/// 1 is the number of bytes of stack to pop.
RET_FLAG,
+ /// Return from interrupt. Operand 0 is the number of bytes to pop.
+ IRET,
+
/// Repeat fill, corresponds to X86::REP_STOSx.
REP_STOS,
/// Compute Sum of Absolute Differences.
PSADBW,
+ /// Compute Double Block Packed Sum-Absolute-Differences
+ DBPSADBW,
/// Bitwise Logical AND NOT of Packed FP values.
ANDNP,
// FP vector get exponent
FGETEXP_RND,
+ // Extract Normalized Mantissas
+ VGETMANT,
// FP Scale
SCALEF,
// Integer add/sub with unsigned saturation.
// Integer absolute value
ABS,
+ // Detect Conflicts Within a Vector
+ CONFLICT,
+
/// Floating point max and min.
FMAX, FMIN,
// Vector integer truncate.
VTRUNC,
-
- // Vector integer truncate with mask.
- VTRUNCM,
+ // Vector integer truncate with unsigned/signed saturation.
+ VTRUNCUS, VTRUNCS,
// Vector FP extend.
VFPEXT,
// Vector FP round.
VFPROUND,
- // Vector signed integer to double.
- CVTDQ2PD,
+ // Vector signed/unsigned integer to double.
+ CVTDQ2PD, CVTUDQ2PD,
+
+ // Convert a vector to mask, set bits base on MSB.
+ CVT2MASK,
// 128-bit vector logical left / right shift
VSHLDQ, VSRLDQ,
// Vector shift elements by immediate
VSHLI, VSRLI, VSRAI,
+ // Bit rotate by immediate
+ VROTLI, VROTRI,
+
// Vector packed double/float comparison.
CMPP,
// OR/AND test for masks
KORTEST,
+ KTEST,
// Several flavors of instructions with vector shuffle behaviors.
PACKSS,
VPERMIV3,
VPERMI,
VPERM2X128,
- //Fix Up Special Packed Float32/64 values
+ // Bitwise ternary logic
+ VPTERNLOG,
+ // Fix Up Special Packed Float32/64 values
VFIXUPIMM,
- //Range Restriction Calculation For Packed Pairs of Float32/64 values
+ // Range Restriction Calculation For Packed Pairs of Float32/64 values
VRANGE,
+ // Reduce - Perform Reduction Transformation on scalar\packed FP
+ VREDUCE,
+ // RndScale - Round FP Values To Include A Given Number Of Fraction Bits
+ VRNDSCALE,
+ // VFPCLASS - Tests Types Of a FP Values for packed types.
+ VFPCLASS,
+ // VFPCLASSS - Tests Types Of a FP Values for scalar types.
+ VFPCLASSS,
// Broadcast scalar to vector
VBROADCAST,
+ // Broadcast mask to vector
+ VBROADCASTM,
// Broadcast subvector to vector
SUBV_BROADCAST,
// Insert/Extract vector element
/// SSE4A Extraction and Insertion.
EXTRQI, INSERTQI,
+ // XOP variable/immediate rotations
+ VPROT, VPROTI,
+ // XOP arithmetic/logical shifts
+ VPSHA, VPSHL,
+ // XOP signed/unsigned integer comparisons
+ VPCOM, VPCOMU,
+
// Vector multiply packed unsigned doubleword integers
PMULUDQ,
// Vector multiply packed signed doubleword integers
PMULDQ,
// Vector Multiply Packed UnsignedIntegers with Round and Scale
MULHRS,
-
+ // Multiply and Add Packed Integers
+ VPMADDUBSW, VPMADDWD,
// FMA nodes
FMADD,
FNMADD,
FNMSUB_RND,
FMADDSUB_RND,
FMSUBADD_RND,
- RNDSCALE,
// Compress and expand
COMPRESS,
//with rounding mode
SINT_TO_FP_RND,
UINT_TO_FP_RND,
+
+ // Vector float/double to signed/unsigned integer.
+ FP_TO_SINT_RND, FP_TO_UINT_RND,
// Save xmm argument registers to the stack, according to %al. An operator
// is needed so that this can be expanded with control flow.
VASTART_SAVE_XMM_REGS,
// falls back to heap allocation if not.
SEG_ALLOCA,
- // Windows's _ftol2 runtime routine to do fptoui.
- WIN_FTOL,
-
// Memory barrier
MEMBARRIER,
MFENCE,
bool isCalleePop(CallingConv::ID CallingConv,
bool is64Bit, bool IsVarArg, bool TailCallOpt);
- /// AVX512 static rounding constants. These need to match the values in
- /// avx512fintrin.h.
- enum STATIC_ROUNDING {
- TO_NEAREST_INT = 0,
- TO_NEG_INF = 1,
- TO_POS_INF = 2,
- TO_ZERO = 3,
- CUR_DIRECTION = 4
- };
}
//===--------------------------------------------------------------------===//
unsigned getJumpTableEncoding() const override;
bool useSoftFloat() const override;
- MVT getScalarShiftAmountTy(EVT LHSTy) const override { return MVT::i8; }
+ MVT getScalarShiftAmountTy(const DataLayout &, EVT) const override {
+ return MVT::i8;
+ }
const MCExpr *
LowerCustomJumpTableEntry(const MachineJumpTableInfo *MJTI,
/// function arguments in the caller parameter area. For X86, aggregates
/// that contains are placed at 16-byte boundaries while the rest are at
/// 4-byte boundaries.
- unsigned getByValTypeAlignment(Type *Ty) const override;
+ unsigned getByValTypeAlignment(Type *Ty,
+ const DataLayout &DL) const override;
/// Returns the target specific optimal type for load
/// and store operations as a result of memset, memcpy, and memmove
/// and some i16 instructions are slow.
bool IsDesirableToPromoteOp(SDValue Op, EVT &PVT) const override;
+ /// Return true if the MachineFunction contains a COPY which would imply
+ /// HasOpaqueSPAdjustment.
+ bool hasCopyImplyingStackAdjustment(MachineFunction *MF) const override;
+
MachineBasicBlock *
EmitInstrWithCustomInserter(MachineInstr *MI,
MachineBasicBlock *MBB) const override;
/// Return true if the addressing mode represented
/// by AM is legal for this target, for a load/store of the specified type.
- bool isLegalAddressingMode(const AddrMode &AM, Type *Ty,
- unsigned AS) const override;
+ bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM,
+ Type *Ty, unsigned AS) const override;
/// Return true if the specified immediate is legal
/// icmp immediate, that is the target has icmp instructions which can
/// of the specified type.
/// If the AM is supported, the return value must be >= 0.
/// If the AM is not supported, it returns a negative value.
- int getScalingFactorCost(const AddrMode &AM, Type *Ty,
+ int getScalingFactorCost(const DataLayout &DL, const AddrMode &AM, Type *Ty,
unsigned AS) const override;
bool isVectorShiftByScalarCheap(Type *Ty) const override;
/// from i32 to i8 but not from i32 to i16.
bool isNarrowingProfitable(EVT VT1, EVT VT2) const override;
+ /// Given an intrinsic, checks if on the target the intrinsic will need to map
+ /// to a MemIntrinsicNode (touches memory). If this is the case, it returns
+ /// true and stores the intrinsic information into the IntrinsicInfo that was
+ /// passed to the function.
+ bool getTgtMemIntrinsic(IntrinsicInfo &Info, const CallInst &I,
+ unsigned Intrinsic) const override;
+
/// Returns true if the target can instruction select the
/// specified FP immediate natively. If false, the legalizer will
/// materialize the FP immediate as a load from a constant pool.
/// register, not on the X87 floating point stack.
bool isScalarFPTypeInSSEReg(EVT VT) const {
return (VT == MVT::f64 && X86ScalarSSEf64) || // f64 is when SSE2
- (VT == MVT::f32 && X86ScalarSSEf32); // f32 is when SSE1
- }
-
- /// Return true if the target uses the MSVC _ftol2 routine for fptoui.
- bool isTargetFTOL() const;
-
- /// Return true if the MSVC _ftol2 routine should be used for fptoui to the
- /// given type.
- bool isIntegerTypeFTOL(EVT VT) const {
- return isTargetFTOL() && VT == MVT::i64;
+ (VT == MVT::f32 && X86ScalarSSEf32); // f32 is when SSE1
}
/// \brief Returns true if it is beneficial to convert a load of a constant
return nullptr; // nothing to do, move along.
}
- unsigned getRegisterByName(const char* RegName, EVT VT) const override;
+ unsigned getRegisterByName(const char* RegName, EVT VT,
+ SelectionDAG &DAG) const override;
+
+ /// If a physical register, this returns the register that receives the
+ /// exception address on entry to an EH pad.
+ unsigned
+ getExceptionPointerRegister(const Constant *PersonalityFn) const override;
+
+ /// If a physical register, this returns the register that receives the
+ /// exception typeid on entry to a landing pad.
+ unsigned
+ getExceptionSelectorRegister(const Constant *PersonalityFn) const override;
/// This method returns a target specific FastISel object,
/// or null if the target does not support "fast" ISel.
bool getStackCookieLocation(unsigned &AddressSpace,
unsigned &Offset) const override;
+ /// Return true if the target stores SafeStack pointer at a fixed offset in
+ /// some non-standard address space, and populates the address space and
+ /// offset as appropriate.
+ Value *getSafeStackPointerLocation(IRBuilder<> &IRB) const override;
+
SDValue BuildFILD(SDValue Op, EVT SrcVT, SDValue Chain, SDValue StackSlot,
SelectionDAG &DAG) const;
/// \brief Customize the preferred legalization strategy for certain types.
LegalizeTypeAction getPreferredVectorAction(EVT VT) const override;
+ bool isIntDivCheap(EVT VT, AttributeSet Attr) const override;
+
protected:
std::pair<const TargetRegisterClass *, uint8_t>
findRepresentativeClass(const TargetRegisterInfo *TRI,
/// Keep a pointer to the X86Subtarget around so that we can
/// make the right decision when generating code for different targets.
const X86Subtarget *Subtarget;
- const DataLayout *TD;
/// Select between SSE or x87 floating point ops.
/// When SSE is available, use it for f32 operations.
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
SelectionDAG& DAG) const;
- bool IsCalleePop(bool isVarArg, CallingConv::ID CallConv) const;
SDValue EmitTailCallLoadRetAddr(SelectionDAG &DAG, SDValue &OutRetAddr,
SDValue Chain, bool IsTailCall, bool Is64Bit,
int FPDiff, SDLoc dl) const;
SDValue LowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBUILD_VECTORvXi1(SDValue Op, SelectionDAG &DAG) const;
- SDValue LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVSELECT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerEXTRACT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
SDValue ExtractBitFromMaskVector(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerToBT(SDValue And, ISD::CondCode CC,
SDLoc dl, SelectionDAG &DAG) const;
SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerSETCCE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSELECT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBRCOND(SDValue Op, SelectionDAG &DAG) const;
- SDValue LowerMEMSET(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVASTART(SDValue Op, SelectionDAG &DAG) const;
const SmallVectorImpl<SDValue> &OutVals,
SDLoc dl, SelectionDAG &DAG) const override;
+ bool supportSplitCSR(MachineFunction *MF) const override {
+ return MF->getFunction()->getCallingConv() == CallingConv::CXX_FAST_TLS &&
+ MF->getFunction()->hasFnAttribute(Attribute::NoUnwind);
+ }
+ void initializeSplitCSR(MachineBasicBlock *Entry) const override;
+ void insertCopiesSplitCSR(
+ MachineBasicBlock *Entry,
+ const SmallVectorImpl<MachineBasicBlock *> &Exits) const override;
+
bool isUsedByReturnOnly(SDNode *N, SDValue &Chain) const override;
bool mayBeEmittedAsTailCall(CallInst *CI) const override;
const MCPhysReg *getScratchRegisters(CallingConv::ID CC) const override;
- bool shouldExpandAtomicLoadInIR(LoadInst *SI) const override;
+ TargetLoweringBase::AtomicExpansionKind
+ shouldExpandAtomicLoadInIR(LoadInst *SI) const override;
bool shouldExpandAtomicStoreInIR(StoreInst *SI) const override;
- TargetLoweringBase::AtomicRMWExpansionKind
+ TargetLoweringBase::AtomicExpansionKind
shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const override;
LoadInst *
lowerIdempotentRMWIntoFencedLoad(AtomicRMWInst *AI) const override;
- bool needsCmpXchgNb(const Type *MemType) const;
-
- /// Utility function to emit atomic-load-arith operations (and, or, xor,
- /// nand, max, min, umax, umin). It takes the corresponding instruction to
- /// expand, the associated machine basic block, and the associated X86
- /// opcodes for reg/reg.
- MachineBasicBlock *EmitAtomicLoadArith(MachineInstr *MI,
- MachineBasicBlock *MBB) const;
-
- /// Utility function to emit atomic-load-arith operations (and, or, xor,
- /// nand, add, sub, swap) for 64-bit operands on 32-bit target.
- MachineBasicBlock *EmitAtomicLoadArith6432(MachineInstr *MI,
- MachineBasicBlock *MBB) const;
+ bool needsCmpXchgNb(Type *MemType) const;
// Utility function to emit the low-level va_arg code for X86-64.
MachineBasicBlock *EmitVAARG64WithCustomInserter(
MachineBasicBlock *EmitLoweredSelect(MachineInstr *I,
MachineBasicBlock *BB) const;
+ MachineBasicBlock *EmitLoweredAtomicFP(MachineInstr *I,
+ MachineBasicBlock *BB) const;
+
MachineBasicBlock *EmitLoweredWinAlloca(MachineInstr *MI,
MachineBasicBlock *BB) const;
+ MachineBasicBlock *EmitLoweredCatchRet(MachineInstr *MI,
+ MachineBasicBlock *BB) const;
+
+ MachineBasicBlock *EmitLoweredCatchPad(MachineInstr *MI,
+ MachineBasicBlock *BB) const;
+
MachineBasicBlock *EmitLoweredSegAlloca(MachineInstr *MI,
MachineBasicBlock *BB) const;
- MachineBasicBlock *EmitLoweredTLSCall(MachineInstr *MI,
+ MachineBasicBlock *EmitLoweredTLSAddr(MachineInstr *MI,
MachineBasicBlock *BB) const;
- MachineBasicBlock *emitLoweredTLSAddr(MachineInstr *MI,
+ MachineBasicBlock *EmitLoweredTLSCall(MachineInstr *MI,
MachineBasicBlock *BB) const;
MachineBasicBlock *emitEHSjLjSetJmp(MachineInstr *MI,
unsigned &RefinementSteps) const override;
/// Reassociate floating point divisions into multiply by reciprocal.
- bool combineRepeatedFPDivisors(unsigned NumUsers) const override;
+ unsigned combineRepeatedFPDivisors() const override;
};
namespace X86 {
projects / oota-llvm.git / blobdiff