/// X86 bit-test instructions.
BT,
- /// X86 SetCC. Operand 0 is condition code, and operand 1 is the flag
- /// operand produced by a CMP instruction.
+ /// X86 SetCC. Operand 0 is condition code, and operand 1 is the EFLAGS
+ /// operand, usually produced by a CMP instruction.
SETCC,
// Same as SETCC except it's materialized with a sbb and the value is all
// one's or all zero's.
- SETCC_CARRY,
+ SETCC_CARRY, // R = carry_bit ? ~0 : 0
+
+ /// X86 FP SETCC, implemented with CMP{cc}SS/CMP{cc}SD.
+ /// Operands are two FP values to compare; result is a mask of
+ /// 0s or 1s. Generally DTRT for C/C++ with NaNs.
+ FSETCCss, FSETCCsd,
+
+ /// X86 MOVMSK{pd|ps}, extracts sign bits of two or four FP values,
+ /// result in an integer GPR. Needs masking for scalar result.
+ FGETSIGNx86,
/// X86 conditional moves. Operand 0 and operand 1 are the two values
/// to select from. Operand 2 is the condition code, and operand 3 is the
/// PSHUFB - Shuffle 16 8-bit values within a vector.
PSHUFB,
+ /// ANDNP - Bitwise Logical AND NOT of Packed FP values.
+ ANDNP,
+
+ /// PSIGNB/W/D - Copy integer sign.
+ PSIGNB, PSIGNW, PSIGND,
+
+ /// BLEND family of opcodes
+ BLENDV,
+
+ /// FHADD - Floating point horizontal add.
+ FHADD,
+
+ /// FHSUB - Floating point horizontal sub.
+ FHSUB,
+
/// FMAX, FMIN - Floating point max and min.
///
FMAX, FMIN,
PCMPEQB, PCMPEQW, PCMPEQD, PCMPEQQ,
PCMPGTB, PCMPGTW, PCMPGTD, PCMPGTQ,
- // ADD, SUB, SMUL, UMUL, etc. - Arithmetic operations with FLAGS results.
- ADD, SUB, SMUL, UMUL,
+ // ADD, SUB, SMUL, etc. - Arithmetic operations with FLAGS results.
+ ADD, SUB, ADC, SBB, SMUL,
INC, DEC, OR, XOR, AND,
+ ANDN, // ANDN - Bitwise AND NOT with FLAGS results.
+
+ UMUL, // LOW, HI, FLAGS = umul LHS, RHS
+
// MUL_IMM - X86 specific multiply by immediate.
MUL_IMM,
MOVSS,
UNPCKLPS,
UNPCKLPD,
+ VUNPCKLPSY,
+ VUNPCKLPDY,
UNPCKHPS,
UNPCKHPD,
+ VUNPCKHPSY,
+ VUNPCKHPDY,
PUNPCKLBW,
PUNPCKLWD,
PUNPCKLDQ,
PUNPCKHWD,
PUNPCKHDQ,
PUNPCKHQDQ,
+ VPERMILPS,
+ VPERMILPSY,
+ VPERMILPD,
+ VPERMILPDY,
+ VPERM2F128,
+ VBROADCAST,
// VASTART_SAVE_XMM_REGS - 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,
- // MINGW_ALLOCA - MingW's __alloca call to do stack probing.
- MINGW_ALLOCA,
+ // WIN_ALLOCA - Windows's _chkstk call to do stack probing.
+ WIN_ALLOCA,
+
+ // SEG_ALLOCA - For allocating variable amounts of stack space when using
+ // segmented stacks. Check if the current stacklet has enough space, and
+ // falls back to heap allocation if not.
+ SEG_ALLOCA,
+
+ // Memory barrier
+ MEMBARRIER,
+ MFENCE,
+ SFENCE,
+ LFENCE,
// ATOMADD64_DAG, ATOMSUB64_DAG, ATOMOR64_DAG, ATOMAND64_DAG,
// ATOMXOR64_DAG, ATOMNAND64_DAG, ATOMSWAP64_DAG -
ATOMNAND64_DAG,
ATOMSWAP64_DAG,
- // Memory barrier
- MEMBARRIER,
- MFENCE,
- SFENCE,
- LFENCE,
-
- // LCMPXCHG_DAG, LCMPXCHG8_DAG - Compare and swap.
+ // LCMPXCHG_DAG, LCMPXCHG8_DAG, LCMPXCHG16_DAG - Compare and swap.
LCMPXCHG_DAG,
LCMPXCHG8_DAG,
+ LCMPXCHG16_DAG,
// VZEXT_LOAD - Load, scalar_to_vector, and zero extend.
VZEXT_LOAD,
/// isMOVSHDUPMask - Return true if the specified VECTOR_SHUFFLE operand
/// specifies a shuffle of elements that is suitable for input to MOVSHDUP.
- bool isMOVSHDUPMask(ShuffleVectorSDNode *N);
+ bool isMOVSHDUPMask(ShuffleVectorSDNode *N, const X86Subtarget *Subtarget);
/// isMOVSLDUPMask - Return true if the specified VECTOR_SHUFFLE operand
/// specifies a shuffle of elements that is suitable for input to MOVSLDUP.
- bool isMOVSLDUPMask(ShuffleVectorSDNode *N);
+ bool isMOVSLDUPMask(ShuffleVectorSDNode *N, const X86Subtarget *Subtarget);
/// isMOVDDUPMask - Return true if the specified VECTOR_SHUFFLE operand
/// specifies a shuffle of elements that is suitable for input to MOVDDUP.
bool isMOVDDUPMask(ShuffleVectorSDNode *N);
- /// isPALIGNRMask - Return true if the specified VECTOR_SHUFFLE operand
- /// specifies a shuffle of elements that is suitable for input to PALIGNR.
- bool isPALIGNRMask(ShuffleVectorSDNode *N);
+ /// isVEXTRACTF128Index - Return true if the specified
+ /// EXTRACT_SUBVECTOR operand specifies a vector extract that is
+ /// suitable for input to VEXTRACTF128.
+ bool isVEXTRACTF128Index(SDNode *N);
+
+ /// isVINSERTF128Index - Return true if the specified
+ /// INSERT_SUBVECTOR operand specifies a subvector insert that is
+ /// suitable for input to VINSERTF128.
+ bool isVINSERTF128Index(SDNode *N);
/// getShuffleSHUFImmediate - Return the appropriate immediate to shuffle
/// the specified isShuffleMask VECTOR_SHUFFLE mask with PSHUF* and SHUFP*
/// the specified VECTOR_SHUFFLE mask with the PALIGNR instruction.
unsigned getShufflePALIGNRImmediate(SDNode *N);
+ /// getExtractVEXTRACTF128Immediate - Return the appropriate
+ /// immediate to extract the specified EXTRACT_SUBVECTOR index
+ /// with VEXTRACTF128 instructions.
+ unsigned getExtractVEXTRACTF128Immediate(SDNode *N);
+
+ /// getInsertVINSERTF128Immediate - Return the appropriate
+ /// immediate to insert at the specified INSERT_SUBVECTOR index
+ /// with VINSERTF128 instructions.
+ unsigned getInsertVINSERTF128Immediate(SDNode *N);
+
/// isZeroNode - Returns true if Elt is a constant zero or a floating point
/// constant +0.0.
bool isZeroNode(SDValue Elt);
/// fit into displacement field of the instruction.
bool isOffsetSuitableForCodeModel(int64_t Offset, CodeModel::Model M,
bool hasSymbolicDisplacement = true);
+
+
+ /// isCalleePop - Determines whether the callee is required to pop its
+ /// own arguments. Callee pop is necessary to support tail calls.
+ bool isCalleePop(CallingConv::ID CallingConv,
+ bool is64Bit, bool IsVarArg, bool TailCallOpt);
}
//===--------------------------------------------------------------------===//
public:
explicit X86TargetLowering(X86TargetMachine &TM);
- /// getPICBaseSymbol - Return the X86-32 PIC base.
- MCSymbol *getPICBaseSymbol(const MachineFunction *MF, MCContext &Ctx) const;
-
virtual unsigned getJumpTableEncoding() const;
+ virtual MVT getShiftAmountTy(EVT LHSTy) const { return MVT::i8; }
+
virtual const MCExpr *
LowerCustomJumpTableEntry(const MachineJumpTableInfo *MJTI,
const MachineBasicBlock *MBB, unsigned uid,
/// 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.
- virtual unsigned getByValTypeAlignment(const Type *Ty) const;
+ virtual unsigned getByValTypeAlignment(Type *Ty) const;
/// getOptimalMemOpType - Returns the target specific optimal type for load
/// and store operations as a result of memset, memcpy, and memmove
/// DAG node.
virtual const char *getTargetNodeName(unsigned Opcode) const;
- /// getSetCCResultType - Return the ISD::SETCC ValueType
- virtual MVT::SimpleValueType getSetCCResultType(EVT VT) const;
+ /// getSetCCResultType - Return the value type to use for ISD::SETCC.
+ virtual EVT getSetCCResultType(EVT VT) const;
/// computeMaskedBitsForTargetNode - Determine which of the bits specified
/// in Mask are known to be either zero or one and return them in the
ConstraintType getConstraintType(const std::string &Constraint) const;
- /// Examine constraint string and operand type and determine a weight value,
- /// where: -1 = invalid match, and 0 = so-so match to 3 = good match.
+ /// Examine constraint string and operand type and determine a weight value.
/// The operand object must already have been set up with the operand type.
- virtual int getSingleConstraintMatchWeight(
+ virtual ConstraintWeight getSingleConstraintMatchWeight(
AsmOperandInfo &info, const char *constraint) const;
- std::vector<unsigned>
- getRegClassForInlineAsmConstraint(const std::string &Constraint,
- EVT VT) const;
-
virtual const char *LowerXConstraint(EVT ConstraintVT) const;
/// LowerAsmOperandForConstraint - Lower the specified operand into the Ops
/// true it means one of the asm constraint of the inline asm instruction
/// being processed is 'm'.
virtual void LowerAsmOperandForConstraint(SDValue Op,
- char ConstraintLetter,
+ std::string &Constraint,
std::vector<SDValue> &Ops,
SelectionDAG &DAG) const;
/// isLegalAddressingMode - Return true if the addressing mode represented
/// by AM is legal for this target, for a load/store of the specified type.
- virtual bool isLegalAddressingMode(const AddrMode &AM, const Type *Ty)const;
+ virtual bool isLegalAddressingMode(const AddrMode &AM, Type *Ty)const;
/// isTruncateFree - Return true if it's free to truncate a value of
/// type Ty1 to type Ty2. e.g. On x86 it's free to truncate a i32 value in
/// register EAX to i16 by referencing its sub-register AX.
- virtual bool isTruncateFree(const Type *Ty1, const Type *Ty2) const;
+ virtual bool isTruncateFree(Type *Ty1, Type *Ty2) const;
virtual bool isTruncateFree(EVT VT1, EVT VT2) const;
/// isZExtFree - Return true if any actual instruction that defines a
/// does not necessarily apply to truncate instructions. e.g. on x86-64,
/// all instructions that define 32-bit values implicit zero-extend the
/// result out to 64 bits.
- virtual bool isZExtFree(const Type *Ty1, const Type *Ty2) const;
+ virtual bool isZExtFree(Type *Ty1, Type *Ty2) const;
virtual bool isZExtFree(EVT VT1, EVT VT2) const;
/// isNarrowingProfitable - Return true if it's profitable to narrow
/// or null if the target does not support "fast" ISel.
virtual FastISel *createFastISel(FunctionLoweringInfo &funcInfo) const;
- /// getFunctionAlignment - Return the Log2 alignment of this function.
- virtual unsigned getFunctionAlignment(const Function *F) const;
-
- unsigned getRegPressureLimit(const TargetRegisterClass *RC,
- MachineFunction &MF) const;
-
/// getStackCookieLocation - Return true if the target stores stack
/// protector cookies at a fixed offset in some non-standard address
/// space, and populates the address space and offset as
/// appropriate.
virtual bool getStackCookieLocation(unsigned &AddressSpace, unsigned &Offset) const;
+ SDValue BuildFILD(SDValue Op, EVT SrcVT, SDValue Chain, SDValue StackSlot,
+ SelectionDAG &DAG) const;
+
protected:
std::pair<const TargetRegisterClass*, uint8_t>
findRepresentativeClass(EVT VT) const;
SDValue Chain, bool IsTailCall, bool Is64Bit,
int FPDiff, DebugLoc dl) const;
- CCAssignFn *CCAssignFnForNode(CallingConv::ID CallConv) const;
unsigned GetAlignedArgumentStackSize(unsigned StackSize,
SelectionDAG &DAG) const;
SDValue LowerINSERT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINSERT_VECTOR_ELT_SSE4(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSCALAR_TO_VECTOR(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerEXTRACT_SUBVECTOR(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerINSERT_SUBVECTOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerGlobalAddress(const GlobalValue *GV, DebugLoc dl,
SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerExternalSymbol(SDValue Op, SelectionDAG &DAG) const;
- SDValue LowerShift(SDValue Op, SelectionDAG &DAG) const;
- SDValue BuildFILD(SDValue Op, EVT SrcVT, SDValue Chain, SDValue StackSlot,
- SelectionDAG &DAG) const;
- SDValue LowerBIT_CONVERT(SDValue op, SelectionDAG &DAG) const;
+ SDValue LowerShiftParts(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerBITCAST(SDValue op, SelectionDAG &DAG) const;
SDValue LowerSINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerUINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerUINT_TO_FP_i64(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFABS(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFNEG(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFCOPYSIGN(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerFGETSIGN(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerToBT(SDValue And, ISD::CondCode CC,
DebugLoc dl, SelectionDAG &DAG) const;
SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFRAME_TO_ARGS_OFFSET(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerEH_RETURN(SDValue Op, SelectionDAG &DAG) const;
- SDValue LowerTRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerINIT_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerADJUST_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerCTLZ(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerCTTZ(SDValue Op, SelectionDAG &DAG) const;
- SDValue LowerMUL_V2I64(SDValue Op, SelectionDAG &DAG) const;
- SDValue LowerSHL(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerADD(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerSUB(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerMUL(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerShift(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerXALUO(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerCMP_SWAP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerLOAD_SUB(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerREADCYCLECOUNTER(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerMEMBARRIER(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerATOMIC_FENCE(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerSIGN_EXTEND_INREG(SDValue Op, SelectionDAG &DAG) const;
// Utility functions to help LowerVECTOR_SHUFFLE
SDValue LowerVECTOR_SHUFFLEv8i16(SDValue Op, SelectionDAG &DAG) const;
const SmallVectorImpl<SDValue> &OutVals,
DebugLoc dl, SelectionDAG &DAG) const;
+ virtual bool isUsedByReturnOnly(SDNode *N) const;
+
+ virtual bool mayBeEmittedAsTailCall(CallInst *CI) const;
+
+ virtual EVT
+ getTypeForExtArgOrReturn(LLVMContext &Context, EVT VT,
+ ISD::NodeType ExtendKind) const;
+
virtual bool
- CanLowerReturn(CallingConv::ID CallConv, bool isVarArg,
- const SmallVectorImpl<ISD::OutputArg> &Outs,
- LLVMContext &Context) const;
+ CanLowerReturn(CallingConv::ID CallConv, MachineFunction &MF,
+ bool isVarArg,
+ const SmallVectorImpl<ISD::OutputArg> &Outs,
+ LLVMContext &Context) const;
void ReplaceATOMIC_BINARY_64(SDNode *N, SmallVectorImpl<SDValue> &Results,
SelectionDAG &DAG, unsigned NewOp) const;
MachineBasicBlock *EmitPCMP(MachineInstr *BInstr, MachineBasicBlock *BB,
unsigned argNum, bool inMem) const;
+ /// Utility functions to emit monitor and mwait instructions. These
+ /// need to make sure that the arguments to the intrinsic are in the
+ /// correct registers.
+ MachineBasicBlock *EmitMonitor(MachineInstr *MI,
+ MachineBasicBlock *BB) const;
+ MachineBasicBlock *EmitMwait(MachineInstr *MI, MachineBasicBlock *BB) const;
+
/// Utility function to emit atomic bitwise operations (and, or, xor).
/// It takes the bitwise instruction to expand, the associated machine basic
/// block, and the associated X86 opcodes for reg/reg and reg/imm.
MachineBasicBlock *EmitLoweredSelect(MachineInstr *I,
MachineBasicBlock *BB) const;
- MachineBasicBlock *EmitLoweredMingwAlloca(MachineInstr *MI,
+ MachineBasicBlock *EmitLoweredWinAlloca(MachineInstr *MI,
MachineBasicBlock *BB) const;
+ MachineBasicBlock *EmitLoweredSegAlloca(MachineInstr *MI,
+ MachineBasicBlock *BB,
+ bool Is64Bit) const;
+
MachineBasicBlock *EmitLoweredTLSCall(MachineInstr *MI,
MachineBasicBlock *BB) const;
+ MachineBasicBlock *emitLoweredTLSAddr(MachineInstr *MI,
+ MachineBasicBlock *BB) const;
+
/// Emit nodes that will be selected as "test Op0,Op0", or something
/// equivalent, for use with the given x86 condition code.
SDValue EmitTest(SDValue Op0, unsigned X86CC, SelectionDAG &DAG) const;