#define LLVM_TARGET_POWERPC_PPC32ISELLOWERING_H
#include "PPC.h"
+#include "PPCInstrInfo.h"
#include "PPCRegisterInfo.h"
#include "PPCSubtarget.h"
+#include "llvm/CodeGen/CallingConvLower.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/Target/TargetLowering.h"
/// Return with a flag operand, matched by 'blr'
RET_FLAG,
- /// R32 = MFCR(CRREG, INFLAG) - Represents the MFCRpseud/MFOCRF
- /// instructions. This copies the bits corresponding to the specified
- /// CRREG into the resultant GPR. Bits corresponding to other CR regs
- /// are undefined.
- MFCR,
+ /// R32 = MFOCRF(CRREG, INFLAG) - Represents the MFOCRF instruction.
+ /// This copies the bits corresponding to the specified CRREG into the
+ /// resultant GPR. Bits corresponding to other CR regs are undefined.
+ MFOCRF,
+
+ // FIXME: Remove these once the ANDI glue bug is fixed:
+ /// i1 = ANDIo_1_[EQ|GT]_BIT(i32 or i64 x) - Represents the result of the
+ /// eq or gt bit of CR0 after executing andi. x, 1. This is used to
+ /// implement truncation of i32 or i64 to i1.
+ ANDIo_1_EQ_BIT, ANDIo_1_GT_BIT,
// EH_SJLJ_SETJMP - SjLj exception handling setjmp.
EH_SJLJ_SETJMP,
/// an optional input flag argument.
COND_BRANCH,
+ /// CHAIN = BDNZ CHAIN, DESTBB - These are used to create counter-based
+ /// loops.
+ BDNZ, BDZ,
+
/// F8RC = FADDRTZ F8RC, F8RC - This is an FADD done with rounding
/// towards zero. Used only as part of the long double-to-int
/// conversion sequence.
CR6SET,
CR6UNSET,
+ /// GPRC = address of _GLOBAL_OFFSET_TABLE_. Used by initial-exec TLS
+ /// on PPC32.
+ PPC32_GOT,
+
/// G8RC = ADDIS_GOT_TPREL_HA %X2, Symbol - Used by the initial-exec
/// TLS model, produces an ADDIS8 instruction that adds the GOT
- /// base to sym@got@tprel@ha.
+ /// base to sym\@got\@tprel\@ha.
ADDIS_GOT_TPREL_HA,
/// G8RC = LD_GOT_TPREL_L Symbol, G8RReg - Used by the initial-exec
/// TLS model, produces a LD instruction with base register G8RReg
- /// and offset sym@got@tprel@l. This completes the addition that
+ /// and offset sym\@got\@tprel\@l. This completes the addition that
/// finds the offset of "sym" relative to the thread pointer.
LD_GOT_TPREL_L,
/// G8RC = ADD_TLS G8RReg, Symbol - Used by the initial-exec TLS
/// model, produces an ADD instruction that adds the contents of
/// G8RReg to the thread pointer. Symbol contains a relocation
- /// sym@tls which is to be replaced by the thread pointer and
+ /// sym\@tls which is to be replaced by the thread pointer and
/// identifies to the linker that the instruction is part of a
/// TLS sequence.
ADD_TLS,
/// G8RC = ADDIS_TLSGD_HA %X2, Symbol - For the general-dynamic TLS
/// model, produces an ADDIS8 instruction that adds the GOT base
- /// register to sym@got@tlsgd@ha.
+ /// register to sym\@got\@tlsgd\@ha.
ADDIS_TLSGD_HA,
/// G8RC = ADDI_TLSGD_L G8RReg, Symbol - For the general-dynamic TLS
/// model, produces an ADDI8 instruction that adds G8RReg to
- /// sym@got@tlsgd@l.
+ /// sym\@got\@tlsgd\@l.
ADDI_TLSGD_L,
/// G8RC = GET_TLS_ADDR %X3, Symbol - For the general-dynamic TLS
- /// model, produces a call to __tls_get_addr(sym@tlsgd).
+ /// model, produces a call to __tls_get_addr(sym\@tlsgd).
GET_TLS_ADDR,
/// G8RC = ADDIS_TLSLD_HA %X2, Symbol - For the local-dynamic TLS
/// model, produces an ADDIS8 instruction that adds the GOT base
- /// register to sym@got@tlsld@ha.
+ /// register to sym\@got\@tlsld\@ha.
ADDIS_TLSLD_HA,
/// G8RC = ADDI_TLSLD_L G8RReg, Symbol - For the local-dynamic TLS
/// model, produces an ADDI8 instruction that adds G8RReg to
- /// sym@got@tlsld@l.
+ /// sym\@got\@tlsld\@l.
ADDI_TLSLD_L,
/// G8RC = GET_TLSLD_ADDR %X3, Symbol - For the local-dynamic TLS
- /// model, produces a call to __tls_get_addr(sym@tlsld).
+ /// model, produces a call to __tls_get_addr(sym\@tlsld).
GET_TLSLD_ADDR,
/// G8RC = ADDIS_DTPREL_HA %X3, Symbol, Chain - For the
/// local-dynamic TLS model, produces an ADDIS8 instruction
- /// that adds X3 to sym@dtprel@ha. The Chain operand is needed
+ /// that adds X3 to sym\@dtprel\@ha. The Chain operand is needed
/// to tie this in place following a copy to %X3 from the result
/// of a GET_TLSLD_ADDR.
ADDIS_DTPREL_HA,
/// G8RC = ADDI_DTPREL_L G8RReg, Symbol - For the local-dynamic TLS
/// model, produces an ADDI8 instruction that adds G8RReg to
- /// sym@got@dtprel@l.
+ /// sym\@got\@dtprel\@l.
ADDI_DTPREL_L,
/// VRRC = VADD_SPLAT Elt, EltSize - Temporary node to be expanded
/// optimizations due to constant folding.
VADD_SPLAT,
+ /// CHAIN = SC CHAIN, Imm128 - System call. The 7-bit unsigned
+ /// operand identifies the operating system entry point.
+ SC,
+
/// CHAIN = STBRX CHAIN, GPRC, Ptr, Type - This is a
/// byte-swapping store instruction. It byte-swaps the low "Type" bits of
/// the GPRC input, then stores it through Ptr. Type can be either i16 or
/// G8RC = ADDIS_TOC_HA %X2, Symbol - For medium and large code model,
/// produces an ADDIS8 instruction that adds the TOC base register to
- /// sym@toc@ha.
+ /// sym\@toc\@ha.
ADDIS_TOC_HA,
/// G8RC = LD_TOC_L Symbol, G8RReg - For medium and large code model,
/// produces a LD instruction with base register G8RReg and offset
- /// sym@toc@l. Preceded by an ADDIS_TOC_HA to form a full 32-bit offset.
+ /// sym\@toc\@l. Preceded by an ADDIS_TOC_HA to form a full 32-bit offset.
LD_TOC_L,
/// G8RC = ADDI_TOC_L G8RReg, Symbol - For medium code model, produces
- /// an ADDI8 instruction that adds G8RReg to sym@toc@l.
+ /// an ADDI8 instruction that adds G8RReg to sym\@toc\@l.
/// Preceded by an ADDIS_TOC_HA to form a full 32-bit offset.
ADDI_TOC_L
};
class PPCTargetLowering : public TargetLowering {
const PPCSubtarget &PPCSubTarget;
- const PPCRegisterInfo *PPCRegInfo;
public:
explicit PPCTargetLowering(PPCTargetMachine &TM);
virtual MVT getScalarShiftAmountTy(EVT LHSTy) const { return MVT::i32; }
/// getSetCCResultType - Return the ISD::SETCC ValueType
- virtual EVT getSetCCResultType(EVT VT) const;
+ virtual EVT getSetCCResultType(LLVMContext &Context, EVT VT) const;
/// getPreIndexedAddressParts - returns true by value, base pointer and
/// offset pointer and addressing mode by reference if the node's address
/// SelectAddressRegImm - Returns true if the address N can be represented
/// by a base register plus a signed 16-bit displacement [r+imm], and if it
- /// is not better represented as reg+reg.
+ /// is not better represented as reg+reg. If Aligned is true, only accept
+ /// displacements suitable for STD and friends, i.e. multiples of 4.
bool SelectAddressRegImm(SDValue N, SDValue &Disp, SDValue &Base,
- SelectionDAG &DAG) const;
+ SelectionDAG &DAG, bool Aligned) const;
/// SelectAddressRegRegOnly - Given the specified addressed, force it to be
/// represented as an indexed [r+r] operation.
bool SelectAddressRegRegOnly(SDValue N, SDValue &Base, SDValue &Index,
SelectionDAG &DAG) const;
- /// SelectAddressRegImmShift - Returns true if the address N can be
- /// represented by a base register plus a signed 14-bit displacement
- /// [r+imm*4]. Suitable for use by STD and friends.
- bool SelectAddressRegImmShift(SDValue N, SDValue &Disp, SDValue &Base,
- SelectionDAG &DAG) const;
-
Sched::Preference getSchedulingPreference(SDNode *N) const;
/// LowerOperation - Provide custom lowering hooks for some operations.
std::pair<unsigned, const TargetRegisterClass*>
getRegForInlineAsmConstraint(const std::string &Constraint,
- EVT VT) const;
+ MVT VT) const;
/// getByValTypeAlignment - Return the desired alignment for ByVal aggregate
/// function arguments in the caller parameter area. This is the actual
/// by AM is legal for this target, for a load/store of the specified type.
virtual bool isLegalAddressingMode(const AddrMode &AM, Type *Ty)const;
- /// isLegalAddressImmediate - Return true if the integer value can be used
- /// as the offset of the target addressing mode for load / store of the
- /// given type.
- virtual bool isLegalAddressImmediate(int64_t V, Type *Ty) const;
-
- /// isLegalAddressImmediate - Return true if the GlobalValue can be used as
- /// the offset of the target addressing mode.
- virtual bool isLegalAddressImmediate(GlobalValue *GV) const;
+ /// isLegalICmpImmediate - Return true if the specified immediate is legal
+ /// icmp immediate, that is the target has icmp instructions which can
+ /// compare a register against the immediate without having to materialize
+ /// the immediate into a register.
+ bool isLegalICmpImmediate(int64_t Imm) const override;
+
+ /// isLegalAddImmediate - Return true if the specified immediate is legal
+ /// add immediate, that is the target has add instructions which can
+ /// add a register and the immediate without having to materialize
+ /// the immediate into a register.
+ bool isLegalAddImmediate(int64_t Imm) const override;
+
+ /// isTruncateFree - Return true if it's free to truncate a value of
+ /// type Ty1 to type Ty2. e.g. On PPC it's free to truncate a i64 value in
+ /// register X1 to i32 by referencing its sub-register R1.
+ bool isTruncateFree(Type *Ty1, Type *Ty2) const override;
+ bool isTruncateFree(EVT VT1, EVT VT2) const override;
+
+ /// \brief Returns true if it is beneficial to convert a load of a constant
+ /// to just the constant itself.
+ bool shouldConvertConstantLoadToIntImm(const APInt &Imm,
+ Type *Ty) const override;
virtual bool isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const;
/// It returns EVT::Other if the type should be determined using generic
/// target-independent logic.
virtual EVT
- getOptimalMemOpType(uint64_t Size, unsigned DstAlign, unsigned SrcAlign,
+ getOptimalMemOpType(uint64_t Size, unsigned DstAlign, unsigned SrcAlign,
bool IsMemset, bool ZeroMemset, bool MemcpyStrSrc,
MachineFunction &MF) const;
/// Is unaligned memory access allowed for the given type, and is it fast
/// relative to software emulation.
- virtual bool allowsUnalignedMemoryAccesses(EVT VT, bool *Fast = 0) const;
+ virtual bool allowsUnalignedMemoryAccesses(EVT VT,
+ unsigned AddrSpace,
+ bool *Fast = nullptr) const;
- /// isFMAFasterThanMulAndAdd - Return true if an FMA operation is faster than
- /// a pair of mul and add instructions. fmuladd intrinsics will be expanded to
- /// FMAs when this method returns true (and FMAs are legal), otherwise fmuladd
- /// is expanded to mul + add.
- virtual bool isFMAFasterThanMulAndAdd(EVT VT) const;
+ /// isFMAFasterThanFMulAndFAdd - Return true if an FMA operation is faster
+ /// than a pair of fmul and fadd instructions. fmuladd intrinsics will be
+ /// expanded to FMAs when this method returns true, otherwise fmuladd is
+ /// expanded to fmul + fadd.
+ virtual bool isFMAFasterThanFMulAndFAdd(EVT VT) const;
+
+ // Should we expand the build vector with shuffles?
+ virtual bool
+ shouldExpandBuildVectorWithShuffles(EVT VT,
+ unsigned DefinedValues) const;
+
+ /// createFastISel - This method returns a target-specific FastISel object,
+ /// or null if the target does not support "fast" instruction selection.
+ virtual FastISel *createFastISel(FunctionLoweringInfo &FuncInfo,
+ const TargetLibraryInfo *LibInfo) const;
private:
SDValue getFramePointerFrameIndex(SelectionDAG & DAG) const;
SDValue &LROpOut,
SDValue &FPOpOut,
bool isDarwinABI,
- DebugLoc dl) const;
+ SDLoc dl) const;
SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const;
const PPCSubtarget &Subtarget) const;
SDValue LowerVAARG(SDValue Op, SelectionDAG &DAG,
const PPCSubtarget &Subtarget) const;
+ SDValue LowerVACOPY(SDValue Op, SelectionDAG &DAG,
+ const PPCSubtarget &Subtarget) const;
SDValue LowerSTACKRESTORE(SDValue Op, SelectionDAG &DAG,
const PPCSubtarget &Subtarget) const;
SDValue LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG,
const PPCSubtarget &Subtarget) const;
+ SDValue LowerLOAD(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerSTORE(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerTRUNCATE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
- SDValue LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG, DebugLoc dl) const;
+ SDValue LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG, SDLoc dl) const;
SDValue LowerINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSHL_PARTS(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSCALAR_TO_VECTOR(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerSIGN_EXTEND_INREG(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerMUL(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerCallResult(SDValue Chain, SDValue InFlag,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
- SDValue FinishCall(CallingConv::ID CallConv, DebugLoc dl, bool isTailCall,
+ SDValue FinishCall(CallingConv::ID CallConv, SDLoc dl, bool isTailCall,
bool isVarArg,
SelectionDAG &DAG,
SmallVector<std::pair<unsigned, SDValue>, 8>
LowerFormalArguments(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
virtual SDValue
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
- DebugLoc dl, SelectionDAG &DAG) const;
+ SDLoc dl, SelectionDAG &DAG) const;
SDValue
extendArgForPPC64(ISD::ArgFlagsTy Flags, EVT ObjectVT, SelectionDAG &DAG,
- SDValue ArgVal, DebugLoc dl) const;
+ SDValue ArgVal, SDLoc dl) const;
void
setMinReservedArea(MachineFunction &MF, SelectionDAG &DAG,
LowerFormalArguments_Darwin(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
LowerFormalArguments_64SVR4(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
LowerFormalArguments_32SVR4(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
createMemcpyOutsideCallSeq(SDValue Arg, SDValue PtrOff,
SDValue CallSeqStart, ISD::ArgFlagsTy Flags,
- SelectionDAG &DAG, DebugLoc dl) const;
+ SelectionDAG &DAG, SDLoc dl) const;
SDValue
LowerCall_Darwin(SDValue Chain, SDValue Callee,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
LowerCall_64SVR4(SDValue Chain, SDValue Callee,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
LowerCall_32SVR4(SDValue Chain, SDValue Callee, CallingConv::ID CallConv,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
- DebugLoc dl, SelectionDAG &DAG,
+ SDLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue lowerEH_SJLJ_SETJMP(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerEH_SJLJ_LONGJMP(SDValue Op, SelectionDAG &DAG) const;
+ SDValue DAGCombineExtBoolTrunc(SDNode *N, DAGCombinerInfo &DCI) const;
+ SDValue DAGCombineTruncBoolExt(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue DAGCombineFastRecip(SDValue Op, DAGCombinerInfo &DCI) const;
SDValue DAGCombineFastRecipFSQRT(SDValue Op, DAGCombinerInfo &DCI) const;
+
+ CCAssignFn *useFastISelCCs(unsigned Flag) const;
};
+
+ namespace PPC {
+ FastISel *createFastISel(FunctionLoweringInfo &FuncInfo,
+ const TargetLibraryInfo *LibInfo);
+ }
+
+ bool CC_PPC32_SVR4_Custom_Dummy(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
+ CCValAssign::LocInfo &LocInfo,
+ ISD::ArgFlagsTy &ArgFlags,
+ CCState &State);
+
+ bool CC_PPC32_SVR4_Custom_AlignArgRegs(unsigned &ValNo, MVT &ValVT,
+ MVT &LocVT,
+ CCValAssign::LocInfo &LocInfo,
+ ISD::ArgFlagsTy &ArgFlags,
+ CCState &State);
+
+ bool CC_PPC32_SVR4_Custom_AlignFPArgRegs(unsigned &ValNo, MVT &ValVT,
+ MVT &LocVT,
+ CCValAssign::LocInfo &LocInfo,
+ ISD::ArgFlagsTy &ArgFlags,
+ CCState &State);
}
#endif // LLVM_TARGET_POWERPC_PPC32ISELLOWERING_H
projects / oota-llvm.git / blobdiff