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
|
//===- 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;
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 InlineFeatureWhitelist.
// 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 InlineFeatureWhitelist = {
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::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; }
bool shouldFavorBackedgeIndex(const Loop *L) const {
if (L->getHeader()->getParent()->hasOptSize())
return false;
return ST->isMClass() && ST->isThumb2() && L->getNumBlocks() == 1;
}
/// Floating-point computation using ARMv8 AArch32 Advanced
/// SIMD instructions remains unchanged from ARMv7. Only AArch64 SIMD
/// is IEEE-754 compliant, but it's not covered in this target.
bool isFPVectorizationPotentiallyUnsafe() {
return !ST->isTargetDarwin();
}
/// \name Scalar TTI Implementations
/// @{
int getIntImmCodeSizeCost(unsigned Opcode, unsigned Idx, const APInt &Imm,
Type *Ty);
using BaseT::getIntImmCost;
int getIntImmCost(const APInt &Imm, Type *Ty);
int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
/// @}
/// \name Vector TTI Implementations
/// @{
unsigned getNumberOfRegisters(bool Vector) {
if (Vector) {
if (ST->hasNEON())
return 16;
return 0;
}
if (ST->isThumb1Only())
return 8;
return 13;
}
unsigned getRegisterBitWidth(bool Vector) const {
if (Vector) {
if (ST->hasNEON())
return 128;
return 0;
}
return 32;
}
unsigned getMaxInterleaveFactor(unsigned VF) {
return ST->getMaxInterleaveFactor();
}
int getMemcpyCost(const Instruction *I);
int getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index, Type *SubTp);
int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
const Instruction *I = nullptr);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
const Instruction *I = nullptr);
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
int getAddressComputationCost(Type *Val, ScalarEvolution *SE,
const SCEV *Ptr);
int getArithmeticInstrCost(
unsigned Opcode, Type *Ty,
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 *>());
int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
unsigned AddressSpace, const Instruction *I = nullptr);
int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
ArrayRef<unsigned> Indices, unsigned Alignment,
unsigned AddressSpace,
bool UseMaskForCond = false,
bool UseMaskForGaps = false);
bool isLoweredToCall(const Function *F);
bool isHardwareLoopProfitable(Loop *L, ScalarEvolution &SE,
AssumptionCache &AC,
TargetLibraryInfo *LibInfo,
HardwareLoopInfo &HWLoopInfo);
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP);
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->needsRelocation();
return true;
}
/// @}
};
} // end namespace llvm
#endif // LLVM_LIB_TARGET_ARM_ARMTARGETTRANSFORMINFO_H
|
