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
|
//===-- X86TargetTransformInfo.h - X86 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
/// X86 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_X86_X86TARGETTRANSFORMINFO_H
#define LLVM_LIB_TARGET_X86_X86TARGETTRANSFORMINFO_H
#include "X86.h"
#include "X86TargetMachine.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/CodeGen/TargetLowering.h"
namespace llvm {
class X86TTIImpl : public BasicTTIImplBase<X86TTIImpl> {
typedef BasicTTIImplBase<X86TTIImpl> BaseT;
typedef TargetTransformInfo TTI;
friend BaseT;
const X86Subtarget *ST;
const X86TargetLowering *TLI;
const X86Subtarget *getST() const { return ST; }
const X86TargetLowering *getTLI() const { return TLI; }
const FeatureBitset InlineFeatureIgnoreList = {
// This indicates the CPU is 64 bit capable not that we are in 64-bit
// mode.
X86::Feature64Bit,
// These features don't have any intrinsics or ABI effect.
X86::FeatureNOPL,
X86::FeatureCMPXCHG16B,
X86::FeatureLAHFSAHF,
// Codegen control options.
X86::FeatureFast11ByteNOP,
X86::FeatureFast15ByteNOP,
X86::FeatureFastBEXTR,
X86::FeatureFastHorizontalOps,
X86::FeatureFastLZCNT,
X86::FeatureFastPartialYMMorZMMWrite,
X86::FeatureFastScalarFSQRT,
X86::FeatureFastSHLDRotate,
X86::FeatureFastScalarShiftMasks,
X86::FeatureFastVectorShiftMasks,
X86::FeatureFastVariableShuffle,
X86::FeatureFastVectorFSQRT,
X86::FeatureLEAForSP,
X86::FeatureLEAUsesAG,
X86::FeatureLZCNTFalseDeps,
X86::FeatureBranchFusion,
X86::FeatureMacroFusion,
X86::FeatureMergeToThreeWayBranch,
X86::FeaturePadShortFunctions,
X86::FeaturePOPCNTFalseDeps,
X86::FeatureSSEUnalignedMem,
X86::FeatureSlow3OpsLEA,
X86::FeatureSlowDivide32,
X86::FeatureSlowDivide64,
X86::FeatureSlowIncDec,
X86::FeatureSlowLEA,
X86::FeatureSlowPMADDWD,
X86::FeatureSlowPMULLD,
X86::FeatureSlowSHLD,
X86::FeatureSlowTwoMemOps,
X86::FeatureSlowUAMem16,
// Perf-tuning flags.
X86::FeatureHasFastGather,
X86::FeatureSlowUAMem32,
// Based on whether user set the -mprefer-vector-width command line.
X86::FeaturePrefer256Bit,
// CPU name enums. These just follow CPU string.
X86::ProcIntelAtom,
X86::ProcIntelGLM,
X86::ProcIntelGLP,
X86::ProcIntelSLM,
X86::ProcIntelTRM,
};
public:
explicit X86TTIImpl(const X86TargetMachine *TM, const Function &F)
: BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
TLI(ST->getTargetLowering()) {}
/// \name Scalar TTI Implementations
/// @{
TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth);
/// @}
/// \name Cache TTI Implementation
/// @{
llvm::Optional<unsigned> getCacheSize(
TargetTransformInfo::CacheLevel Level) const;
llvm::Optional<unsigned> getCacheAssociativity(
TargetTransformInfo::CacheLevel Level) const;
/// @}
/// \name Vector TTI Implementations
/// @{
unsigned getNumberOfRegisters(bool Vector);
unsigned getRegisterBitWidth(bool Vector) const;
unsigned getLoadStoreVecRegBitWidth(unsigned AS) const;
unsigned getMaxInterleaveFactor(unsigned VF);
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 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 getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
unsigned AddressSpace, const Instruction *I = nullptr);
int getMaskedMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
unsigned AddressSpace);
int getGatherScatterOpCost(unsigned Opcode, Type *DataTy, Value *Ptr,
bool VariableMask, unsigned Alignment);
int getAddressComputationCost(Type *PtrTy, ScalarEvolution *SE,
const SCEV *Ptr);
unsigned getAtomicMemIntrinsicMaxElementSize() const;
int getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
ArrayRef<Type *> Tys, FastMathFlags FMF,
unsigned ScalarizationCostPassed = UINT_MAX);
int getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
ArrayRef<Value *> Args, FastMathFlags FMF,
unsigned VF = 1);
int getArithmeticReductionCost(unsigned Opcode, Type *Ty,
bool IsPairwiseForm);
int getMinMaxReductionCost(Type *Ty, Type *CondTy, bool IsPairwiseForm,
bool IsUnsigned);
int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
unsigned Factor, ArrayRef<unsigned> Indices,
unsigned Alignment, unsigned AddressSpace,
bool UseMaskForCond = false,
bool UseMaskForGaps = false);
int getInterleavedMemoryOpCostAVX512(unsigned Opcode, Type *VecTy,
unsigned Factor, ArrayRef<unsigned> Indices,
unsigned Alignment, unsigned AddressSpace,
bool UseMaskForCond = false,
bool UseMaskForGaps = false);
int getInterleavedMemoryOpCostAVX2(unsigned Opcode, Type *VecTy,
unsigned Factor, ArrayRef<unsigned> Indices,
unsigned Alignment, unsigned AddressSpace,
bool UseMaskForCond = false,
bool UseMaskForGaps = false);
int getIntImmCost(int64_t);
int getIntImmCost(const APInt &Imm, Type *Ty);
unsigned getUserCost(const User *U, ArrayRef<const Value *> Operands);
int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
Type *Ty);
bool isLSRCostLess(TargetTransformInfo::LSRCost &C1,
TargetTransformInfo::LSRCost &C2);
bool canMacroFuseCmp();
bool isLegalMaskedLoad(Type *DataType);
bool isLegalMaskedStore(Type *DataType);
bool isLegalNTLoad(Type *DataType, unsigned Alignment);
bool isLegalNTStore(Type *DataType, unsigned Alignment);
bool isLegalMaskedGather(Type *DataType);
bool isLegalMaskedScatter(Type *DataType);
bool isLegalMaskedExpandLoad(Type *DataType);
bool isLegalMaskedCompressStore(Type *DataType);
bool hasDivRemOp(Type *DataType, bool IsSigned);
bool isFCmpOrdCheaperThanFCmpZero(Type *Ty);
bool areInlineCompatible(const Function *Caller,
const Function *Callee) const;
bool areFunctionArgsABICompatible(const Function *Caller,
const Function *Callee,
SmallPtrSetImpl<Argument *> &Args) const;
TTI::MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
bool IsZeroCmp) const;
bool enableInterleavedAccessVectorization();
private:
int getGSScalarCost(unsigned Opcode, Type *DataTy, bool VariableMask,
unsigned Alignment, unsigned AddressSpace);
int getGSVectorCost(unsigned Opcode, Type *DataTy, Value *Ptr,
unsigned Alignment, unsigned AddressSpace);
/// @}
};
} // end namespace llvm
#endif
|
