mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-11-03 14:21:30 +00:00
de2b151dbf
float t1(int argc) {
return (argc == 1123) ? 1.234f : 2.38213f;
}
We would generate truly awful code on ARM (those with a weak stomach should look
away):
_t1:
movw r1, #1123
movs r2, #1
movs r3, #0
cmp r0, r1
mov.w r0, #0
it eq
moveq r0, r2
movs r1, #4
cmp r0, #0
it ne
movne r3, r1
adr r0, #LCPI1_0
ldr r0, [r0, r3]
bx lr
The problem was that legalization was creating a cascade of SELECT_CC nodes, for
for the comparison of "argc == 1123" which was fed into a SELECT node for the ?:
statement which was itself converted to a SELECT_CC node. This is because the
ARM back-end doesn't have custom lowering for SELECT nodes, so it used the
default "Expand".
I added a fairly simple "LowerSELECT" to the ARM back-end. It takes care of this
testcase, but can obviously be expanded to include more cases.
Now we generate this, which looks optimal to me:
_t1:
movw r1, #1123
movs r2, #0
cmp r0, r1
adr r0, #LCPI0_0
it eq
moveq r2, #4
ldr r0, [r0, r2]
bx lr
.align 2
LCPI0_0:
.long 1075344593 @ float 2.382130e+00
.long 1067316150 @ float 1.234000e+00
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110799 91177308-0d34-0410-b5e6-96231b3b80d8
413 lines
18 KiB
C++
413 lines
18 KiB
C++
//===-- ARMISelLowering.h - ARM 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 ARM uses to lower LLVM code into a
|
|
// selection DAG.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef ARMISELLOWERING_H
|
|
#define ARMISELLOWERING_H
|
|
|
|
#include "ARMSubtarget.h"
|
|
#include "llvm/Target/TargetLowering.h"
|
|
#include "llvm/Target/TargetRegisterInfo.h"
|
|
#include "llvm/CodeGen/FastISel.h"
|
|
#include "llvm/CodeGen/SelectionDAG.h"
|
|
#include "llvm/CodeGen/CallingConvLower.h"
|
|
#include <vector>
|
|
|
|
namespace llvm {
|
|
class ARMConstantPoolValue;
|
|
|
|
namespace ARMISD {
|
|
// ARM Specific DAG Nodes
|
|
enum NodeType {
|
|
// Start the numbering where the builtin ops and target ops leave off.
|
|
FIRST_NUMBER = ISD::BUILTIN_OP_END,
|
|
|
|
Wrapper, // Wrapper - A wrapper node for TargetConstantPool,
|
|
// TargetExternalSymbol, and TargetGlobalAddress.
|
|
WrapperJT, // WrapperJT - A wrapper node for TargetJumpTable
|
|
|
|
CALL, // Function call.
|
|
CALL_PRED, // Function call that's predicable.
|
|
CALL_NOLINK, // Function call with branch not branch-and-link.
|
|
tCALL, // Thumb function call.
|
|
BRCOND, // Conditional branch.
|
|
BR_JT, // Jumptable branch.
|
|
BR2_JT, // Jumptable branch (2 level - jumptable entry is a jump).
|
|
RET_FLAG, // Return with a flag operand.
|
|
|
|
PIC_ADD, // Add with a PC operand and a PIC label.
|
|
|
|
CMP, // ARM compare instructions.
|
|
CMPZ, // ARM compare that sets only Z flag.
|
|
CMPFP, // ARM VFP compare instruction, sets FPSCR.
|
|
CMPFPw0, // ARM VFP compare against zero instruction, sets FPSCR.
|
|
FMSTAT, // ARM fmstat instruction.
|
|
CMOV, // ARM conditional move instructions.
|
|
CNEG, // ARM conditional negate instructions.
|
|
|
|
BCC_i64,
|
|
|
|
RBIT, // ARM bitreverse instruction
|
|
|
|
FTOSI, // FP to sint within a FP register.
|
|
FTOUI, // FP to uint within a FP register.
|
|
SITOF, // sint to FP within a FP register.
|
|
UITOF, // uint to FP within a FP register.
|
|
|
|
SRL_FLAG, // V,Flag = srl_flag X -> srl X, 1 + save carry out.
|
|
SRA_FLAG, // V,Flag = sra_flag X -> sra X, 1 + save carry out.
|
|
RRX, // V = RRX X, Flag -> srl X, 1 + shift in carry flag.
|
|
|
|
VMOVRRD, // double to two gprs.
|
|
VMOVDRR, // Two gprs to double.
|
|
|
|
EH_SJLJ_SETJMP, // SjLj exception handling setjmp.
|
|
EH_SJLJ_LONGJMP, // SjLj exception handling longjmp.
|
|
|
|
TC_RETURN, // Tail call return pseudo.
|
|
|
|
THREAD_POINTER,
|
|
|
|
DYN_ALLOC, // Dynamic allocation on the stack.
|
|
|
|
MEMBARRIER, // Memory barrier
|
|
SYNCBARRIER, // Memory sync barrier
|
|
|
|
VCEQ, // Vector compare equal.
|
|
VCGE, // Vector compare greater than or equal.
|
|
VCGEU, // Vector compare unsigned greater than or equal.
|
|
VCGT, // Vector compare greater than.
|
|
VCGTU, // Vector compare unsigned greater than.
|
|
VTST, // Vector test bits.
|
|
|
|
// Vector shift by immediate:
|
|
VSHL, // ...left
|
|
VSHRs, // ...right (signed)
|
|
VSHRu, // ...right (unsigned)
|
|
VSHLLs, // ...left long (signed)
|
|
VSHLLu, // ...left long (unsigned)
|
|
VSHLLi, // ...left long (with maximum shift count)
|
|
VSHRN, // ...right narrow
|
|
|
|
// Vector rounding shift by immediate:
|
|
VRSHRs, // ...right (signed)
|
|
VRSHRu, // ...right (unsigned)
|
|
VRSHRN, // ...right narrow
|
|
|
|
// Vector saturating shift by immediate:
|
|
VQSHLs, // ...left (signed)
|
|
VQSHLu, // ...left (unsigned)
|
|
VQSHLsu, // ...left (signed to unsigned)
|
|
VQSHRNs, // ...right narrow (signed)
|
|
VQSHRNu, // ...right narrow (unsigned)
|
|
VQSHRNsu, // ...right narrow (signed to unsigned)
|
|
|
|
// Vector saturating rounding shift by immediate:
|
|
VQRSHRNs, // ...right narrow (signed)
|
|
VQRSHRNu, // ...right narrow (unsigned)
|
|
VQRSHRNsu, // ...right narrow (signed to unsigned)
|
|
|
|
// Vector shift and insert:
|
|
VSLI, // ...left
|
|
VSRI, // ...right
|
|
|
|
// Vector get lane (VMOV scalar to ARM core register)
|
|
// (These are used for 8- and 16-bit element types only.)
|
|
VGETLANEu, // zero-extend vector extract element
|
|
VGETLANEs, // sign-extend vector extract element
|
|
|
|
// Vector move immediate and move negated immediate:
|
|
VMOVIMM,
|
|
VMVNIMM,
|
|
|
|
// Vector duplicate:
|
|
VDUP,
|
|
VDUPLANE,
|
|
|
|
// Vector shuffles:
|
|
VEXT, // extract
|
|
VREV64, // reverse elements within 64-bit doublewords
|
|
VREV32, // reverse elements within 32-bit words
|
|
VREV16, // reverse elements within 16-bit halfwords
|
|
VZIP, // zip (interleave)
|
|
VUZP, // unzip (deinterleave)
|
|
VTRN, // transpose
|
|
|
|
// Operands of the standard BUILD_VECTOR node are not legalized, which
|
|
// is fine if BUILD_VECTORs are always lowered to shuffles or other
|
|
// operations, but for ARM some BUILD_VECTORs are legal as-is and their
|
|
// operands need to be legalized. Define an ARM-specific version of
|
|
// BUILD_VECTOR for this purpose.
|
|
BUILD_VECTOR,
|
|
|
|
// Floating-point max and min:
|
|
FMAX,
|
|
FMIN,
|
|
|
|
// Bit-field insert
|
|
BFI
|
|
};
|
|
}
|
|
|
|
/// Define some predicates that are used for node matching.
|
|
namespace ARM {
|
|
/// getVFPf32Imm / getVFPf64Imm - If the given fp immediate can be
|
|
/// materialized with a VMOV.f32 / VMOV.f64 (i.e. fconsts / fconstd)
|
|
/// instruction, returns its 8-bit integer representation. Otherwise,
|
|
/// returns -1.
|
|
int getVFPf32Imm(const APFloat &FPImm);
|
|
int getVFPf64Imm(const APFloat &FPImm);
|
|
bool isBitFieldInvertedMask(unsigned v);
|
|
}
|
|
|
|
//===--------------------------------------------------------------------===//
|
|
// ARMTargetLowering - ARM Implementation of the TargetLowering interface
|
|
|
|
class ARMTargetLowering : public TargetLowering {
|
|
public:
|
|
explicit ARMTargetLowering(TargetMachine &TM);
|
|
|
|
virtual unsigned getJumpTableEncoding(void) const;
|
|
|
|
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 const char *getTargetNodeName(unsigned Opcode) const;
|
|
|
|
virtual MachineBasicBlock *
|
|
EmitInstrWithCustomInserter(MachineInstr *MI,
|
|
MachineBasicBlock *MBB) const;
|
|
|
|
/// allowsUnalignedMemoryAccesses - Returns true if the target allows
|
|
/// unaligned memory accesses. of the specified type.
|
|
/// FIXME: Add getOptimalMemOpType to implement memcpy with NEON?
|
|
virtual bool allowsUnalignedMemoryAccesses(EVT VT) 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;
|
|
bool isLegalT2ScaledAddressingMode(const AddrMode &AM, EVT VT) 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.
|
|
virtual bool isLegalICmpImmediate(int64_t Imm) 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;
|
|
|
|
/// getPostIndexedAddressParts - returns true by value, base pointer and
|
|
/// offset pointer and addressing mode by reference if this node can be
|
|
/// combined with a load / store to form a post-indexed load / store.
|
|
virtual bool getPostIndexedAddressParts(SDNode *N, SDNode *Op,
|
|
SDValue &Base, SDValue &Offset,
|
|
ISD::MemIndexedMode &AM,
|
|
SelectionDAG &DAG) const;
|
|
|
|
virtual void computeMaskedBitsForTargetNode(const SDValue Op,
|
|
const APInt &Mask,
|
|
APInt &KnownZero,
|
|
APInt &KnownOne,
|
|
const SelectionDAG &DAG,
|
|
unsigned Depth) const;
|
|
|
|
|
|
ConstraintType getConstraintType(const std::string &Constraint) const;
|
|
std::pair<unsigned, const TargetRegisterClass*>
|
|
getRegForInlineAsmConstraint(const std::string &Constraint,
|
|
EVT VT) const;
|
|
std::vector<unsigned>
|
|
getRegClassForInlineAsmConstraint(const std::string &Constraint,
|
|
EVT VT) const;
|
|
|
|
/// LowerAsmOperandForConstraint - Lower the specified operand into the Ops
|
|
/// vector. If it is invalid, don't add anything to Ops. If hasMemory is
|
|
/// 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::vector<SDValue> &Ops,
|
|
SelectionDAG &DAG) const;
|
|
|
|
const ARMSubtarget* getSubtarget() const {
|
|
return Subtarget;
|
|
}
|
|
|
|
/// getRegClassFor - Return the register class that should be used for the
|
|
/// specified value type.
|
|
virtual TargetRegisterClass *getRegClassFor(EVT VT) const;
|
|
|
|
/// getFunctionAlignment - Return the Log2 alignment of this function.
|
|
virtual unsigned getFunctionAlignment(const Function *F) const;
|
|
|
|
/// getMaximalGlobalOffset - Returns the maximal possible offset which can
|
|
/// be used for loads / stores from the global.
|
|
virtual unsigned getMaximalGlobalOffset() const;
|
|
|
|
/// createFastISel - This method returns a target specific FastISel object,
|
|
/// or null if the target does not support "fast" ISel.
|
|
virtual FastISel *createFastISel(FunctionLoweringInfo &funcInfo) const;
|
|
|
|
Sched::Preference getSchedulingPreference(SDNode *N) const;
|
|
|
|
unsigned getRegPressureLimit(const TargetRegisterClass *RC,
|
|
MachineFunction &MF) const;
|
|
|
|
bool isShuffleMaskLegal(const SmallVectorImpl<int> &M, EVT VT) const;
|
|
bool isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const;
|
|
|
|
/// isFPImmLegal - 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.
|
|
virtual bool isFPImmLegal(const APFloat &Imm, EVT VT) const;
|
|
|
|
protected:
|
|
std::pair<const TargetRegisterClass*, uint8_t>
|
|
findRepresentativeClass(EVT VT) const;
|
|
|
|
private:
|
|
/// Subtarget - Keep a pointer to the ARMSubtarget around so that we can
|
|
/// make the right decision when generating code for different targets.
|
|
const ARMSubtarget *Subtarget;
|
|
|
|
const TargetRegisterInfo *RegInfo;
|
|
|
|
/// ARMPCLabelIndex - Keep track of the number of ARM PC labels created.
|
|
///
|
|
unsigned ARMPCLabelIndex;
|
|
|
|
void addTypeForNEON(EVT VT, EVT PromotedLdStVT, EVT PromotedBitwiseVT);
|
|
void addDRTypeForNEON(EVT VT);
|
|
void addQRTypeForNEON(EVT VT);
|
|
|
|
typedef SmallVector<std::pair<unsigned, SDValue>, 8> RegsToPassVector;
|
|
void PassF64ArgInRegs(DebugLoc dl, SelectionDAG &DAG,
|
|
SDValue Chain, SDValue &Arg,
|
|
RegsToPassVector &RegsToPass,
|
|
CCValAssign &VA, CCValAssign &NextVA,
|
|
SDValue &StackPtr,
|
|
SmallVector<SDValue, 8> &MemOpChains,
|
|
ISD::ArgFlagsTy Flags) const;
|
|
SDValue GetF64FormalArgument(CCValAssign &VA, CCValAssign &NextVA,
|
|
SDValue &Root, SelectionDAG &DAG,
|
|
DebugLoc dl) const;
|
|
|
|
CCAssignFn *CCAssignFnForNode(CallingConv::ID CC, bool Return,
|
|
bool isVarArg) const;
|
|
SDValue LowerMemOpCallTo(SDValue Chain, SDValue StackPtr, SDValue Arg,
|
|
DebugLoc dl, SelectionDAG &DAG,
|
|
const CCValAssign &VA,
|
|
ISD::ArgFlagsTy Flags) const;
|
|
SDValue LowerEH_SJLJ_SETJMP(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerEH_SJLJ_LONGJMP(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG,
|
|
const ARMSubtarget *Subtarget) const;
|
|
SDValue LowerBlockAddress(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerGlobalAddressDarwin(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerGlobalAddressELF(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerToTLSGeneralDynamicModel(GlobalAddressSDNode *GA,
|
|
SelectionDAG &DAG) const;
|
|
SDValue LowerToTLSExecModels(GlobalAddressSDNode *GA,
|
|
SelectionDAG &DAG) const;
|
|
SDValue LowerGLOBAL_OFFSET_TABLE(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerBR_JT(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerSELECT(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerBR_CC(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerFCOPYSIGN(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerShiftRightParts(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerShiftLeftParts(SDValue Op, SelectionDAG &DAG) const;
|
|
SDValue LowerFLT_ROUNDS_(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;
|
|
|
|
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(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;
|
|
|
|
/// IsEligibleForTailCallOptimization - Check whether the call is eligible
|
|
/// for tail call optimization. Targets which want to do tail call
|
|
/// optimization should implement this function.
|
|
bool IsEligibleForTailCallOptimization(SDValue Callee,
|
|
CallingConv::ID CalleeCC,
|
|
bool isVarArg,
|
|
bool isCalleeStructRet,
|
|
bool isCallerStructRet,
|
|
const SmallVectorImpl<ISD::OutputArg> &Outs,
|
|
const SmallVectorImpl<SDValue> &OutVals,
|
|
const SmallVectorImpl<ISD::InputArg> &Ins,
|
|
SelectionDAG& DAG) 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 getARMCmp(SDValue LHS, SDValue RHS, ISD::CondCode CC,
|
|
SDValue &ARMcc, SelectionDAG &DAG, DebugLoc dl) const;
|
|
SDValue getVFPCmp(SDValue LHS, SDValue RHS,
|
|
SelectionDAG &DAG, DebugLoc dl) const;
|
|
|
|
SDValue OptimizeVFPBrcond(SDValue Op, SelectionDAG &DAG) const;
|
|
|
|
MachineBasicBlock *EmitAtomicCmpSwap(MachineInstr *MI,
|
|
MachineBasicBlock *BB,
|
|
unsigned Size) const;
|
|
MachineBasicBlock *EmitAtomicBinary(MachineInstr *MI,
|
|
MachineBasicBlock *BB,
|
|
unsigned Size,
|
|
unsigned BinOpcode) const;
|
|
|
|
};
|
|
|
|
namespace ARM {
|
|
FastISel *createFastISel(FunctionLoweringInfo &funcInfo);
|
|
}
|
|
}
|
|
|
|
#endif // ARMISELLOWERING_H
|