X86::VBROADCASTSSrr, X86::VBROADCASTSSrm, TB_NO_REVERSE },
+ { X86::VBROADCASTSSYrr, X86::VBROADCASTSSYrm, TB_NO_REVERSE },
+ { X86::VBROADCASTSDYrr, X86::VBROADCASTSDYrm, TB_NO_REVERSE },
{ X86::VPABSBrr256, X86::VPABSBrm256, 0 },
{ X86::VPABSDrr256, X86::VPABSDrm256, 0 },
{ X86::VPABSWrr256, X86::VPABSWrm256, 0 },
{ X86::VDIVSSrr_Int, X86::VDIVSSrm_Int, 0 },
{ X86::VDPPDrri, X86::VDPPDrmi, 0 },
{ X86::VDPPSrri, X86::VDPPSrmi, 0 },
- { X86::VFsANDNPDrr, X86::VFsANDNPDrm, TB_ALIGN_16 },
- { X86::VFsANDNPSrr, X86::VFsANDNPSrm, TB_ALIGN_16 },
- { X86::VFsANDPDrr, X86::VFsANDPDrm, TB_ALIGN_16 },
- { X86::VFsANDPSrr, X86::VFsANDPSrm, TB_ALIGN_16 },
- { X86::VFsORPDrr, X86::VFsORPDrm, TB_ALIGN_16 },
- { X86::VFsORPSrr, X86::VFsORPSrm, TB_ALIGN_16 },
- { X86::VFsXORPDrr, X86::VFsXORPDrm, TB_ALIGN_16 },
- { X86::VFsXORPSrr, X86::VFsXORPSrm, TB_ALIGN_16 },
+ { X86::VFsANDNPDrr, X86::VFsANDNPDrm, 0 },
+ { X86::VFsANDNPSrr, X86::VFsANDNPSrm, 0 },
+ { X86::VFsANDPDrr, X86::VFsANDPDrm, 0 },
+ { X86::VFsANDPSrr, X86::VFsANDPSrm, 0 },
+ { X86::VFsORPDrr, X86::VFsORPDrm, 0 },
+ { X86::VFsORPSrr, X86::VFsORPSrm, 0 },
+ { X86::VFsXORPDrr, X86::VFsXORPDrm, 0 },
+ { X86::VFsXORPSrr, X86::VFsXORPSrm, 0 },
{ X86::VHADDPDrr, X86::VHADDPDrm, 0 },
{ X86::VHADDPSrr, X86::VHADDPSrm, 0 },
{ X86::VHSUBPDrr, X86::VHSUBPDrm, 0 },
// FIXME: add AVX 256-bit foldable instructions
// FMA4 foldable patterns
- { X86::VFMADDSS4rr, X86::VFMADDSS4mr, 0 },
- { X86::VFMADDSD4rr, X86::VFMADDSD4mr, 0 },
- { X86::VFMADDPS4rr, X86::VFMADDPS4mr, TB_ALIGN_16 },
- { X86::VFMADDPD4rr, X86::VFMADDPD4mr, TB_ALIGN_16 },
- { X86::VFMADDPS4rrY, X86::VFMADDPS4mrY, TB_ALIGN_32 },
- { X86::VFMADDPD4rrY, X86::VFMADDPD4mrY, TB_ALIGN_32 },
- { X86::VFNMADDSS4rr, X86::VFNMADDSS4mr, 0 },
- { X86::VFNMADDSD4rr, X86::VFNMADDSD4mr, 0 },
- { X86::VFNMADDPS4rr, X86::VFNMADDPS4mr, TB_ALIGN_16 },
- { X86::VFNMADDPD4rr, X86::VFNMADDPD4mr, TB_ALIGN_16 },
- { X86::VFNMADDPS4rrY, X86::VFNMADDPS4mrY, TB_ALIGN_32 },
- { X86::VFNMADDPD4rrY, X86::VFNMADDPD4mrY, TB_ALIGN_32 },
- { X86::VFMSUBSS4rr, X86::VFMSUBSS4mr, 0 },
- { X86::VFMSUBSD4rr, X86::VFMSUBSD4mr, 0 },
- { X86::VFMSUBPS4rr, X86::VFMSUBPS4mr, TB_ALIGN_16 },
- { X86::VFMSUBPD4rr, X86::VFMSUBPD4mr, TB_ALIGN_16 },
- { X86::VFMSUBPS4rrY, X86::VFMSUBPS4mrY, TB_ALIGN_32 },
- { X86::VFMSUBPD4rrY, X86::VFMSUBPD4mrY, TB_ALIGN_32 },
- { X86::VFNMSUBSS4rr, X86::VFNMSUBSS4mr, 0 },
- { X86::VFNMSUBSD4rr, X86::VFNMSUBSD4mr, 0 },
- { X86::VFNMSUBPS4rr, X86::VFNMSUBPS4mr, TB_ALIGN_16 },
- { X86::VFNMSUBPD4rr, X86::VFNMSUBPD4mr, TB_ALIGN_16 },
- { X86::VFNMSUBPS4rrY, X86::VFNMSUBPS4mrY, TB_ALIGN_32 },
- { X86::VFNMSUBPD4rrY, X86::VFNMSUBPD4mrY, TB_ALIGN_32 },
- { X86::VFMADDSUBPS4rr, X86::VFMADDSUBPS4mr, TB_ALIGN_16 },
- { X86::VFMADDSUBPD4rr, X86::VFMADDSUBPD4mr, TB_ALIGN_16 },
- { X86::VFMADDSUBPS4rrY, X86::VFMADDSUBPS4mrY, TB_ALIGN_32 },
- { X86::VFMADDSUBPD4rrY, X86::VFMADDSUBPD4mrY, TB_ALIGN_32 },
- { X86::VFMSUBADDPS4rr, X86::VFMSUBADDPS4mr, TB_ALIGN_16 },
- { X86::VFMSUBADDPD4rr, X86::VFMSUBADDPD4mr, TB_ALIGN_16 },
- { X86::VFMSUBADDPS4rrY, X86::VFMSUBADDPS4mrY, TB_ALIGN_32 },
- { X86::VFMSUBADDPD4rrY, X86::VFMSUBADDPD4mrY, TB_ALIGN_32 },
+ { X86::VFMADDSS4rr, X86::VFMADDSS4mr, 0 },
+ { X86::VFMADDSD4rr, X86::VFMADDSD4mr, 0 },
+ { X86::VFMADDPS4rr, X86::VFMADDPS4mr, 0 },
+ { X86::VFMADDPD4rr, X86::VFMADDPD4mr, 0 },
+ { X86::VFMADDPS4rrY, X86::VFMADDPS4mrY, 0 },
+ { X86::VFMADDPD4rrY, X86::VFMADDPD4mrY, 0 },
+ { X86::VFNMADDSS4rr, X86::VFNMADDSS4mr, 0 },
+ { X86::VFNMADDSD4rr, X86::VFNMADDSD4mr, 0 },
+ { X86::VFNMADDPS4rr, X86::VFNMADDPS4mr, 0 },
+ { X86::VFNMADDPD4rr, X86::VFNMADDPD4mr, 0 },
+ { X86::VFNMADDPS4rrY, X86::VFNMADDPS4mrY, 0 },
+ { X86::VFNMADDPD4rrY, X86::VFNMADDPD4mrY, 0 },
+ { X86::VFMSUBSS4rr, X86::VFMSUBSS4mr, 0 },
+ { X86::VFMSUBSD4rr, X86::VFMSUBSD4mr, 0 },
+ { X86::VFMSUBPS4rr, X86::VFMSUBPS4mr, 0 },
+ { X86::VFMSUBPD4rr, X86::VFMSUBPD4mr, 0 },
+ { X86::VFMSUBPS4rrY, X86::VFMSUBPS4mrY, 0 },
+ { X86::VFMSUBPD4rrY, X86::VFMSUBPD4mrY, 0 },
+ { X86::VFNMSUBSS4rr, X86::VFNMSUBSS4mr, 0 },
+ { X86::VFNMSUBSD4rr, X86::VFNMSUBSD4mr, 0 },
+ { X86::VFNMSUBPS4rr, X86::VFNMSUBPS4mr, 0 },
+ { X86::VFNMSUBPD4rr, X86::VFNMSUBPD4mr, 0 },
+ { X86::VFNMSUBPS4rrY, X86::VFNMSUBPS4mrY, 0 },
+ { X86::VFNMSUBPD4rrY, X86::VFNMSUBPD4mrY, 0 },
+ { X86::VFMADDSUBPS4rr, X86::VFMADDSUBPS4mr, 0 },
+ { X86::VFMADDSUBPD4rr, X86::VFMADDSUBPD4mr, 0 },
+ { X86::VFMADDSUBPS4rrY, X86::VFMADDSUBPS4mrY, 0 },
+ { X86::VFMADDSUBPD4rrY, X86::VFMADDSUBPD4mrY, 0 },
+ { X86::VFMSUBADDPS4rr, X86::VFMSUBADDPS4mr, 0 },
+ { X86::VFMSUBADDPD4rr, X86::VFMSUBADDPD4mr, 0 },
+ { X86::VFMSUBADDPS4rrY, X86::VFMSUBADDPS4mrY, 0 },
+ { X86::VFMSUBADDPD4rrY, X86::VFMSUBADDPD4mrY, 0 },
// BMI/BMI2 foldable instructions
{ X86::ANDN32rr, X86::ANDN32rm, 0 },
{ X86::AESDECrr, X86::AESDECrm, TB_ALIGN_16 },
{ X86::AESENCLASTrr, X86::AESENCLASTrm, TB_ALIGN_16 },
{ X86::AESENCrr, X86::AESENCrm, TB_ALIGN_16 },
- { X86::VAESDECLASTrr, X86::VAESDECLASTrm, TB_ALIGN_16 },
- { X86::VAESDECrr, X86::VAESDECrm, TB_ALIGN_16 },
- { X86::VAESENCLASTrr, X86::VAESENCLASTrm, TB_ALIGN_16 },
- { X86::VAESENCrr, X86::VAESENCrm, TB_ALIGN_16 },
+ { X86::VAESDECLASTrr, X86::VAESDECLASTrm, 0 },
+ { X86::VAESDECrr, X86::VAESDECrm, 0 },
+ { X86::VAESENCLASTrr, X86::VAESENCLASTrm, 0 },
+ { X86::VAESENCrr, X86::VAESENCrm, 0 },
// SHA foldable instructions
{ X86::SHA1MSG1rr, X86::SHA1MSG1rm, TB_ALIGN_16 },
assert(MF.getFrameInfo()->getObjectSize(FrameIdx) >= RC->getSize() &&
"Stack slot too small for store");
unsigned Alignment = std::max<uint32_t>(RC->getSize(), 16);
- bool isAligned = (MF.getTarget()
- .getSubtargetImpl()
- ->getFrameLowering()
- ->getStackAlignment() >= Alignment) ||
- RI.canRealignStack(MF);
+ bool isAligned =
+ (Subtarget.getFrameLowering()->getStackAlignment() >= Alignment) ||
+ RI.canRealignStack(MF);
unsigned Opc = getStoreRegOpcode(SrcReg, RC, isAligned, Subtarget);
DebugLoc DL = MBB.findDebugLoc(MI);
addFrameReference(BuildMI(MBB, MI, DL, get(Opc)), FrameIdx)
const TargetRegisterInfo *TRI) const {
const MachineFunction &MF = *MBB.getParent();
unsigned Alignment = std::max<uint32_t>(RC->getSize(), 16);
- bool isAligned = (MF.getTarget()
- .getSubtargetImpl()
- ->getFrameLowering()
- ->getStackAlignment() >= Alignment) ||
- RI.canRealignStack(MF);
+ bool isAligned =
+ (Subtarget.getFrameLowering()->getStackAlignment() >= Alignment) ||
+ RI.canRealignStack(MF);
unsigned Opc = getLoadRegOpcode(DestReg, RC, isAligned, Subtarget);
DebugLoc DL = MBB.findDebugLoc(MI);
addFrameReference(BuildMI(MBB, MI, DL, get(Opc), DestReg), FrameIdx);
MachineInstr*
X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
- MachineInstr *MI, unsigned i,
+ MachineInstr *MI, unsigned OpNum,
const SmallVectorImpl<MachineOperand> &MOs,
unsigned Size, unsigned Align,
bool AllowCommute) const {
bool isCallRegIndirect = Subtarget.callRegIndirect();
bool isTwoAddrFold = false;
- // Atom favors register form of call. So, we do not fold loads into calls
- // when X86Subtarget is Atom.
+ // For CPUs that favor the register form of a call,
+ // do not fold loads into calls.
if (isCallRegIndirect &&
- (MI->getOpcode() == X86::CALL32r || MI->getOpcode() == X86::CALL64r)) {
+ (MI->getOpcode() == X86::CALL32r || MI->getOpcode() == X86::CALL64r))
return nullptr;
- }
unsigned NumOps = MI->getDesc().getNumOperands();
bool isTwoAddr = NumOps > 1 &&
// Folding a memory location into the two-address part of a two-address
// instruction is different than folding it other places. It requires
// replacing the *two* registers with the memory location.
- if (isTwoAddr && NumOps >= 2 && i < 2 &&
+ if (isTwoAddr && NumOps >= 2 && OpNum < 2 &&
MI->getOperand(0).isReg() &&
MI->getOperand(1).isReg() &&
MI->getOperand(0).getReg() == MI->getOperand(1).getReg()) {
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
isTwoAddrFold = true;
- } else if (i == 0) { // If operand 0
+ } else if (OpNum == 0) {
if (MI->getOpcode() == X86::MOV32r0) {
NewMI = MakeM0Inst(*this, X86::MOV32mi, MOs, MI);
if (NewMI)
}
OpcodeTablePtr = &RegOp2MemOpTable0;
- } else if (i == 1) {
+ } else if (OpNum == 1) {
OpcodeTablePtr = &RegOp2MemOpTable1;
- } else if (i == 2) {
+ } else if (OpNum == 2) {
OpcodeTablePtr = &RegOp2MemOpTable2;
- } else if (i == 3) {
+ } else if (OpNum == 3) {
OpcodeTablePtr = &RegOp2MemOpTable3;
- } else if (i == 4) {
+ } else if (OpNum == 4) {
OpcodeTablePtr = &RegOp2MemOpTable4;
}
return nullptr;
bool NarrowToMOV32rm = false;
if (Size) {
- unsigned RCSize = getRegClass(MI->getDesc(), i, &RI, MF)->getSize();
+ unsigned RCSize = getRegClass(MI->getDesc(), OpNum, &RI, MF)->getSize();
if (Size < RCSize) {
// Check if it's safe to fold the load. If the size of the object is
// narrower than the load width, then it's not.
if (isTwoAddrFold)
NewMI = FuseTwoAddrInst(MF, Opcode, MOs, MI, *this);
else
- NewMI = FuseInst(MF, Opcode, i, MOs, MI, *this);
+ NewMI = FuseInst(MF, Opcode, OpNum, MOs, MI, *this);
if (NarrowToMOV32rm) {
// If this is the special case where we use a MOV32rm to load a 32-bit
// If the instruction and target operand are commutable, commute the
// instruction and try again.
if (AllowCommute) {
- unsigned OriginalOpIdx = i, CommuteOpIdx1, CommuteOpIdx2;
+ unsigned OriginalOpIdx = OpNum, CommuteOpIdx1, CommuteOpIdx2;
if (findCommutedOpIndices(MI, CommuteOpIdx1, CommuteOpIdx2)) {
bool HasDef = MI->getDesc().getNumDefs();
unsigned Reg0 = HasDef ? MI->getOperand(0).getReg() : 0;
// No fusion
if (PrintFailedFusing && !MI->isCopy())
- dbgs() << "We failed to fuse operand " << i << " in " << *MI;
+ dbgs() << "We failed to fuse operand " << OpNum << " in " << *MI;
return nullptr;
}
// If the function stack isn't realigned we don't want to fold instructions
// that need increased alignment.
if (!RI.needsStackRealignment(MF))
- Alignment = std::min(Alignment, MF.getTarget()
- .getSubtargetImpl()
- ->getFrameLowering()
- ->getStackAlignment());
+ Alignment =
+ std::min(Alignment, Subtarget.getFrameLowering()->getStackAlignment());
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
unsigned NewOpc = 0;
unsigned RCSize = 0;
std::pair<unsigned,unsigned> > *OpcodeTablePtr = nullptr;
if (isTwoAddr && NumOps >= 2 && OpNum < 2) {
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
- } else if (OpNum == 0) { // If operand 0
+ } else if (OpNum == 0) {
if (Opc == X86::MOV32r0)
return true;
NewNodes.push_back(Store);
// Preserve memory reference information.
- cast<MachineSDNode>(Load)->setMemRefs(MMOs.first, MMOs.second);
+ cast<MachineSDNode>(Store)->setMemRefs(MMOs.first, MMOs.second);
}
return true;
bool runOnMachineFunction(MachineFunction &MF) override {
const X86TargetMachine *TM =
static_cast<const X86TargetMachine *>(&MF.getTarget());
+ const X86Subtarget &STI = MF.getSubtarget<X86Subtarget>();
// Don't do anything if this is 64-bit as 64-bit PIC
// uses RIP relative addressing.
- if (TM->getSubtarget<X86Subtarget>().is64Bit())
+ if (STI.is64Bit())
return false;
// Only emit a global base reg in PIC mode.
MachineBasicBlock::iterator MBBI = FirstMBB.begin();
DebugLoc DL = FirstMBB.findDebugLoc(MBBI);
MachineRegisterInfo &RegInfo = MF.getRegInfo();
- const X86InstrInfo *TII = TM->getSubtargetImpl()->getInstrInfo();
+ const X86InstrInfo *TII = STI.getInstrInfo();
unsigned PC;
- if (TM->getSubtarget<X86Subtarget>().isPICStyleGOT())
+ if (STI.isPICStyleGOT())
PC = RegInfo.createVirtualRegister(&X86::GR32RegClass);
else
PC = GlobalBaseReg;
// If we're using vanilla 'GOT' PIC style, we should use relative addressing
// not to pc, but to _GLOBAL_OFFSET_TABLE_ external.
- if (TM->getSubtarget<X86Subtarget>().isPICStyleGOT()) {
+ if (STI.isPICStyleGOT()) {
// Generate addl $__GLOBAL_OFFSET_TABLE_ + [.-piclabel], %some_register
BuildMI(FirstMBB, MBBI, DL, TII->get(X86::ADD32ri), GlobalBaseReg)
.addReg(PC).addExternalSymbol("_GLOBAL_OFFSET_TABLE_",
MachineInstr *ReplaceTLSBaseAddrCall(MachineInstr *I,
unsigned TLSBaseAddrReg) {
MachineFunction *MF = I->getParent()->getParent();
- const X86TargetMachine *TM =
- static_cast<const X86TargetMachine *>(&MF->getTarget());
- const bool is64Bit = TM->getSubtarget<X86Subtarget>().is64Bit();
- const X86InstrInfo *TII = TM->getSubtargetImpl()->getInstrInfo();
+ const X86Subtarget &STI = MF->getSubtarget<X86Subtarget>();
+ const bool is64Bit = STI.is64Bit();
+ const X86InstrInfo *TII = STI.getInstrInfo();
// Insert a Copy from TLSBaseAddrReg to RAX/EAX.
MachineInstr *Copy = BuildMI(*I->getParent(), I, I->getDebugLoc(),
// inserting a copy instruction after I. Returns the new instruction.
MachineInstr *SetRegister(MachineInstr *I, unsigned *TLSBaseAddrReg) {
MachineFunction *MF = I->getParent()->getParent();
- const X86TargetMachine *TM =
- static_cast<const X86TargetMachine *>(&MF->getTarget());
- const bool is64Bit = TM->getSubtarget<X86Subtarget>().is64Bit();
- const X86InstrInfo *TII = TM->getSubtargetImpl()->getInstrInfo();
+ const X86Subtarget &STI = MF->getSubtarget<X86Subtarget>();
+ const bool is64Bit = STI.is64Bit();
+ const X86InstrInfo *TII = STI.getInstrInfo();
// Create a virtual register for the TLS base address.
MachineRegisterInfo &RegInfo = MF->getRegInfo();