summaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86TargetTransformInfo.cpp
blob: eba9d782d5c35a5a5fec723b31ed0d80e38b54aa (plain)
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
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
//===-- X86TargetTransformInfo.cpp - X86 specific TTI pass ----------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
/// \file
/// This file implements a TargetTransformInfo analysis pass 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.
///
//===----------------------------------------------------------------------===//

#define DEBUG_TYPE "x86tti"
#include "X86.h"
#include "X86TargetMachine.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/CostTable.h"
using namespace llvm;

// Declare the pass initialization routine locally as target-specific passes
// don't havve a target-wide initialization entry point, and so we rely on the
// pass constructor initialization.
namespace llvm {
void initializeX86TTIPass(PassRegistry &);
}

namespace {

class X86TTI : public ImmutablePass, public TargetTransformInfo {
  const X86TargetMachine *TM;
  const X86Subtarget *ST;
  const X86TargetLowering *TLI;

  /// Estimate the overhead of scalarizing an instruction. Insert and Extract
  /// are set if the result needs to be inserted and/or extracted from vectors.
  unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const;

public:
  X86TTI() : ImmutablePass(ID), TM(0), ST(0), TLI(0) {
    llvm_unreachable("This pass cannot be directly constructed");
  }

  X86TTI(const X86TargetMachine *TM)
      : ImmutablePass(ID), TM(TM), ST(TM->getSubtargetImpl()),
        TLI(TM->getTargetLowering()) {
    initializeX86TTIPass(*PassRegistry::getPassRegistry());
  }

  virtual void initializePass() {
    pushTTIStack(this);
  }

  virtual void finalizePass() {
    popTTIStack();
  }

  virtual void getAnalysisUsage(AnalysisUsage &AU) const {
    TargetTransformInfo::getAnalysisUsage(AU);
  }

  /// Pass identification.
  static char ID;

  /// Provide necessary pointer adjustments for the two base classes.
  virtual void *getAdjustedAnalysisPointer(const void *ID) {
    if (ID == &TargetTransformInfo::ID)
      return (TargetTransformInfo*)this;
    return this;
  }

  /// \name Scalar TTI Implementations
  /// @{
  virtual PopcntSupportKind getPopcntSupport(unsigned TyWidth) const;

  /// @}

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

  virtual unsigned getNumberOfRegisters(bool Vector) const;
  virtual unsigned getRegisterBitWidth(bool Vector) const;
  virtual unsigned getMaximumUnrollFactor() const;
  virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty,
                                          OperandValueKind,
                                          OperandValueKind) const;
  virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
                                  int Index, Type *SubTp) const;
  virtual unsigned getCastInstrCost(unsigned Opcode, Type *Dst,
                                    Type *Src) const;
  virtual unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
                                      Type *CondTy) const;
  virtual unsigned getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index) const;
  virtual unsigned getMemoryOpCost(unsigned Opcode, Type *Src,
                                   unsigned Alignment,
                                   unsigned AddressSpace) const;

  /// @}
};

} // end anonymous namespace

INITIALIZE_AG_PASS(X86TTI, TargetTransformInfo, "x86tti",
                   "X86 Target Transform Info", true, true, false)
char X86TTI::ID = 0;

ImmutablePass *
llvm::createX86TargetTransformInfoPass(const X86TargetMachine *TM) {
  return new X86TTI(TM);
}


//===----------------------------------------------------------------------===//
//
// X86 cost model.
//
//===----------------------------------------------------------------------===//

X86TTI::PopcntSupportKind X86TTI::getPopcntSupport(unsigned TyWidth) const {
  assert(isPowerOf2_32(TyWidth) && "Ty width must be power of 2");
  // TODO: Currently the __builtin_popcount() implementation using SSE3
  //   instructions is inefficient. Once the problem is fixed, we should
  //   call ST->hasSSE3() instead of ST->hasSSE4().
  return ST->hasSSE41() ? PSK_FastHardware : PSK_Software;
}

unsigned X86TTI::getNumberOfRegisters(bool Vector) const {
  if (Vector && !ST->hasSSE1())
    return 0;

  if (ST->is64Bit())
    return 16;
  return 8;
}

unsigned X86TTI::getRegisterBitWidth(bool Vector) const {
  if (Vector) {
    if (ST->hasAVX()) return 256;
    if (ST->hasSSE1()) return 128;
    return 0;
  }

  if (ST->is64Bit())
    return 64;
  return 32;

}

unsigned X86TTI::getMaximumUnrollFactor() const {
  if (ST->isAtom())
    return 1;

  // Sandybridge and Haswell have multiple execution ports and pipelined
  // vector units.
  if (ST->hasAVX())
    return 4;

  return 2;
}

unsigned X86TTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty,
                                        OperandValueKind Op1Info,
                                        OperandValueKind Op2Info) const {
  // Legalize the type.
  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Ty);

  int ISD = TLI->InstructionOpcodeToISD(Opcode);
  assert(ISD && "Invalid opcode");

  static const CostTblEntry<MVT> AVX2CostTable[] = {
    // Shifts on v4i64/v8i32 on AVX2 is legal even though we declare to
    // customize them to detect the cases where shift amount is a scalar one.
    { ISD::SHL,     MVT::v4i32,    1 },
    { ISD::SRL,     MVT::v4i32,    1 },
    { ISD::SRA,     MVT::v4i32,    1 },
    { ISD::SHL,     MVT::v8i32,    1 },
    { ISD::SRL,     MVT::v8i32,    1 },
    { ISD::SRA,     MVT::v8i32,    1 },
    { ISD::SHL,     MVT::v2i64,    1 },
    { ISD::SRL,     MVT::v2i64,    1 },
    { ISD::SHL,     MVT::v4i64,    1 },
    { ISD::SRL,     MVT::v4i64,    1 },

    { ISD::SHL,  MVT::v32i8,  42 }, // cmpeqb sequence.
    { ISD::SHL,  MVT::v16i16,  16*10 }, // Scalarized.

    { ISD::SRL,  MVT::v32i8,  32*10 }, // Scalarized.
    { ISD::SRL,  MVT::v16i16,  8*10 }, // Scalarized.

    { ISD::SRA,  MVT::v32i8,  32*10 }, // Scalarized.
    { ISD::SRA,  MVT::v16i16,  16*10 }, // Scalarized.
    { ISD::SRA,  MVT::v4i64,  4*10 }, // Scalarized.
  };

  // Look for AVX2 lowering tricks.
  if (ST->hasAVX2()) {
    int Idx = CostTableLookup<MVT>(AVX2CostTable, array_lengthof(AVX2CostTable),
                                   ISD, LT.second);
    if (Idx != -1)
      return LT.first * AVX2CostTable[Idx].Cost;
  }

  static const CostTblEntry<MVT> SSE2UniformConstCostTable[] = {
    // We don't correctly identify costs of casts because they are marked as
    // custom.
    // Constant splats are cheaper for the following instructions.
    { ISD::SHL,  MVT::v16i8,  1 }, // psllw.
    { ISD::SHL,  MVT::v8i16,  1 }, // psllw.
    { ISD::SHL,  MVT::v4i32,  1 }, // pslld
    { ISD::SHL,  MVT::v2i64,  1 }, // psllq.

    { ISD::SRL,  MVT::v16i8,  1 }, // psrlw.
    { ISD::SRL,  MVT::v8i16,  1 }, // psrlw.
    { ISD::SRL,  MVT::v4i32,  1 }, // psrld.
    { ISD::SRL,  MVT::v2i64,  1 }, // psrlq.

    { ISD::SRA,  MVT::v16i8,  4 }, // psrlw, pand, pxor, psubb.
    { ISD::SRA,  MVT::v8i16,  1 }, // psraw.
    { ISD::SRA,  MVT::v4i32,  1 }, // psrad.
  };

  if (Op2Info == TargetTransformInfo::OK_UniformConstantValue &&
      ST->hasSSE2()) {
    int Idx = CostTableLookup<MVT>(SSE2UniformConstCostTable,
                                   array_lengthof(SSE2UniformConstCostTable),
                                   ISD, LT.second);
    if (Idx != -1)
      return LT.first * SSE2UniformConstCostTable[Idx].Cost;
  }


  static const CostTblEntry<MVT> SSE2CostTable[] = {
    // We don't correctly identify costs of casts because they are marked as
    // custom.
    // For some cases, where the shift amount is a scalar we would be able
    // to generate better code. Unfortunately, when this is the case the value
    // (the splat) will get hoisted out of the loop, thereby making it invisible
    // to ISel. The cost model must return worst case assumptions because it is
    // used for vectorization and we don't want to make vectorized code worse
    // than scalar code.
    { ISD::SHL,  MVT::v16i8,  30 }, // cmpeqb sequence.
    { ISD::SHL,  MVT::v8i16,  8*10 }, // Scalarized.
    { ISD::SHL,  MVT::v4i32,  2*5 }, // We optimized this using mul.
    { ISD::SHL,  MVT::v2i64,  2*10 }, // Scalarized.

    { ISD::SRL,  MVT::v16i8,  16*10 }, // Scalarized.
    { ISD::SRL,  MVT::v8i16,  8*10 }, // Scalarized.
    { ISD::SRL,  MVT::v4i32,  4*10 }, // Scalarized.
    { ISD::SRL,  MVT::v2i64,  2*10 }, // Scalarized.

    { ISD::SRA,  MVT::v16i8,  16*10 }, // Scalarized.
    { ISD::SRA,  MVT::v8i16,  8*10 }, // Scalarized.
    { ISD::SRA,  MVT::v4i32,  4*10 }, // Scalarized.
    { ISD::SRA,  MVT::v2i64,  2*10 }, // Scalarized.
  };

  if (ST->hasSSE2()) {
    int Idx = CostTableLookup<MVT>(SSE2CostTable, array_lengthof(SSE2CostTable),
                                   ISD, LT.second);
    if (Idx != -1)
      return LT.first * SSE2CostTable[Idx].Cost;
  }

  static const CostTblEntry<MVT> AVX1CostTable[] = {
    // We don't have to scalarize unsupported ops. We can issue two half-sized
    // operations and we only need to extract the upper YMM half.
    // Two ops + 1 extract + 1 insert = 4.
    { ISD::MUL,     MVT::v8i32,    4 },
    { ISD::SUB,     MVT::v8i32,    4 },
    { ISD::ADD,     MVT::v8i32,    4 },
    { ISD::SUB,     MVT::v4i64,    4 },
    { ISD::ADD,     MVT::v4i64,    4 },
    // A v4i64 multiply is custom lowered as two split v2i64 vectors that then
    // are lowered as a series of long multiplies(3), shifts(4) and adds(2)
    // Because we believe v4i64 to be a legal type, we must also include the
    // split factor of two in the cost table. Therefore, the cost here is 18
    // instead of 9.
    { ISD::MUL,     MVT::v4i64,    18 },
  };

  // Look for AVX1 lowering tricks.
  if (ST->hasAVX() && !ST->hasAVX2()) {
    int Idx = CostTableLookup<MVT>(AVX1CostTable, array_lengthof(AVX1CostTable),
                                   ISD, LT.second);
    if (Idx != -1)
      return LT.first * AVX1CostTable[Idx].Cost;
  }

  // Custom lowering of vectors.
  static const CostTblEntry<MVT> CustomLowered[] = {
    // A v2i64/v4i64 and multiply is custom lowered as a series of long
    // multiplies(3), shifts(4) and adds(2).
    { ISD::MUL,     MVT::v2i64,    9 },
    { ISD::MUL,     MVT::v4i64,    9 },
  };
  int Idx = CostTableLookup<MVT>(CustomLowered, array_lengthof(CustomLowered),
                                 ISD, LT.second);
  if (Idx != -1)
    return LT.first * CustomLowered[Idx].Cost;

  // Special lowering of v4i32 mul on sse2, sse3: Lower v4i32 mul as 2x shuffle,
  // 2x pmuludq, 2x shuffle.
  if (ISD == ISD::MUL && LT.second == MVT::v4i32 && ST->hasSSE2() &&
      !ST->hasSSE41())
    return 6;

  // Fallback to the default implementation.
  return TargetTransformInfo::getArithmeticInstrCost(Opcode, Ty, Op1Info,
                                                     Op2Info);
}

unsigned X86TTI::getShuffleCost(ShuffleKind Kind, Type *Tp, int Index,
                                Type *SubTp) const {
  // We only estimate the cost of reverse shuffles.
  if (Kind != SK_Reverse)
    return TargetTransformInfo::getShuffleCost(Kind, Tp, Index, SubTp);

  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Tp);
  unsigned Cost = 1;
  if (LT.second.getSizeInBits() > 128)
    Cost = 3; // Extract + insert + copy.

  // Multiple by the number of parts.
  return Cost * LT.first;
}

unsigned X86TTI::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) const {
  int ISD = TLI->InstructionOpcodeToISD(Opcode);
  assert(ISD && "Invalid opcode");

  std::pair<unsigned, MVT> LTSrc = TLI->getTypeLegalizationCost(Src);
  std::pair<unsigned, MVT> LTDest = TLI->getTypeLegalizationCost(Dst);

  static const TypeConversionCostTblEntry<MVT> SSE2ConvTbl[] = {
    // These are somewhat magic numbers justified by looking at the output of
    // Intel's IACA, running some kernels and making sure when we take
    // legalization into account the throughput will be overestimated.
    { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 2*10 },
    { ISD::UINT_TO_FP, MVT::v2f64, MVT::v4i32, 4*10 },
    { ISD::UINT_TO_FP, MVT::v2f64, MVT::v8i16, 8*10 },
    { ISD::UINT_TO_FP, MVT::v2f64, MVT::v16i8, 16*10 },
    { ISD::SINT_TO_FP, MVT::v2f64, MVT::v2i64, 2*10 },
    { ISD::SINT_TO_FP, MVT::v2f64, MVT::v4i32, 4*10 },
    { ISD::SINT_TO_FP, MVT::v2f64, MVT::v8i16, 8*10 },
    { ISD::SINT_TO_FP, MVT::v2f64, MVT::v16i8, 16*10 },
    // There are faster sequences for float conversions.
    { ISD::UINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
    { ISD::UINT_TO_FP, MVT::v4f32, MVT::v4i32, 15 },
    { ISD::UINT_TO_FP, MVT::v4f32, MVT::v8i16, 15 },
    { ISD::UINT_TO_FP, MVT::v4f32, MVT::v16i8, 8 },
    { ISD::SINT_TO_FP, MVT::v4f32, MVT::v2i64, 15 },
    { ISD::SINT_TO_FP, MVT::v4f32, MVT::v4i32, 15 },
    { ISD::SINT_TO_FP, MVT::v4f32, MVT::v8i16, 15 },
    { ISD::SINT_TO_FP, MVT::v4f32, MVT::v16i8, 8 },
  };

  if (ST->hasSSE2() && !ST->hasAVX()) {
    int Idx = ConvertCostTableLookup<MVT>(SSE2ConvTbl,
                                          array_lengthof(SSE2ConvTbl),
                                          ISD, LTDest.second, LTSrc.second);
    if (Idx != -1)
      return LTSrc.first * SSE2ConvTbl[Idx].Cost;
  }

  EVT SrcTy = TLI->getValueType(Src);
  EVT DstTy = TLI->getValueType(Dst);

  // The function getSimpleVT only handles simple value types.
  if (!SrcTy.isSimple() || !DstTy.isSimple())
    return TargetTransformInfo::getCastInstrCost(Opcode, Dst, Src);

  static const TypeConversionCostTblEntry<MVT> AVXConversionTbl[] = {
    { ISD::SIGN_EXTEND, MVT::v8i32, MVT::v8i16, 1 },
    { ISD::ZERO_EXTEND, MVT::v8i32, MVT::v8i16, 1 },
    { ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i32, 1 },
    { ISD::ZERO_EXTEND, MVT::v4i64, MVT::v4i32, 1 },
    { ISD::TRUNCATE,    MVT::v4i32, MVT::v4i64, 1 },
    { ISD::TRUNCATE,    MVT::v8i16, MVT::v8i32, 1 },

    { ISD::SINT_TO_FP,  MVT::v8f32, MVT::v8i1,  8 },
    { ISD::SINT_TO_FP,  MVT::v8f32, MVT::v8i8,  8 },
    { ISD::SINT_TO_FP,  MVT::v8f32, MVT::v8i16, 5 },
    { ISD::SINT_TO_FP,  MVT::v8f32, MVT::v8i32, 1 },
    { ISD::SINT_TO_FP,  MVT::v4f32, MVT::v4i1,  3 },
    { ISD::SINT_TO_FP,  MVT::v4f32, MVT::v4i8,  3 },
    { ISD::SINT_TO_FP,  MVT::v4f32, MVT::v4i16, 3 },
    { ISD::SINT_TO_FP,  MVT::v4f32, MVT::v4i32, 1 },
    { ISD::SINT_TO_FP,  MVT::v4f64, MVT::v4i1,  3 },
    { ISD::SINT_TO_FP,  MVT::v4f64, MVT::v4i8,  3 },
    { ISD::SINT_TO_FP,  MVT::v4f64, MVT::v4i16, 3 },
    { ISD::SINT_TO_FP,  MVT::v4f64, MVT::v4i32, 1 },

    { ISD::UINT_TO_FP,  MVT::v8f32, MVT::v8i1,  6 },
    { ISD::UINT_TO_FP,  MVT::v8f32, MVT::v8i8,  5 },
    { ISD::UINT_TO_FP,  MVT::v8f32, MVT::v8i16, 5 },
    { ISD::UINT_TO_FP,  MVT::v8f32, MVT::v8i32, 9 },
    { ISD::UINT_TO_FP,  MVT::v4f32, MVT::v4i1,  7 },
    { ISD::UINT_TO_FP,  MVT::v4f32, MVT::v4i8,  2 },
    { ISD::UINT_TO_FP,  MVT::v4f32, MVT::v4i16, 2 },
    { ISD::UINT_TO_FP,  MVT::v4f32, MVT::v4i32, 6 },
    { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i1,  7 },
    { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i8,  2 },
    { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i16, 2 },
    { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i32, 6 },

    { ISD::FP_TO_SINT,  MVT::v8i8,  MVT::v8f32, 1 },
    { ISD::FP_TO_SINT,  MVT::v4i8,  MVT::v4f32, 1 },
    { ISD::ZERO_EXTEND, MVT::v8i32, MVT::v8i1,  6 },
    { ISD::SIGN_EXTEND, MVT::v8i32, MVT::v8i1,  9 },
    { ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i1,  8 },
    { ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i8,  6 },
    { ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i16, 6 },
    { ISD::TRUNCATE,    MVT::v8i32, MVT::v8i64, 3 },
  };

  if (ST->hasAVX()) {
    int Idx = ConvertCostTableLookup<MVT>(AVXConversionTbl,
                                 array_lengthof(AVXConversionTbl),
                                 ISD, DstTy.getSimpleVT(), SrcTy.getSimpleVT());
    if (Idx != -1)
      return AVXConversionTbl[Idx].Cost;
  }

  return TargetTransformInfo::getCastInstrCost(Opcode, Dst, Src);
}

unsigned X86TTI::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
                                    Type *CondTy) const {
  // Legalize the type.
  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(ValTy);

  MVT MTy = LT.second;

  int ISD = TLI->InstructionOpcodeToISD(Opcode);
  assert(ISD && "Invalid opcode");

  static const CostTblEntry<MVT> SSE42CostTbl[] = {
    { ISD::SETCC,   MVT::v2f64,   1 },
    { ISD::SETCC,   MVT::v4f32,   1 },
    { ISD::SETCC,   MVT::v2i64,   1 },
    { ISD::SETCC,   MVT::v4i32,   1 },
    { ISD::SETCC,   MVT::v8i16,   1 },
    { ISD::SETCC,   MVT::v16i8,   1 },
  };

  static const CostTblEntry<MVT> AVX1CostTbl[] = {
    { ISD::SETCC,   MVT::v4f64,   1 },
    { ISD::SETCC,   MVT::v8f32,   1 },
    // AVX1 does not support 8-wide integer compare.
    { ISD::SETCC,   MVT::v4i64,   4 },
    { ISD::SETCC,   MVT::v8i32,   4 },
    { ISD::SETCC,   MVT::v16i16,  4 },
    { ISD::SETCC,   MVT::v32i8,   4 },
  };

  static const CostTblEntry<MVT> AVX2CostTbl[] = {
    { ISD::SETCC,   MVT::v4i64,   1 },
    { ISD::SETCC,   MVT::v8i32,   1 },
    { ISD::SETCC,   MVT::v16i16,  1 },
    { ISD::SETCC,   MVT::v32i8,   1 },
  };

  if (ST->hasAVX2()) {
    int Idx = CostTableLookup<MVT>(AVX2CostTbl, array_lengthof(AVX2CostTbl), ISD, MTy);
    if (Idx != -1)
      return LT.first * AVX2CostTbl[Idx].Cost;
  }

  if (ST->hasAVX()) {
    int Idx = CostTableLookup<MVT>(AVX1CostTbl, array_lengthof(AVX1CostTbl), ISD, MTy);
    if (Idx != -1)
      return LT.first * AVX1CostTbl[Idx].Cost;
  }

  if (ST->hasSSE42()) {
    int Idx = CostTableLookup<MVT>(SSE42CostTbl, array_lengthof(SSE42CostTbl), ISD, MTy);
    if (Idx != -1)
      return LT.first * SSE42CostTbl[Idx].Cost;
  }

  return TargetTransformInfo::getCmpSelInstrCost(Opcode, ValTy, CondTy);
}

unsigned X86TTI::getVectorInstrCost(unsigned Opcode, Type *Val,
                                    unsigned Index) const {
  assert(Val->isVectorTy() && "This must be a vector type");

  if (Index != -1U) {
    // Legalize the type.
    std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Val);

    // This type is legalized to a scalar type.
    if (!LT.second.isVector())
      return 0;

    // The type may be split. Normalize the index to the new type.
    unsigned Width = LT.second.getVectorNumElements();
    Index = Index % Width;

    // Floating point scalars are already located in index #0.
    if (Val->getScalarType()->isFloatingPointTy() && Index == 0)
      return 0;
  }

  return TargetTransformInfo::getVectorInstrCost(Opcode, Val, Index);
}

unsigned X86TTI::getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
                                 unsigned AddressSpace) const {
  // Legalize the type.
  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Src);
  assert((Opcode == Instruction::Load || Opcode == Instruction::Store) &&
         "Invalid Opcode");

  // Each load/store unit costs 1.
  unsigned Cost = LT.first * 1;

  // On Sandybridge 256bit load/stores are double pumped
  // (but not on Haswell).
  if (LT.second.getSizeInBits() > 128 && !ST->hasAVX2())
    Cost*=2;

  return Cost;
}