aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Target/ARM/ARMTargetTransformInfo.h
blob: 5bb84899e5ef05506927d341a529c097a0b6aea0 (plain) (blame)
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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
//===- ARMTargetTransformInfo.h - ARM 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
/// ARM 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_ARM_ARMTARGETTRANSFORMINFO_H
#define LLVM_LIB_TARGET_ARM_ARMTARGETTRANSFORMINFO_H

#include "ARM.h"
#include "ARMSubtarget.h"
#include "ARMTargetMachine.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Function.h"
#include "llvm/MC/SubtargetFeature.h"

namespace llvm {

class APInt;
class ARMTargetLowering;
class Instruction;
class Loop;
class SCEV;
class ScalarEvolution;
class Type;
class Value;

namespace TailPredication {
  enum Mode {
    Disabled = 0,
    EnabledNoReductions,
    Enabled,
    ForceEnabledNoReductions,
    ForceEnabled
  };
}

// For controlling conversion of memcpy into Tail Predicated loop.
namespace TPLoop {
enum MemTransfer { ForceDisabled = 0, ForceEnabled, Allow };
}

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

  friend BaseT;

  const ARMSubtarget *ST;
  const ARMTargetLowering *TLI;

  // Currently the following features are excluded from InlineFeaturesAllowed.
  // ModeThumb, FeatureNoARM, ModeSoftFloat, FeatureFP64, FeatureD32
  // Depending on whether they are set or unset, different
  // instructions/registers are available. For example, inlining a callee with
  // -thumb-mode in a caller with +thumb-mode, may cause the assembler to
  // fail if the callee uses ARM only instructions, e.g. in inline asm.
  const FeatureBitset InlineFeaturesAllowed = {
      ARM::FeatureVFP2, ARM::FeatureVFP3, ARM::FeatureNEON, ARM::FeatureThumb2,
      ARM::FeatureFP16, ARM::FeatureVFP4, ARM::FeatureFPARMv8,
      ARM::FeatureFullFP16, ARM::FeatureFP16FML, ARM::FeatureHWDivThumb,
      ARM::FeatureHWDivARM, ARM::FeatureDB, ARM::FeatureV7Clrex,
      ARM::FeatureAcquireRelease, ARM::FeatureSlowFPBrcc,
      ARM::FeaturePerfMon, ARM::FeatureTrustZone, ARM::Feature8MSecExt,
      ARM::FeatureCrypto, ARM::FeatureCRC, ARM::FeatureRAS,
      ARM::FeatureFPAO, ARM::FeatureFuseAES, ARM::FeatureZCZeroing,
      ARM::FeatureProfUnpredicate, ARM::FeatureSlowVGETLNi32,
      ARM::FeatureSlowVDUP32, ARM::FeaturePreferVMOVSR,
      ARM::FeaturePrefISHSTBarrier, ARM::FeatureMuxedUnits,
      ARM::FeatureSlowOddRegister, ARM::FeatureSlowLoadDSubreg,
      ARM::FeatureDontWidenVMOVS, ARM::FeatureExpandMLx,
      ARM::FeatureHasVMLxHazards, ARM::FeatureNEONForFPMovs,
      ARM::FeatureNEONForFP, ARM::FeatureCheckVLDnAlign,
      ARM::FeatureHasSlowFPVMLx, ARM::FeatureHasSlowFPVFMx,
      ARM::FeatureVMLxForwarding, ARM::FeaturePref32BitThumb,
      ARM::FeatureAvoidPartialCPSR, ARM::FeatureCheapPredicableCPSR,
      ARM::FeatureAvoidMOVsShOp, ARM::FeatureHasRetAddrStack,
      ARM::FeatureHasNoBranchPredictor, ARM::FeatureDSP, ARM::FeatureMP,
      ARM::FeatureVirtualization, ARM::FeatureMClass, ARM::FeatureRClass,
      ARM::FeatureAClass, ARM::FeatureNaClTrap, ARM::FeatureStrictAlign,
      ARM::FeatureLongCalls, ARM::FeatureExecuteOnly, ARM::FeatureReserveR9,
      ARM::FeatureNoMovt, ARM::FeatureNoNegativeImmediates
  };

  const ARMSubtarget *getST() const { return ST; }
  const ARMTargetLowering *getTLI() const { return TLI; }

public:
  explicit ARMTTIImpl(const ARMBaseTargetMachine *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;

  bool enableInterleavedAccessVectorization() { return true; }

  TTI::AddressingModeKind
    getPreferredAddressingMode(const Loop *L, ScalarEvolution *SE) const;

  /// Floating-point computation using ARMv8 AArch32 Advanced
  /// SIMD instructions remains unchanged from ARMv7. Only AArch64 SIMD
  /// and Arm MVE are IEEE-754 compliant.
  bool isFPVectorizationPotentiallyUnsafe() {
    return !ST->isTargetDarwin() && !ST->hasMVEFloatOps();
  }

  Optional<Instruction *> instCombineIntrinsic(InstCombiner &IC,
                                               IntrinsicInst &II) const;
  Optional<Value *> simplifyDemandedVectorEltsIntrinsic(
      InstCombiner &IC, IntrinsicInst &II, APInt DemandedElts, APInt &UndefElts,
      APInt &UndefElts2, APInt &UndefElts3,
      std::function<void(Instruction *, unsigned, APInt, APInt &)>
          SimplifyAndSetOp) const;

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

  InstructionCost getIntImmCodeSizeCost(unsigned Opcode, unsigned Idx,
                                        const APInt &Imm, Type *Ty);

  using BaseT::getIntImmCost;
  InstructionCost getIntImmCost(const APInt &Imm, Type *Ty,
                                TTI::TargetCostKind CostKind);

  InstructionCost getIntImmCostInst(unsigned Opcode, unsigned Idx,
                                    const APInt &Imm, Type *Ty,
                                    TTI::TargetCostKind CostKind,
                                    Instruction *Inst = nullptr);

  /// @}

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

  unsigned getNumberOfRegisters(unsigned ClassID) const {
    bool Vector = (ClassID == 1);
    if (Vector) {
      if (ST->hasNEON())
        return 16;
      if (ST->hasMVEIntegerOps())
        return 8;
      return 0;
    }

    if (ST->isThumb1Only())
      return 8;
    return 13;
  }

  TypeSize getRegisterBitWidth(TargetTransformInfo::RegisterKind K) const {
    switch (K) {
    case TargetTransformInfo::RGK_Scalar:
      return TypeSize::getFixed(32);
    case TargetTransformInfo::RGK_FixedWidthVector:
      if (ST->hasNEON())
        return TypeSize::getFixed(128);
      if (ST->hasMVEIntegerOps())
        return TypeSize::getFixed(128);
      return TypeSize::getFixed(0);
    case TargetTransformInfo::RGK_ScalableVector:
      return TypeSize::getScalable(0);
    }
    llvm_unreachable("Unsupported register kind");
  }

  unsigned getMaxInterleaveFactor(unsigned VF) {
    return ST->getMaxInterleaveFactor();
  }

  bool isProfitableLSRChainElement(Instruction *I);

  bool isLegalMaskedLoad(Type *DataTy, Align Alignment);

  bool isLegalMaskedStore(Type *DataTy, Align Alignment) {
    return isLegalMaskedLoad(DataTy, Alignment);
  }

  bool forceScalarizeMaskedGather(VectorType *VTy, Align Alignment) {
    // For MVE, we have a custom lowering pass that will already have custom
    // legalised any gathers that we can lower to MVE intrinsics, and want to
    // expand all the rest. The pass runs before the masked intrinsic lowering
    // pass.
    return true;
  }

  bool forceScalarizeMaskedScatter(VectorType *VTy, Align Alignment) {
    return forceScalarizeMaskedGather(VTy, Alignment);
  }

  bool isLegalMaskedGather(Type *Ty, Align Alignment);

  bool isLegalMaskedScatter(Type *Ty, Align Alignment) {
    return isLegalMaskedGather(Ty, Alignment);
  }

  InstructionCost getMemcpyCost(const Instruction *I);

  int getNumMemOps(const IntrinsicInst *I) const;

  InstructionCost getShuffleCost(TTI::ShuffleKind Kind, VectorType *Tp,
                                 ArrayRef<int> Mask, int Index,
                                 VectorType *SubTp);

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

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

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

  InstructionCost getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
                                 const Instruction *I = nullptr);

  InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                                   TTI::CastContextHint CCH,
                                   TTI::TargetCostKind CostKind,
                                   const Instruction *I = nullptr);

  InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                                     CmpInst::Predicate VecPred,
                                     TTI::TargetCostKind CostKind,
                                     const Instruction *I = nullptr);

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

  InstructionCost getAddressComputationCost(Type *Val, ScalarEvolution *SE,
                                            const SCEV *Ptr);

  InstructionCost getArithmeticInstrCost(
      unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
      TTI::OperandValueKind Op1Info = TTI::OK_AnyValue,
      TTI::OperandValueKind Op2Info = TTI::OK_AnyValue,
      TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
      TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None,
      ArrayRef<const Value *> Args = ArrayRef<const Value *>(),
      const Instruction *CxtI = nullptr);

  InstructionCost getMemoryOpCost(unsigned Opcode, Type *Src,
                                  MaybeAlign Alignment, unsigned AddressSpace,
                                  TTI::TargetCostKind CostKind,
                                  const Instruction *I = nullptr);

  InstructionCost getMaskedMemoryOpCost(unsigned Opcode, Type *Src,
                                        Align Alignment, unsigned AddressSpace,
                                        TTI::TargetCostKind CostKind);

  InstructionCost getInterleavedMemoryOpCost(
      unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
      Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
      bool UseMaskForCond = false, bool UseMaskForGaps = false);

  InstructionCost getGatherScatterOpCost(unsigned Opcode, Type *DataTy,
                                         const Value *Ptr, bool VariableMask,
                                         Align Alignment,
                                         TTI::TargetCostKind CostKind,
                                         const Instruction *I = nullptr);

  InstructionCost getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
                                             Optional<FastMathFlags> FMF,
                                             TTI::TargetCostKind CostKind);
  InstructionCost getExtendedAddReductionCost(bool IsMLA, bool IsUnsigned,
                                              Type *ResTy, VectorType *ValTy,
                                              TTI::TargetCostKind CostKind);

  InstructionCost getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                                        TTI::TargetCostKind CostKind);

  bool maybeLoweredToCall(Instruction &I);
  bool isLoweredToCall(const Function *F);
  bool isHardwareLoopProfitable(Loop *L, ScalarEvolution &SE,
                                AssumptionCache &AC,
                                TargetLibraryInfo *LibInfo,
                                HardwareLoopInfo &HWLoopInfo);
  bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI,
                                   ScalarEvolution &SE,
                                   AssumptionCache &AC,
                                   TargetLibraryInfo *TLI,
                                   DominatorTree *DT,
                                   const LoopAccessInfo *LAI);
  void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                               TTI::UnrollingPreferences &UP,
                               OptimizationRemarkEmitter *ORE);

  bool emitGetActiveLaneMask() const;

  void getPeelingPreferences(Loop *L, ScalarEvolution &SE,
                             TTI::PeelingPreferences &PP);
  bool shouldBuildLookupTablesForConstant(Constant *C) const {
    // In the ROPI and RWPI relocation models we can't have pointers to global
    // variables or functions in constant data, so don't convert switches to
    // lookup tables if any of the values would need relocation.
    if (ST->isROPI() || ST->isRWPI())
      return !C->needsDynamicRelocation();

    return true;
  }
  /// @}
};

/// isVREVMask - Check if a vector shuffle corresponds to a VREV
/// instruction with the specified blocksize.  (The order of the elements
/// within each block of the vector is reversed.)
inline bool isVREVMask(ArrayRef<int> M, EVT VT, unsigned BlockSize) {
  assert((BlockSize == 16 || BlockSize == 32 || BlockSize == 64) &&
         "Only possible block sizes for VREV are: 16, 32, 64");

  unsigned EltSz = VT.getScalarSizeInBits();
  if (EltSz != 8 && EltSz != 16 && EltSz != 32)
    return false;

  unsigned BlockElts = M[0] + 1;
  // If the first shuffle index is UNDEF, be optimistic.
  if (M[0] < 0)
    BlockElts = BlockSize / EltSz;

  if (BlockSize <= EltSz || BlockSize != BlockElts * EltSz)
    return false;

  for (unsigned i = 0, e = M.size(); i < e; ++i) {
    if (M[i] < 0)
      continue; // ignore UNDEF indices
    if ((unsigned)M[i] != (i - i % BlockElts) + (BlockElts - 1 - i % BlockElts))
      return false;
  }

  return true;
}

} // end namespace llvm

#endif // LLVM_LIB_TARGET_ARM_ARMTARGETTRANSFORMINFO_H