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
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
|
// llvm/Target/TargetTransformImpl.cpp - Target Loop Trans Info ---*- C++ -*-=//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "llvm/Target/TargetTransformImpl.h"
#include "llvm/Target/TargetLowering.h"
#include <utility>
using namespace llvm;
//===----------------------------------------------------------------------===//
//
// Calls used by scalar transformations.
//
//===----------------------------------------------------------------------===//
bool ScalarTargetTransformImpl::isLegalAddImmediate(int64_t imm) const {
return TLI->isLegalAddImmediate(imm);
}
bool ScalarTargetTransformImpl::isLegalICmpImmediate(int64_t imm) const {
return TLI->isLegalICmpImmediate(imm);
}
bool ScalarTargetTransformImpl::isLegalAddressingMode(const AddrMode &AM,
Type *Ty) const {
return TLI->isLegalAddressingMode(AM, Ty);
}
bool ScalarTargetTransformImpl::isTruncateFree(Type *Ty1, Type *Ty2) const {
return TLI->isTruncateFree(Ty1, Ty2);
}
bool ScalarTargetTransformImpl::isTypeLegal(Type *Ty) const {
EVT T = TLI->getValueType(Ty);
return TLI->isTypeLegal(T);
}
unsigned ScalarTargetTransformImpl::getJumpBufAlignment() const {
return TLI->getJumpBufAlignment();
}
unsigned ScalarTargetTransformImpl::getJumpBufSize() const {
return TLI->getJumpBufSize();
}
bool ScalarTargetTransformImpl::shouldBuildLookupTables() const {
return TLI->supportJumpTables() &&
(TLI->isOperationLegalOrCustom(ISD::BR_JT, MVT::Other) ||
TLI->isOperationLegalOrCustom(ISD::BRIND, MVT::Other));
}
//===----------------------------------------------------------------------===//
//
// Calls used by the vectorizers.
//
//===----------------------------------------------------------------------===//
int VectorTargetTransformImpl::InstructionOpcodeToISD(unsigned Opcode) const {
enum InstructionOpcodes {
#define HANDLE_INST(NUM, OPCODE, CLASS) OPCODE = NUM,
#define LAST_OTHER_INST(NUM) InstructionOpcodesCount = NUM
#include "llvm/Instruction.def"
};
switch (static_cast<InstructionOpcodes>(Opcode)) {
case Ret: return 0;
case Br: return 0;
case Switch: return 0;
case IndirectBr: return 0;
case Invoke: return 0;
case Resume: return 0;
case Unreachable: return 0;
case Add: return ISD::ADD;
case FAdd: return ISD::FADD;
case Sub: return ISD::SUB;
case FSub: return ISD::FSUB;
case Mul: return ISD::MUL;
case FMul: return ISD::FMUL;
case UDiv: return ISD::UDIV;
case SDiv: return ISD::UDIV;
case FDiv: return ISD::FDIV;
case URem: return ISD::UREM;
case SRem: return ISD::SREM;
case FRem: return ISD::FREM;
case Shl: return ISD::SHL;
case LShr: return ISD::SRL;
case AShr: return ISD::SRA;
case And: return ISD::AND;
case Or: return ISD::OR;
case Xor: return ISD::XOR;
case Alloca: return 0;
case Load: return ISD::LOAD;
case Store: return ISD::STORE;
case GetElementPtr: return 0;
case Fence: return 0;
case AtomicCmpXchg: return 0;
case AtomicRMW: return 0;
case Trunc: return ISD::TRUNCATE;
case ZExt: return ISD::ZERO_EXTEND;
case SExt: return ISD::SIGN_EXTEND;
case FPToUI: return ISD::FP_TO_UINT;
case FPToSI: return ISD::FP_TO_SINT;
case UIToFP: return ISD::UINT_TO_FP;
case SIToFP: return ISD::SINT_TO_FP;
case FPTrunc: return ISD::FP_ROUND;
case FPExt: return ISD::FP_EXTEND;
case PtrToInt: return ISD::BITCAST;
case IntToPtr: return ISD::BITCAST;
case BitCast: return ISD::BITCAST;
case ICmp: return ISD::SETCC;
case FCmp: return ISD::SETCC;
case PHI: return 0;
case Call: return 0;
case Select: return ISD::SELECT;
case UserOp1: return 0;
case UserOp2: return 0;
case VAArg: return 0;
case ExtractElement: return ISD::EXTRACT_VECTOR_ELT;
case InsertElement: return ISD::INSERT_VECTOR_ELT;
case ShuffleVector: return ISD::VECTOR_SHUFFLE;
case ExtractValue: return ISD::MERGE_VALUES;
case InsertValue: return ISD::MERGE_VALUES;
case LandingPad: return 0;
}
llvm_unreachable("Unknown instruction type encountered!");
}
std::pair<unsigned, MVT>
VectorTargetTransformImpl::getTypeLegalizationCost(Type *Ty) const {
LLVMContext &C = Ty->getContext();
EVT MTy = TLI->getValueType(Ty);
unsigned Cost = 1;
// We keep legalizing the type until we find a legal kind. We assume that
// the only operation that costs anything is the split. After splitting
// we need to handle two types.
while (true) {
TargetLowering::LegalizeKind LK = TLI->getTypeConversion(C, MTy);
if (LK.first == TargetLowering::TypeLegal)
return std::make_pair(Cost, MTy.getSimpleVT());
if (LK.first == TargetLowering::TypeSplitVector ||
LK.first == TargetLowering::TypeExpandInteger)
Cost *= 2;
// Keep legalizing the type.
MTy = LK.second;
}
}
unsigned
VectorTargetTransformImpl::getScalarizationOverhead(Type *Ty,
bool Insert,
bool Extract) const {
assert (Ty->isVectorTy() && "Can only scalarize vectors");
unsigned Cost = 0;
for (int i = 0, e = Ty->getVectorNumElements(); i < e; ++i) {
if (Insert)
Cost += getVectorInstrCost(Instruction::InsertElement, Ty, i);
if (Extract)
Cost += getVectorInstrCost(Instruction::ExtractElement, Ty, i);
}
return Cost;
}
unsigned VectorTargetTransformImpl::getArithmeticInstrCost(unsigned Opcode,
Type *Ty) const {
// Check if any of the operands are vector operands.
int ISD = InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
std::pair<unsigned, MVT> LT = getTypeLegalizationCost(Ty);
if (!TLI->isOperationExpand(ISD, LT.second)) {
// The operation is legal. Assume it costs 1. Multiply
// by the type-legalization overhead.
return LT.first * 1;
}
// Else, assume that we need to scalarize this op.
if (Ty->isVectorTy()) {
unsigned Num = Ty->getVectorNumElements();
unsigned Cost = getArithmeticInstrCost(Opcode, Ty->getScalarType());
// return the cost of multiple scalar invocation plus the cost of inserting
// and extracting the values.
return getScalarizationOverhead(Ty, true, true) + Num * Cost;
}
// We don't know anything about this scalar instruction.
return 1;
}
unsigned VectorTargetTransformImpl::getBroadcastCost(Type *Tp) const {
return 1;
}
unsigned VectorTargetTransformImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
Type *Src) const {
int ISD = InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
std::pair<unsigned, MVT> SrcLT = getTypeLegalizationCost(Src);
std::pair<unsigned, MVT> DstLT = getTypeLegalizationCost(Dst);
// Handle scalar conversions.
if (!Src->isVectorTy() && !Dst->isVectorTy()) {
// Scalar bitcasts are usually free.
if (Opcode == Instruction::BitCast)
return 0;
if (Opcode == Instruction::Trunc &&
TLI->isTruncateFree(SrcLT.second, DstLT.second))
return 0;
if (Opcode == Instruction::ZExt &&
TLI->isZExtFree(SrcLT.second, DstLT.second))
return 0;
// Just check the op cost. If the operation is legal then assume it costs 1.
if (!TLI->isOperationExpand(ISD, DstLT.second))
return 1;
// Assume that illegal scalar instruction are expensive.
return 4;
}
// Check vector-to-vector casts.
if (Dst->isVectorTy() && Src->isVectorTy()) {
// If the cast is between same-sized registers, then the check is simple.
if (SrcLT.first == DstLT.first &&
SrcLT.second.getSizeInBits() == DstLT.second.getSizeInBits()) {
// Bitcast between types that are legalized to the same type are free.
if (Opcode == Instruction::BitCast || Opcode == Instruction::Trunc)
return 0;
// Assume that Zext is done using AND.
if (Opcode == Instruction::ZExt)
return 1;
// Assume that sext is done using SHL and SRA.
if (Opcode == Instruction::SExt)
return 2;
// Just check the op cost. If the operation is legal then assume it costs
// 1 and multiply by the type-legalization overhead.
if (!TLI->isOperationExpand(ISD, DstLT.second))
return SrcLT.first * 1;
}
// If we are converting vectors and the operation is illegal, or
// if the vectors are legalized to different types, estimate the
// scalarization costs.
unsigned Num = Dst->getVectorNumElements();
unsigned Cost = getCastInstrCost(Opcode, Dst->getScalarType(),
Src->getScalarType());
// Return the cost of multiple scalar invocation plus the cost of
// inserting and extracting the values.
return getScalarizationOverhead(Dst, true, true) + Num * Cost;
}
// We already handled vector-to-vector and scalar-to-scalar conversions. This
// is where we handle bitcast between vectors and scalars. We need to assume
// that the conversion is scalarized in one way or another.
if (Opcode == Instruction::BitCast)
// Illegal bitcasts are done by storing and loading from a stack slot.
return (Src->isVectorTy()? getScalarizationOverhead(Src, false, true):0) +
(Dst->isVectorTy()? getScalarizationOverhead(Dst, true, false):0);
llvm_unreachable("Unhandled cast");
}
unsigned VectorTargetTransformImpl::getCFInstrCost(unsigned Opcode) const {
return 0;
}
unsigned VectorTargetTransformImpl::getCmpSelInstrCost(unsigned Opcode,
Type *ValTy,
Type *CondTy) const {
int ISD = InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
// Selects on vectors are actually vector selects.
if (ISD == ISD::SELECT) {
assert(CondTy && "CondTy must exist");
if (CondTy->isVectorTy())
ISD = ISD::VSELECT;
}
std::pair<unsigned, MVT> LT = getTypeLegalizationCost(ValTy);
if (!TLI->isOperationExpand(ISD, LT.second)) {
// The operation is legal. Assume it costs 1. Multiply
// by the type-legalization overhead.
return LT.first * 1;
}
// Otherwise, assume that the cast is scalarized.
if (ValTy->isVectorTy()) {
unsigned Num = ValTy->getVectorNumElements();
if (CondTy)
CondTy = CondTy->getScalarType();
unsigned Cost = getCmpSelInstrCost(Opcode, ValTy->getScalarType(),
CondTy);
// Return the cost of multiple scalar invocation plus the cost of inserting
// and extracting the values.
return getScalarizationOverhead(ValTy, true, false) + Num * Cost;
}
// Unknown scalar opcode.
return 1;
}
unsigned VectorTargetTransformImpl::getVectorInstrCost(unsigned Opcode,
Type *Val,
unsigned Index) const {
return 1;
}
unsigned
VectorTargetTransformImpl::getInstrCost(unsigned Opcode, Type *Ty1,
Type *Ty2) const {
return 1;
}
unsigned
VectorTargetTransformImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
unsigned Alignment,
unsigned AddressSpace) const {
std::pair<unsigned, MVT> LT = getTypeLegalizationCost(Src);
// Assume that all loads of legal types cost 1.
return LT.first;
}
unsigned
VectorTargetTransformImpl::getIntrinsicInstrCost(Intrinsic::ID, Type *RetTy,
ArrayRef<Type*> Tys) const {
// assume that we need to scalarize this intrinsic.
unsigned ScalarizationCost = 0;
unsigned ScalarCalls = 1;
if (RetTy->isVectorTy()) {
ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
}
for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
if (Tys[i]->isVectorTy()) {
ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
}
}
return ScalarCalls + ScalarizationCost;
}
unsigned
VectorTargetTransformImpl::getNumberOfParts(Type *Tp) const {
std::pair<unsigned, MVT> LT = getTypeLegalizationCost(Tp);
return LT.first;
}
|