llvm-6502/lib/Target/PowerPC/PPCISelLowering.h

604 lines
27 KiB
C
Raw Normal View History

//===-- PPCISelLowering.h - PPC32 DAG Lowering Interface --------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the interfaces that PPC uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_TARGET_POWERPC_PPC32ISELLOWERING_H
#define LLVM_TARGET_POWERPC_PPC32ISELLOWERING_H
#include "PPC.h"
#include "PPCSubtarget.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/Target/TargetLowering.h"
namespace llvm {
namespace PPCISD {
enum NodeType {
// Start the numbering where the builtin ops and target ops leave off.
FIRST_NUMBER = ISD::BUILTIN_OP_END,
/// FSEL - Traditional three-operand fsel node.
///
FSEL,
/// FCFID - The FCFID instruction, taking an f64 operand and producing
/// and f64 value containing the FP representation of the integer that
/// was temporarily in the f64 operand.
FCFID,
/// FCTI[D,W]Z - The FCTIDZ and FCTIWZ instructions, taking an f32 or f64
/// operand, producing an f64 value containing the integer representation
/// of that FP value.
FCTIDZ, FCTIWZ,
/// STFIWX - The STFIWX instruction. The first operand is an input token
/// chain, then an f64 value to store, then an address to store it to.
STFIWX,
// VMADDFP, VNMSUBFP - The VMADDFP and VNMSUBFP instructions, taking
// three v4f32 operands and producing a v4f32 result.
VMADDFP, VNMSUBFP,
/// VPERM - The PPC VPERM Instruction.
///
VPERM,
/// Hi/Lo - These represent the high and low 16-bit parts of a global
/// address respectively. These nodes have two operands, the first of
/// which must be a TargetGlobalAddress, and the second of which must be a
/// Constant. Selected naively, these turn into 'lis G+C' and 'li G+C',
/// though these are usually folded into other nodes.
Hi, Lo,
TOC_ENTRY,
/// The following three target-specific nodes are used for calls through
/// function pointers in the 64-bit SVR4 ABI.
/// Restore the TOC from the TOC save area of the current stack frame.
/// This is basically a hard coded load instruction which additionally
/// takes/produces a flag.
TOC_RESTORE,
/// Like a regular LOAD but additionally taking/producing a flag.
LOAD,
/// LOAD into r2 (also taking/producing a flag). Like TOC_RESTORE, this is
/// a hard coded load instruction.
LOAD_TOC,
/// OPRC, CHAIN = DYNALLOC(CHAIN, NEGSIZE, FRAME_INDEX)
/// This instruction is lowered in PPCRegisterInfo::eliminateFrameIndex to
/// compute an allocation on the stack.
DYNALLOC,
/// GlobalBaseReg - On Darwin, this node represents the result of the mflr
/// at function entry, used for PIC code.
GlobalBaseReg,
/// These nodes represent the 32-bit PPC shifts that operate on 6-bit
/// shift amounts. These nodes are generated by the multi-precision shift
/// code.
SRL, SRA, SHL,
/// EXTSW_32 - This is the EXTSW instruction for use with "32-bit"
/// registers.
EXTSW_32,
/// CALL - A direct function call.
/// CALL_NOP_SVR4 is a call with the special NOP which follows 64-bit
/// SVR4 calls.
CALL_Darwin, CALL_SVR4, CALL_NOP_SVR4,
/// NOP - Special NOP which follows 64-bit SVR4 calls.
NOP,
/// CHAIN,FLAG = MTCTR(VAL, CHAIN[, INFLAG]) - Directly corresponds to a
/// MTCTR instruction.
MTCTR,
/// CHAIN,FLAG = BCTRL(CHAIN, INFLAG) - Directly corresponds to a
/// BCTRL instruction.
BCTRL_Darwin, BCTRL_SVR4,
/// 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,
/// RESVEC = VCMP(LHS, RHS, OPC) - Represents one of the altivec VCMP*
/// instructions. For lack of better number, we use the opcode number
/// encoding for the OPC field to identify the compare. For example, 838
/// is VCMPGTSH.
VCMP,
/// RESVEC, OUTFLAG = VCMPo(LHS, RHS, OPC) - Represents one of the
/// altivec VCMP*o instructions. For lack of better number, we use the
/// opcode number encoding for the OPC field to identify the compare. For
/// example, 838 is VCMPGTSH.
VCMPo,
/// CHAIN = COND_BRANCH CHAIN, CRRC, OPC, DESTBB [, INFLAG] - This
/// corresponds to the COND_BRANCH pseudo instruction. CRRC is the
/// condition register to branch on, OPC is the branch opcode to use (e.g.
/// PPC::BLE), DESTBB is the destination block to branch to, and INFLAG is
/// an optional input flag argument.
COND_BRANCH,
// The following 5 instructions are used only as part of the
// long double-to-int conversion sequence.
/// OUTFLAG = MFFS F8RC - This moves the FPSCR (not modelled) into the
/// register.
MFFS,
/// OUTFLAG = MTFSB0 INFLAG - This clears a bit in the FPSCR.
MTFSB0,
/// OUTFLAG = MTFSB1 INFLAG - This sets a bit in the FPSCR.
MTFSB1,
/// F8RC, OUTFLAG = FADDRTZ F8RC, F8RC, INFLAG - This is an FADD done with
/// rounding towards zero. It has flags added so it won't move past the
/// FPSCR-setting instructions.
FADDRTZ,
/// MTFSF = F8RC, INFLAG - This moves the register into the FPSCR.
MTFSF,
/// LARX = This corresponds to PPC l{w|d}arx instrcution: load and
/// reserve indexed. This is used to implement atomic operations.
LARX,
/// STCX = This corresponds to PPC stcx. instrcution: store conditional
/// indexed. This is used to implement atomic operations.
STCX,
/// TC_RETURN - A tail call return.
/// operand #0 chain
/// operand #1 callee (register or absolute)
/// operand #2 stack adjustment
/// operand #3 optional in flag
TC_RETURN,
/// ch, gl = CR6[UN]SET ch, inglue - Toggle CR bit 6 for SVR4 vararg calls
CR6SET,
CR6UNSET,
/// 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.
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
/// 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
/// identifies to the linker that the instruction is part of a
/// TLS sequence.
ADD_TLS,
This patch implements the general dynamic TLS model for 64-bit PowerPC. Given a thread-local symbol x with global-dynamic access, the generated code to obtain x's address is: Instruction Relocation Symbol addis ra,r2,x@got@tlsgd@ha R_PPC64_GOT_TLSGD16_HA x addi r3,ra,x@got@tlsgd@l R_PPC64_GOT_TLSGD16_L x bl __tls_get_addr(x@tlsgd) R_PPC64_TLSGD x R_PPC64_REL24 __tls_get_addr nop <use address in r3> The implementation borrows from the medium code model work for introducing special forms of ADDIS and ADDI into the DAG representation. This is made slightly more complicated by having to introduce a call to the external function __tls_get_addr. Using the full call machinery is overkill and, more importantly, makes it difficult to add a special relocation. So I've introduced another opcode GET_TLS_ADDR to represent the function call, and surrounded it with register copies to set up the parameter and return value. Most of the code is pretty straightforward. I ran into one peculiarity when I introduced a new PPC opcode BL8_NOP_ELF_TLSGD, which is just like BL8_NOP_ELF except that it takes another parameter to represent the symbol ("x" above) that requires a relocation on the call. Something in the TblGen machinery causes BL8_NOP_ELF and BL8_NOP_ELF_TLSGD to be treated identically during the emit phase, so this second operand was never visited to generate relocations. This is the reason for the slightly messy workaround in PPCMCCodeEmitter.cpp:getDirectBrEncoding(). Two new tests are included to demonstrate correct external assembly and correct generation of relocations using the integrated assembler. Comments welcome! Thanks, Bill git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169910 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-11 20:30:11 +00:00
/// 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.
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.
ADDI_TLSGD_L,
/// G8RC = GET_TLS_ADDR %X3, Symbol - For the general-dynamic TLS
/// 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.
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.
ADDI_TLSLD_L,
/// G8RC = GET_TLSLD_ADDR %X3, Symbol - For the local-dynamic TLS
/// 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
/// 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.
ADDI_DTPREL_L,
/// STD_32 - This is the STD instruction for use with "32-bit" registers.
STD_32 = ISD::FIRST_TARGET_MEMORY_OPCODE,
/// 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
/// i32.
STBRX,
/// GPRC, CHAIN = LBRX CHAIN, Ptr, Type - This is a
/// byte-swapping load instruction. It loads "Type" bits, byte swaps it,
/// then puts it in the bottom bits of the GPRC. TYPE can be either i16
/// or i32.
This patch implements medium code model support for 64-bit PowerPC. The default for 64-bit PowerPC is small code model, in which TOC entries must be addressable using a 16-bit offset from the TOC pointer. Additionally, only TOC entries are addressed via the TOC pointer. With medium code model, TOC entries and data sections can all be addressed via the TOC pointer using a 32-bit offset. Cooperation with the linker allows 16-bit offsets to be used when these are sufficient, reducing the number of extra instructions that need to be executed. Medium code model also does not generate explicit TOC entries in ".section toc" for variables that are wholly internal to the compilation unit. Consider a load of an external 4-byte integer. With small code model, the compiler generates: ld 3, .LC1@toc(2) lwz 4, 0(3) .section .toc,"aw",@progbits .LC1: .tc ei[TC],ei With medium model, it instead generates: addis 3, 2, .LC1@toc@ha ld 3, .LC1@toc@l(3) lwz 4, 0(3) .section .toc,"aw",@progbits .LC1: .tc ei[TC],ei Here .LC1@toc@ha is a relocation requesting the upper 16 bits of the 32-bit offset of ei's TOC entry from the TOC base pointer. Similarly, .LC1@toc@l is a relocation requesting the lower 16 bits. Note that if the linker determines that ei's TOC entry is within a 16-bit offset of the TOC base pointer, it will replace the "addis" with a "nop", and replace the "ld" with the identical "ld" instruction from the small code model example. Consider next a load of a function-scope static integer. For small code model, the compiler generates: ld 3, .LC1@toc(2) lwz 4, 0(3) .section .toc,"aw",@progbits .LC1: .tc test_fn_static.si[TC],test_fn_static.si .type test_fn_static.si,@object .local test_fn_static.si .comm test_fn_static.si,4,4 For medium code model, the compiler generates: addis 3, 2, test_fn_static.si@toc@ha addi 3, 3, test_fn_static.si@toc@l lwz 4, 0(3) .type test_fn_static.si,@object .local test_fn_static.si .comm test_fn_static.si,4,4 Again, the linker may replace the "addis" with a "nop", calculating only a 16-bit offset when this is sufficient. Note that it would be more efficient for the compiler to generate: addis 3, 2, test_fn_static.si@toc@ha lwz 4, test_fn_static.si@toc@l(3) The current patch does not perform this optimization yet. This will be addressed as a peephole optimization in a later patch. For the moment, the default code model for 64-bit PowerPC will remain the small code model. We plan to eventually change the default to medium code model, which matches current upstream GCC behavior. Note that the different code models are ABI-compatible, so code compiled with different models will be linked and execute correctly. I've tested the regression suite and the application/benchmark test suite in two ways: Once with the patch as submitted here, and once with additional logic to force medium code model as the default. The tests all compile cleanly, with one exception. The mandel-2 application test fails due to an unrelated ABI compatibility with passing complex numbers. It just so happens that small code model was incredibly lucky, in that temporary values in floating-point registers held the expected values needed by the external library routine that was called incorrectly. My current thought is to correct the ABI problems with _Complex before making medium code model the default, to avoid introducing this "regression." Here are a few comments on how the patch works, since the selection code can be difficult to follow: The existing logic for small code model defines three pseudo-instructions: LDtoc for most uses, LDtocJTI for jump table addresses, and LDtocCPT for constant pool addresses. These are expanded by SelectCodeCommon(). The pseudo-instruction approach doesn't work for medium code model, because we need to generate two instructions when we match the same pattern. Instead, new logic in PPCDAGToDAGISel::Select() intercepts the TOC_ENTRY node for medium code model, and generates an ADDIStocHA followed by either a LDtocL or an ADDItocL. These new node types correspond naturally to the sequences described above. The addis/ld sequence is generated for the following cases: * Jump table addresses * Function addresses * External global variables * Tentative definitions of global variables (common linkage) The addis/addi sequence is generated for the following cases: * Constant pool entries * File-scope static global variables * Function-scope static variables Expanding to the two-instruction sequences at select time exposes the instructions to subsequent optimization, particularly scheduling. The rest of the processing occurs at assembly time, in PPCAsmPrinter::EmitInstruction. Each of the instructions is converted to a "real" PowerPC instruction. When a TOC entry needs to be created, this is done here in the same manner as for the existing LDtoc, LDtocJTI, and LDtocCPT pseudo-instructions (I factored out a new routine to handle this). I had originally thought that if a TOC entry was needed for LDtocL or ADDItocL, it would already have been generated for the previous ADDIStocHA. However, at higher optimization levels, the ADDIStocHA may appear in a different block, which may be assembled textually following the block containing the LDtocL or ADDItocL. So it is necessary to include the possibility of creating a new TOC entry for those two instructions. Note that for LDtocL, we generate a new form of LD called LDrs. This allows specifying the @toc@l relocation for the offset field of the LD instruction (i.e., the offset is replaced by a SymbolLo relocation). When the peephole optimization described above is added, we will need to do similar things for all immediate-form load and store operations. The seven "mcm-n.ll" test cases are kept separate because otherwise the intermingling of various TOC entries and so forth makes the tests fragile and hard to understand. The above assumes use of an external assembler. For use of the integrated assembler, new relocations are added and used by PPCELFObjectWriter. Testing is done with "mcm-obj.ll", which tests for proper generation of the various relocations for the same sequences tested with the external assembler. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168708 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-27 17:35:46 +00:00
LBRX,
/// G8RC = ADDIS_TOC_HA %X2, Symbol - For medium code model, produces
/// an ADDIS8 instruction that adds the TOC base register to sym@toc@ha.
ADDIS_TOC_HA,
/// G8RC = LD_TOC_L Symbol, G8RReg - For medium 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.
LD_TOC_L,
/// G8RC = ADDI_TOC_L G8RReg, Symbol - For medium code model, produces
/// 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
};
}
/// Define some predicates that are used for node matching.
namespace PPC {
/// isVPKUHUMShuffleMask - Return true if this is the shuffle mask for a
/// VPKUHUM instruction.
bool isVPKUHUMShuffleMask(ShuffleVectorSDNode *N, bool isUnary);
/// isVPKUWUMShuffleMask - Return true if this is the shuffle mask for a
/// VPKUWUM instruction.
bool isVPKUWUMShuffleMask(ShuffleVectorSDNode *N, bool isUnary);
/// isVMRGLShuffleMask - Return true if this is a shuffle mask suitable for
/// a VRGL* instruction with the specified unit size (1,2 or 4 bytes).
bool isVMRGLShuffleMask(ShuffleVectorSDNode *N, unsigned UnitSize,
bool isUnary);
/// isVMRGHShuffleMask - Return true if this is a shuffle mask suitable for
/// a VRGH* instruction with the specified unit size (1,2 or 4 bytes).
bool isVMRGHShuffleMask(ShuffleVectorSDNode *N, unsigned UnitSize,
bool isUnary);
/// isVSLDOIShuffleMask - If this is a vsldoi shuffle mask, return the shift
/// amount, otherwise return -1.
int isVSLDOIShuffleMask(SDNode *N, bool isUnary);
/// isSplatShuffleMask - Return true if the specified VECTOR_SHUFFLE operand
/// specifies a splat of a single element that is suitable for input to
/// VSPLTB/VSPLTH/VSPLTW.
bool isSplatShuffleMask(ShuffleVectorSDNode *N, unsigned EltSize);
/// isAllNegativeZeroVector - Returns true if all elements of build_vector
/// are -0.0.
bool isAllNegativeZeroVector(SDNode *N);
/// getVSPLTImmediate - Return the appropriate VSPLT* immediate to splat the
/// specified isSplatShuffleMask VECTOR_SHUFFLE mask.
unsigned getVSPLTImmediate(SDNode *N, unsigned EltSize);
/// get_VSPLTI_elt - If this is a build_vector of constants which can be
/// formed by using a vspltis[bhw] instruction of the specified element
/// size, return the constant being splatted. The ByteSize field indicates
/// the number of bytes of each element [124] -> [bhw].
SDValue get_VSPLTI_elt(SDNode *N, unsigned ByteSize, SelectionDAG &DAG);
}
class PPCTargetLowering : public TargetLowering {
const PPCSubtarget &PPCSubTarget;
public:
explicit PPCTargetLowering(PPCTargetMachine &TM);
/// getTargetNodeName() - This method returns the name of a target specific
/// DAG node.
virtual const char *getTargetNodeName(unsigned Opcode) const;
virtual MVT getShiftAmountTy(EVT LHSTy) const { return MVT::i32; }
/// getSetCCResultType - Return the ISD::SETCC ValueType
virtual EVT getSetCCResultType(EVT VT) const;
/// getPreIndexedAddressParts - returns true by value, base pointer and
/// offset pointer and addressing mode by reference if the node's address
/// can be legally represented as pre-indexed load / store address.
virtual bool getPreIndexedAddressParts(SDNode *N, SDValue &Base,
SDValue &Offset,
ISD::MemIndexedMode &AM,
SelectionDAG &DAG) const;
/// SelectAddressRegReg - Given the specified addressed, check to see if it
/// can be represented as an indexed [r+r] operation. Returns false if it
/// can be more efficiently represented with [r+imm].
bool SelectAddressRegReg(SDValue N, SDValue &Base, SDValue &Index,
SelectionDAG &DAG) const;
/// 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.
bool SelectAddressRegImm(SDValue N, SDValue &Disp, SDValue &Base,
SelectionDAG &DAG) 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.
///
virtual SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const;
/// ReplaceNodeResults - Replace the results of node with an illegal result
/// type with new values built out of custom code.
///
virtual void ReplaceNodeResults(SDNode *N, SmallVectorImpl<SDValue>&Results,
SelectionDAG &DAG) const;
virtual SDValue PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) const;
virtual void computeMaskedBitsForTargetNode(const SDValue Op,
APInt &KnownZero,
APInt &KnownOne,
const SelectionDAG &DAG,
unsigned Depth = 0) const;
virtual MachineBasicBlock *
EmitInstrWithCustomInserter(MachineInstr *MI,
MachineBasicBlock *MBB) const;
MachineBasicBlock *EmitAtomicBinary(MachineInstr *MI,
MachineBasicBlock *MBB, bool is64Bit,
unsigned BinOpcode) const;
MachineBasicBlock *EmitPartwordAtomicBinary(MachineInstr *MI,
MachineBasicBlock *MBB,
bool is8bit, unsigned Opcode) const;
ConstraintType getConstraintType(const std::string &Constraint) const;
/// Examine constraint string and operand type and determine a weight value.
/// The operand object must already have been set up with the operand type.
ConstraintWeight getSingleConstraintMatchWeight(
AsmOperandInfo &info, const char *constraint) const;
std::pair<unsigned, const TargetRegisterClass*>
getRegForInlineAsmConstraint(const std::string &Constraint,
EVT VT) const;
/// getByValTypeAlignment - Return the desired alignment for ByVal aggregate
/// function arguments in the caller parameter area. This is the actual
/// alignment, not its logarithm.
unsigned getByValTypeAlignment(Type *Ty) const;
/// LowerAsmOperandForConstraint - Lower the specified operand into the Ops
/// vector. If it is invalid, don't add anything to Ops.
virtual void LowerAsmOperandForConstraint(SDValue Op,
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, 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;
virtual bool isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const;
/// getOptimalMemOpType - Returns the target specific optimal type for load
/// and store operations as a result of memset, memcpy, and memmove
/// lowering. If DstAlign is zero that means it's safe to destination
/// alignment can satisfy any constraint. Similarly if SrcAlign is zero it
/// means there isn't a need to check it against alignment requirement,
/// probably because the source does not need to be loaded. If 'IsMemset' is
/// true, that means it's expanding a memset. If 'ZeroMemset' is true, that
/// means it's a memset of zero. 'MemcpyStrSrc' indicates whether the memcpy
/// source is constant so it does not need to be loaded.
/// 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,
bool IsMemset, bool ZeroMemset, bool MemcpyStrSrc,
MachineFunction &MF) 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;
private:
SDValue getFramePointerFrameIndex(SelectionDAG & DAG) const;
SDValue getReturnAddrFrameIndex(SelectionDAG & DAG) const;
bool
IsEligibleForTailCallOptimization(SDValue Callee,
CallingConv::ID CalleeCC,
bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
SelectionDAG& DAG) const;
SDValue EmitTailCallLoadFPAndRetAddr(SelectionDAG & DAG,
int SPDiff,
SDValue Chain,
SDValue &LROpOut,
SDValue &FPOpOut,
bool isDarwinABI,
DebugLoc dl) const;
SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINIT_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerADJUST_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerVASTART(SDValue Op, SelectionDAG &DAG,
const PPCSubtarget &Subtarget) const;
SDValue LowerVAARG(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 LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG, DebugLoc dl) const;
SDValue LowerSINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSHL_PARTS(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSRL_PARTS(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSRA_PARTS(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBUILD_VECTOR(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 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,
SmallVectorImpl<SDValue> &InVals) const;
SDValue FinishCall(CallingConv::ID CallConv, DebugLoc dl, bool isTailCall,
bool isVarArg,
SelectionDAG &DAG,
SmallVector<std::pair<unsigned, SDValue>, 8>
&RegsToPass,
SDValue InFlag, SDValue Chain,
SDValue &Callee,
int SPDiff, unsigned NumBytes,
const SmallVectorImpl<ISD::InputArg> &Ins,
SmallVectorImpl<SDValue> &InVals) const;
virtual SDValue
LowerFormalArguments(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
DebugLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
virtual SDValue
LowerCall(TargetLowering::CallLoweringInfo &CLI,
SmallVectorImpl<SDValue> &InVals) const;
virtual bool
CanLowerReturn(CallingConv::ID CallConv, MachineFunction &MF,
bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
LLVMContext &Context) const;
virtual SDValue
LowerReturn(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
DebugLoc dl, SelectionDAG &DAG) const;
SDValue
extendArgForPPC64(ISD::ArgFlagsTy Flags, EVT ObjectVT, SelectionDAG &DAG,
SDValue ArgVal, DebugLoc dl) const;
void
setMinReservedArea(MachineFunction &MF, SelectionDAG &DAG,
unsigned nAltivecParamsAtEnd,
unsigned MinReservedArea, bool isPPC64) const;
SDValue
LowerFormalArguments_Darwin(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
DebugLoc 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,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
LowerFormalArguments_32SVR4(SDValue Chain,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
DebugLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
createMemcpyOutsideCallSeq(SDValue Arg, SDValue PtrOff,
SDValue CallSeqStart, ISD::ArgFlagsTy Flags,
SelectionDAG &DAG, DebugLoc dl) const;
SDValue
LowerCall_Darwin(SDValue Chain, SDValue Callee,
CallingConv::ID CallConv,
bool isVarArg, bool isTailCall,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
DebugLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
LowerCall_64SVR4(SDValue Chain, SDValue Callee,
CallingConv::ID CallConv,
bool isVarArg, bool isTailCall,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
DebugLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
SDValue
LowerCall_32SVR4(SDValue Chain, SDValue Callee, CallingConv::ID CallConv,
bool isVarArg, bool isTailCall,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
DebugLoc dl, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const;
};
}
#endif // LLVM_TARGET_POWERPC_PPC32ISELLOWERING_H