reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
  120
  121
  122
  123
  124
  125
  126
  127
  128
  129
  130
  131
  132
  133
  134
  135
  136
  137
  138
  139
  140
  141
  142
  143
  144
  145
  146
  147
  148
  149
  150
  151
  152
  153
  154
  155
  156
  157
  158
  159
  160
  161
  162
  163
  164
  165
  166
  167
  168
  169
  170
  171
  172
  173
  174
  175
  176
  177
  178
  179
  180
  181
  182
  183
  184
  185
  186
  187
  188
  189
  190
  191
  192
  193
  194
  195
//===- AArch64TargetTransformInfo.h - AArch64 specific TTI ------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
/// \file
/// This file a TargetTransformInfo::Concept conforming object specific to the
/// AArch64 target machine. It uses the target's detailed information to
/// provide more precise answers to certain TTI queries, while letting the
/// target independent and default TTI implementations handle the rest.
///
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_AARCH64_AARCH64TARGETTRANSFORMINFO_H
#define LLVM_LIB_TARGET_AARCH64_AARCH64TARGETTRANSFORMINFO_H

#include "AArch64.h"
#include "AArch64Subtarget.h"
#include "AArch64TargetMachine.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Intrinsics.h"
#include <cstdint>

namespace llvm {

class APInt;
class Instruction;
class IntrinsicInst;
class Loop;
class SCEV;
class ScalarEvolution;
class Type;
class Value;
class VectorType;

class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
  using BaseT = BasicTTIImplBase<AArch64TTIImpl>;
  using TTI = TargetTransformInfo;

  friend BaseT;

  const AArch64Subtarget *ST;
  const AArch64TargetLowering *TLI;

  const AArch64Subtarget *getST() const { return ST; }
  const AArch64TargetLowering *getTLI() const { return TLI; }

  enum MemIntrinsicType {
    VECTOR_LDST_TWO_ELEMENTS,
    VECTOR_LDST_THREE_ELEMENTS,
    VECTOR_LDST_FOUR_ELEMENTS
  };

  bool isWideningInstruction(Type *Ty, unsigned Opcode,
                             ArrayRef<const Value *> Args);

public:
  explicit AArch64TTIImpl(const AArch64TargetMachine *TM, const Function &F)
      : BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
        TLI(ST->getTargetLowering()) {}

  bool areInlineCompatible(const Function *Caller,
                           const Function *Callee) const;

  /// \name Scalar TTI Implementations
  /// @{

  using BaseT::getIntImmCost;
  int getIntImmCost(int64_t Val);
  int getIntImmCost(const APInt &Imm, Type *Ty);
  int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
  int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
                    Type *Ty);
  TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth);

  /// @}

  /// \name Vector TTI Implementations
  /// @{

  bool enableInterleavedAccessVectorization() { return true; }

  unsigned getNumberOfRegisters(unsigned ClassID) const {
    bool Vector = (ClassID == 1);
    if (Vector) {
      if (ST->hasNEON())
        return 32;
      return 0;
    }
    return 31;
  }

  unsigned getRegisterBitWidth(bool Vector) const {
    if (Vector) {
      if (ST->hasNEON())
        return 128;
      return 0;
    }
    return 64;
  }

  unsigned getMinVectorRegisterBitWidth() {
    return ST->getMinVectorRegisterBitWidth();
  }

  unsigned getMaxInterleaveFactor(unsigned VF);

  int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                       const Instruction *I = nullptr);

  int getExtractWithExtendCost(unsigned Opcode, Type *Dst, VectorType *VecTy,
                               unsigned Index);

  int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);

  int getArithmeticInstrCost(
      unsigned Opcode, Type *Ty,
      TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
      TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue,
      TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
      TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None,
      ArrayRef<const Value *> Args = ArrayRef<const Value *>());

  int getAddressComputationCost(Type *Ty, ScalarEvolution *SE, const SCEV *Ptr);

  int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                         const Instruction *I = nullptr);

  TTI::MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
                                                    bool IsZeroCmp) const;

  int getMemoryOpCost(unsigned Opcode, Type *Src, MaybeAlign Alignment,
                      unsigned AddressSpace, const Instruction *I = nullptr);

  int getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys);

  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                               TTI::UnrollingPreferences &UP);

  Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
                                           Type *ExpectedType);

  bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info);

  bool isLegalMaskedLoad(Type *DataType, MaybeAlign Alignment) {
    if (!isa<VectorType>(DataType) || !ST->hasSVE())
      return false;

    Type *Ty = DataType->getVectorElementType();
    if (Ty->isHalfTy() || Ty->isFloatTy() || Ty->isDoubleTy())
      return true;

    if (Ty->isIntegerTy(8) || Ty->isIntegerTy(16) ||
        Ty->isIntegerTy(32) || Ty->isIntegerTy(64))
      return true;

    return false;
  }

  int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
                                 ArrayRef<unsigned> Indices, unsigned Alignment,
                                 unsigned AddressSpace,
                                 bool UseMaskForCond = false,
                                 bool UseMaskForGaps = false);

  bool
  shouldConsiderAddressTypePromotion(const Instruction &I,
                                     bool &AllowPromotionWithoutCommonHeader);

  bool shouldExpandReduction(const IntrinsicInst *II) const {
    return false;
  }

  unsigned getGISelRematGlobalCost() const {
    return 2;
  }

  bool useReductionIntrinsic(unsigned Opcode, Type *Ty,
                             TTI::ReductionFlags Flags) const;

  int getArithmeticReductionCost(unsigned Opcode, Type *Ty,
                                 bool IsPairwiseForm);

  int getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index, Type *SubTp);
  /// @}
};

} // end namespace llvm

#endif // LLVM_LIB_TARGET_AARCH64_AARCH64TARGETTRANSFORMINFO_H