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
| //===- AMDGPUTargetTransformInfo.h - AMDGPU 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
/// AMDGPU 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_AMDGPU_AMDGPUTARGETTRANSFORMINFO_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUTARGETTRANSFORMINFO_H
#include "AMDGPU.h"
#include "AMDGPUSubtarget.h"
#include "AMDGPUTargetMachine.h"
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "Utils/AMDGPUBaseInfo.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/IR/Function.h"
#include "llvm/MC/SubtargetFeature.h"
#include "llvm/Support/MathExtras.h"
#include <cassert>
namespace llvm {
class AMDGPUTargetLowering;
class Loop;
class ScalarEvolution;
class Type;
class Value;
class AMDGPUTTIImpl final : public BasicTTIImplBase<AMDGPUTTIImpl> {
using BaseT = BasicTTIImplBase<AMDGPUTTIImpl>;
using TTI = TargetTransformInfo;
friend BaseT;
Triple TargetTriple;
const TargetSubtargetInfo *ST;
const TargetLoweringBase *TLI;
const TargetSubtargetInfo *getST() const { return ST; }
const TargetLoweringBase *getTLI() const { return TLI; }
public:
explicit AMDGPUTTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
: BaseT(TM, F.getParent()->getDataLayout()),
TargetTriple(TM->getTargetTriple()),
ST(static_cast<const GCNSubtarget *>(TM->getSubtargetImpl(F))),
TLI(ST->getTargetLowering()) {}
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP);
};
class GCNTTIImpl final : public BasicTTIImplBase<GCNTTIImpl> {
using BaseT = BasicTTIImplBase<GCNTTIImpl>;
using TTI = TargetTransformInfo;
friend BaseT;
const GCNSubtarget *ST;
const AMDGPUTargetLowering *TLI;
AMDGPUTTIImpl CommonTTI;
bool IsGraphicsShader;
const FeatureBitset InlineFeatureIgnoreList = {
// Codegen control options which don't matter.
AMDGPU::FeatureEnableLoadStoreOpt,
AMDGPU::FeatureEnableSIScheduler,
AMDGPU::FeatureEnableUnsafeDSOffsetFolding,
AMDGPU::FeatureFlatForGlobal,
AMDGPU::FeaturePromoteAlloca,
AMDGPU::FeatureUnalignedBufferAccess,
AMDGPU::FeatureUnalignedScratchAccess,
AMDGPU::FeatureAutoWaitcntBeforeBarrier,
// Property of the kernel/environment which can't actually differ.
AMDGPU::FeatureSGPRInitBug,
AMDGPU::FeatureXNACK,
AMDGPU::FeatureTrapHandler,
AMDGPU::FeatureCodeObjectV3,
// The default assumption needs to be ecc is enabled, but no directly
// exposed operations depend on it, so it can be safely inlined.
AMDGPU::FeatureSRAMECC,
// Perf-tuning features
AMDGPU::FeatureFastFMAF32,
AMDGPU::HalfRate64Ops
};
const GCNSubtarget *getST() const { return ST; }
const AMDGPUTargetLowering *getTLI() const { return TLI; }
static inline int getFullRateInstrCost() {
return TargetTransformInfo::TCC_Basic;
}
static inline int getHalfRateInstrCost() {
return 2 * TargetTransformInfo::TCC_Basic;
}
// TODO: The size is usually 8 bytes, but takes 4x as many cycles. Maybe
// should be 2 or 4.
static inline int getQuarterRateInstrCost() {
return 3 * TargetTransformInfo::TCC_Basic;
}
// On some parts, normal fp64 operations are half rate, and others
// quarter. This also applies to some integer operations.
inline int get64BitInstrCost() const {
return ST->hasHalfRate64Ops() ?
getHalfRateInstrCost() : getQuarterRateInstrCost();
}
public:
explicit GCNTTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
: BaseT(TM, F.getParent()->getDataLayout()),
ST(static_cast<const GCNSubtarget*>(TM->getSubtargetImpl(F))),
TLI(ST->getTargetLowering()),
CommonTTI(TM, F),
IsGraphicsShader(AMDGPU::isShader(F.getCallingConv())) {}
bool hasBranchDivergence() { return true; }
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP);
TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth) {
assert(isPowerOf2_32(TyWidth) && "Ty width must be power of 2");
return TTI::PSK_FastHardware;
}
unsigned getHardwareNumberOfRegisters(bool Vector) const;
unsigned getNumberOfRegisters(bool Vector) const;
unsigned getRegisterBitWidth(bool Vector) const;
unsigned getMinVectorRegisterBitWidth() const;
unsigned getLoadVectorFactor(unsigned VF, unsigned LoadSize,
unsigned ChainSizeInBytes,
VectorType *VecTy) const;
unsigned getStoreVectorFactor(unsigned VF, unsigned StoreSize,
unsigned ChainSizeInBytes,
VectorType *VecTy) const;
unsigned getLoadStoreVecRegBitWidth(unsigned AddrSpace) const;
bool isLegalToVectorizeMemChain(unsigned ChainSizeInBytes,
unsigned Alignment,
unsigned AddrSpace) const;
bool isLegalToVectorizeLoadChain(unsigned ChainSizeInBytes,
unsigned Alignment,
unsigned AddrSpace) const;
bool isLegalToVectorizeStoreChain(unsigned ChainSizeInBytes,
unsigned Alignment,
unsigned AddrSpace) const;
unsigned getMaxInterleaveFactor(unsigned VF);
bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info) const;
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 *>());
unsigned getCFInstrCost(unsigned Opcode);
int getVectorInstrCost(unsigned Opcode, Type *ValTy, unsigned Index);
bool isSourceOfDivergence(const Value *V) const;
bool isAlwaysUniform(const Value *V) const;
unsigned getFlatAddressSpace() const {
// Don't bother running InferAddressSpaces pass on graphics shaders which
// don't use flat addressing.
if (IsGraphicsShader)
return -1;
return AMDGPUAS::FLAT_ADDRESS;
}
bool collectFlatAddressOperands(SmallVectorImpl<int> &OpIndexes,
Intrinsic::ID IID) const;
bool rewriteIntrinsicWithAddressSpace(IntrinsicInst *II,
Value *OldV, Value *NewV) const;
unsigned getVectorSplitCost() { return 0; }
unsigned getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index,
Type *SubTp);
bool areInlineCompatible(const Function *Caller,
const Function *Callee) const;
unsigned getInliningThresholdMultiplier() { return 9; }
int getInlinerVectorBonusPercent() { return 0; }
int getArithmeticReductionCost(unsigned Opcode,
Type *Ty,
bool IsPairwise);
int getMinMaxReductionCost(Type *Ty, Type *CondTy,
bool IsPairwiseForm,
bool IsUnsigned);
unsigned getUserCost(const User *U, ArrayRef<const Value *> Operands);
};
class R600TTIImpl final : public BasicTTIImplBase<R600TTIImpl> {
using BaseT = BasicTTIImplBase<R600TTIImpl>;
using TTI = TargetTransformInfo;
friend BaseT;
const R600Subtarget *ST;
const AMDGPUTargetLowering *TLI;
AMDGPUTTIImpl CommonTTI;
public:
explicit R600TTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
: BaseT(TM, F.getParent()->getDataLayout()),
ST(static_cast<const R600Subtarget*>(TM->getSubtargetImpl(F))),
TLI(ST->getTargetLowering()),
CommonTTI(TM, F) {}
const R600Subtarget *getST() const { return ST; }
const AMDGPUTargetLowering *getTLI() const { return TLI; }
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP);
unsigned getHardwareNumberOfRegisters(bool Vec) const;
unsigned getNumberOfRegisters(bool Vec) const;
unsigned getRegisterBitWidth(bool Vector) const;
unsigned getMinVectorRegisterBitWidth() const;
unsigned getLoadStoreVecRegBitWidth(unsigned AddrSpace) const;
bool isLegalToVectorizeMemChain(unsigned ChainSizeInBytes, unsigned Alignment,
unsigned AddrSpace) const;
bool isLegalToVectorizeLoadChain(unsigned ChainSizeInBytes,
unsigned Alignment,
unsigned AddrSpace) const;
bool isLegalToVectorizeStoreChain(unsigned ChainSizeInBytes,
unsigned Alignment,
unsigned AddrSpace) const;
unsigned getMaxInterleaveFactor(unsigned VF);
unsigned getCFInstrCost(unsigned Opcode);
int getVectorInstrCost(unsigned Opcode, Type *ValTy, unsigned Index);
};
} // end namespace llvm
#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUTARGETTRANSFORMINFO_H
|