aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm16/lib/CodeGen/MachineCombiner.cpp
blob: 974d570ece51f4ce24a5ede63772a09e3f003306 (plain) (blame)
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
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
//===---- MachineCombiner.cpp - Instcombining on SSA form machine code ----===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// The machine combiner pass uses machine trace metrics to ensure the combined
// instructions do not lengthen the critical path or the resource depth.
//===----------------------------------------------------------------------===//

#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/ProfileSummaryInfo.h"
#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
#include "llvm/CodeGen/MachineCombinerPattern.h"
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineLoopInfo.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/MachineSizeOpts.h"
#include "llvm/CodeGen/MachineTraceMetrics.h"
#include "llvm/CodeGen/RegisterClassInfo.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
#include "llvm/CodeGen/TargetSchedule.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/InitializePasses.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"

using namespace llvm;

#define DEBUG_TYPE "machine-combiner"

STATISTIC(NumInstCombined, "Number of machineinst combined");

static cl::opt<unsigned>
inc_threshold("machine-combiner-inc-threshold", cl::Hidden,
              cl::desc("Incremental depth computation will be used for basic "
                       "blocks with more instructions."), cl::init(500));

static cl::opt<bool> dump_intrs("machine-combiner-dump-subst-intrs", cl::Hidden,
                                cl::desc("Dump all substituted intrs"),
                                cl::init(false));

#ifdef EXPENSIVE_CHECKS
static cl::opt<bool> VerifyPatternOrder(
    "machine-combiner-verify-pattern-order", cl::Hidden,
    cl::desc(
        "Verify that the generated patterns are ordered by increasing latency"),
    cl::init(true));
#else
static cl::opt<bool> VerifyPatternOrder(
    "machine-combiner-verify-pattern-order", cl::Hidden,
    cl::desc(
        "Verify that the generated patterns are ordered by increasing latency"),
    cl::init(false));
#endif

namespace {
class MachineCombiner : public MachineFunctionPass {
  const TargetSubtargetInfo *STI;
  const TargetInstrInfo *TII;
  const TargetRegisterInfo *TRI;
  MCSchedModel SchedModel;
  MachineRegisterInfo *MRI;
  MachineLoopInfo *MLI; // Current MachineLoopInfo
  MachineTraceMetrics *Traces;
  MachineTraceMetrics::Ensemble *MinInstr;
  MachineBlockFrequencyInfo *MBFI;
  ProfileSummaryInfo *PSI;
  RegisterClassInfo RegClassInfo;

  TargetSchedModel TSchedModel;

  /// True if optimizing for code size.
  bool OptSize;

public:
  static char ID;
  MachineCombiner() : MachineFunctionPass(ID) {
    initializeMachineCombinerPass(*PassRegistry::getPassRegistry());
  }
  void getAnalysisUsage(AnalysisUsage &AU) const override;
  bool runOnMachineFunction(MachineFunction &MF) override;
  StringRef getPassName() const override { return "Machine InstCombiner"; }

private:
  bool combineInstructions(MachineBasicBlock *);
  MachineInstr *getOperandDef(const MachineOperand &MO);
  bool isTransientMI(const MachineInstr *MI);
  unsigned getDepth(SmallVectorImpl<MachineInstr *> &InsInstrs,
                    DenseMap<unsigned, unsigned> &InstrIdxForVirtReg,
                    MachineTraceMetrics::Trace BlockTrace);
  unsigned getLatency(MachineInstr *Root, MachineInstr *NewRoot,
                      MachineTraceMetrics::Trace BlockTrace);
  bool
  improvesCriticalPathLen(MachineBasicBlock *MBB, MachineInstr *Root,
                          MachineTraceMetrics::Trace BlockTrace,
                          SmallVectorImpl<MachineInstr *> &InsInstrs,
                          SmallVectorImpl<MachineInstr *> &DelInstrs,
                          DenseMap<unsigned, unsigned> &InstrIdxForVirtReg,
                          MachineCombinerPattern Pattern, bool SlackIsAccurate);
  bool reduceRegisterPressure(MachineInstr &Root, MachineBasicBlock *MBB,
                              SmallVectorImpl<MachineInstr *> &InsInstrs,
                              SmallVectorImpl<MachineInstr *> &DelInstrs,
                              MachineCombinerPattern Pattern);
  bool preservesResourceLen(MachineBasicBlock *MBB,
                            MachineTraceMetrics::Trace BlockTrace,
                            SmallVectorImpl<MachineInstr *> &InsInstrs,
                            SmallVectorImpl<MachineInstr *> &DelInstrs);
  void instr2instrSC(SmallVectorImpl<MachineInstr *> &Instrs,
                     SmallVectorImpl<const MCSchedClassDesc *> &InstrsSC);
  std::pair<unsigned, unsigned>
  getLatenciesForInstrSequences(MachineInstr &MI,
                                SmallVectorImpl<MachineInstr *> &InsInstrs,
                                SmallVectorImpl<MachineInstr *> &DelInstrs,
                                MachineTraceMetrics::Trace BlockTrace);

  void verifyPatternOrder(MachineBasicBlock *MBB, MachineInstr &Root,
                          SmallVector<MachineCombinerPattern, 16> &Patterns);
};
}

char MachineCombiner::ID = 0;
char &llvm::MachineCombinerID = MachineCombiner::ID;

INITIALIZE_PASS_BEGIN(MachineCombiner, DEBUG_TYPE,
                      "Machine InstCombiner", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
INITIALIZE_PASS_DEPENDENCY(MachineTraceMetrics)
INITIALIZE_PASS_END(MachineCombiner, DEBUG_TYPE, "Machine InstCombiner",
                    false, false)

void MachineCombiner::getAnalysisUsage(AnalysisUsage &AU) const {
  AU.setPreservesCFG();
  AU.addPreserved<MachineDominatorTree>();
  AU.addRequired<MachineLoopInfo>();
  AU.addPreserved<MachineLoopInfo>();
  AU.addRequired<MachineTraceMetrics>();
  AU.addPreserved<MachineTraceMetrics>();
  AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
  AU.addRequired<ProfileSummaryInfoWrapperPass>();
  MachineFunctionPass::getAnalysisUsage(AU);
}

MachineInstr *MachineCombiner::getOperandDef(const MachineOperand &MO) {
  MachineInstr *DefInstr = nullptr;
  // We need a virtual register definition.
  if (MO.isReg() && MO.getReg().isVirtual())
    DefInstr = MRI->getUniqueVRegDef(MO.getReg());
  // PHI's have no depth etc.
  if (DefInstr && DefInstr->isPHI())
    DefInstr = nullptr;
  return DefInstr;
}

/// Return true if MI is unlikely to generate an actual target instruction.
bool MachineCombiner::isTransientMI(const MachineInstr *MI) {
  if (!MI->isCopy())
    return MI->isTransient();

  // If MI is a COPY, check if its src and dst registers can be coalesced.
  Register Dst = MI->getOperand(0).getReg();
  Register Src = MI->getOperand(1).getReg();

  if (!MI->isFullCopy()) {
    // If src RC contains super registers of dst RC, it can also be coalesced.
    if (MI->getOperand(0).getSubReg() || Src.isPhysical() || Dst.isPhysical())
      return false;

    auto SrcSub = MI->getOperand(1).getSubReg();
    auto SrcRC = MRI->getRegClass(Src);
    auto DstRC = MRI->getRegClass(Dst);
    return TRI->getMatchingSuperRegClass(SrcRC, DstRC, SrcSub) != nullptr;
  }

  if (Src.isPhysical() && Dst.isPhysical())
    return Src == Dst;

  if (Src.isVirtual() && Dst.isVirtual()) {
    auto SrcRC = MRI->getRegClass(Src);
    auto DstRC = MRI->getRegClass(Dst);
    return SrcRC->hasSuperClassEq(DstRC) || SrcRC->hasSubClassEq(DstRC);
  }

  if (Src.isVirtual())
    std::swap(Src, Dst);

  // Now Src is physical register, Dst is virtual register.
  auto DstRC = MRI->getRegClass(Dst);
  return DstRC->contains(Src);
}

/// Computes depth of instructions in vector \InsInstr.
///
/// \param InsInstrs is a vector of machine instructions
/// \param InstrIdxForVirtReg is a dense map of virtual register to index
/// of defining machine instruction in \p InsInstrs
/// \param BlockTrace is a trace of machine instructions
///
/// \returns Depth of last instruction in \InsInstrs ("NewRoot")
unsigned
MachineCombiner::getDepth(SmallVectorImpl<MachineInstr *> &InsInstrs,
                          DenseMap<unsigned, unsigned> &InstrIdxForVirtReg,
                          MachineTraceMetrics::Trace BlockTrace) {
  SmallVector<unsigned, 16> InstrDepth;
  // For each instruction in the new sequence compute the depth based on the
  // operands. Use the trace information when possible. For new operands which
  // are tracked in the InstrIdxForVirtReg map depth is looked up in InstrDepth
  for (auto *InstrPtr : InsInstrs) { // for each Use
    unsigned IDepth = 0;
    for (const MachineOperand &MO : InstrPtr->operands()) {
      // Check for virtual register operand.
      if (!(MO.isReg() && MO.getReg().isVirtual()))
        continue;
      if (!MO.isUse())
        continue;
      unsigned DepthOp = 0;
      unsigned LatencyOp = 0;
      DenseMap<unsigned, unsigned>::iterator II =
          InstrIdxForVirtReg.find(MO.getReg());
      if (II != InstrIdxForVirtReg.end()) {
        // Operand is new virtual register not in trace
        assert(II->second < InstrDepth.size() && "Bad Index");
        MachineInstr *DefInstr = InsInstrs[II->second];
        assert(DefInstr &&
               "There must be a definition for a new virtual register");
        DepthOp = InstrDepth[II->second];
        int DefIdx = DefInstr->findRegisterDefOperandIdx(MO.getReg());
        int UseIdx = InstrPtr->findRegisterUseOperandIdx(MO.getReg());
        LatencyOp = TSchedModel.computeOperandLatency(DefInstr, DefIdx,
                                                      InstrPtr, UseIdx);
      } else {
        MachineInstr *DefInstr = getOperandDef(MO);
        if (DefInstr) {
          DepthOp = BlockTrace.getInstrCycles(*DefInstr).Depth;
          if (!isTransientMI(DefInstr))
            LatencyOp = TSchedModel.computeOperandLatency(
                DefInstr, DefInstr->findRegisterDefOperandIdx(MO.getReg()),
                InstrPtr, InstrPtr->findRegisterUseOperandIdx(MO.getReg()));
        }
      }
      IDepth = std::max(IDepth, DepthOp + LatencyOp);
    }
    InstrDepth.push_back(IDepth);
  }
  unsigned NewRootIdx = InsInstrs.size() - 1;
  return InstrDepth[NewRootIdx];
}

/// Computes instruction latency as max of latency of defined operands.
///
/// \param Root is a machine instruction that could be replaced by NewRoot.
/// It is used to compute a more accurate latency information for NewRoot in
/// case there is a dependent instruction in the same trace (\p BlockTrace)
/// \param NewRoot is the instruction for which the latency is computed
/// \param BlockTrace is a trace of machine instructions
///
/// \returns Latency of \p NewRoot
unsigned MachineCombiner::getLatency(MachineInstr *Root, MachineInstr *NewRoot,
                                     MachineTraceMetrics::Trace BlockTrace) {
  // Check each definition in NewRoot and compute the latency
  unsigned NewRootLatency = 0;

  for (const MachineOperand &MO : NewRoot->operands()) {
    // Check for virtual register operand.
    if (!(MO.isReg() && MO.getReg().isVirtual()))
      continue;
    if (!MO.isDef())
      continue;
    // Get the first instruction that uses MO
    MachineRegisterInfo::reg_iterator RI = MRI->reg_begin(MO.getReg());
    RI++;
    if (RI == MRI->reg_end())
      continue;
    MachineInstr *UseMO = RI->getParent();
    unsigned LatencyOp = 0;
    if (UseMO && BlockTrace.isDepInTrace(*Root, *UseMO)) {
      LatencyOp = TSchedModel.computeOperandLatency(
          NewRoot, NewRoot->findRegisterDefOperandIdx(MO.getReg()), UseMO,
          UseMO->findRegisterUseOperandIdx(MO.getReg()));
    } else {
      LatencyOp = TSchedModel.computeInstrLatency(NewRoot);
    }
    NewRootLatency = std::max(NewRootLatency, LatencyOp);
  }
  return NewRootLatency;
}

/// The combiner's goal may differ based on which pattern it is attempting
/// to optimize.
enum class CombinerObjective {
  MustReduceDepth,            // The data dependency chain must be improved.
  MustReduceRegisterPressure, // The register pressure must be reduced.
  Default                     // The critical path must not be lengthened.
};

static CombinerObjective getCombinerObjective(MachineCombinerPattern P) {
  // TODO: If C++ ever gets a real enum class, make this part of the
  // MachineCombinerPattern class.
  switch (P) {
  case MachineCombinerPattern::REASSOC_AX_BY:
  case MachineCombinerPattern::REASSOC_AX_YB:
  case MachineCombinerPattern::REASSOC_XA_BY:
  case MachineCombinerPattern::REASSOC_XA_YB:
  case MachineCombinerPattern::REASSOC_XY_AMM_BMM:
  case MachineCombinerPattern::REASSOC_XMM_AMM_BMM:
  case MachineCombinerPattern::SUBADD_OP1:
  case MachineCombinerPattern::SUBADD_OP2:
  case MachineCombinerPattern::FMADD_AX:
  case MachineCombinerPattern::FMADD_XA:
  case MachineCombinerPattern::FMSUB:
  case MachineCombinerPattern::FNMSUB:
    return CombinerObjective::MustReduceDepth;
  case MachineCombinerPattern::REASSOC_XY_BCA:
  case MachineCombinerPattern::REASSOC_XY_BAC:
    return CombinerObjective::MustReduceRegisterPressure;
  default:
    return CombinerObjective::Default;
  }
}

/// Estimate the latency of the new and original instruction sequence by summing
/// up the latencies of the inserted and deleted instructions. This assumes
/// that the inserted and deleted instructions are dependent instruction chains,
/// which might not hold in all cases.
std::pair<unsigned, unsigned> MachineCombiner::getLatenciesForInstrSequences(
    MachineInstr &MI, SmallVectorImpl<MachineInstr *> &InsInstrs,
    SmallVectorImpl<MachineInstr *> &DelInstrs,
    MachineTraceMetrics::Trace BlockTrace) {
  assert(!InsInstrs.empty() && "Only support sequences that insert instrs.");
  unsigned NewRootLatency = 0;
  // NewRoot is the last instruction in the \p InsInstrs vector.
  MachineInstr *NewRoot = InsInstrs.back();
  for (unsigned i = 0; i < InsInstrs.size() - 1; i++)
    NewRootLatency += TSchedModel.computeInstrLatency(InsInstrs[i]);
  NewRootLatency += getLatency(&MI, NewRoot, BlockTrace);

  unsigned RootLatency = 0;
  for (auto *I : DelInstrs)
    RootLatency += TSchedModel.computeInstrLatency(I);

  return {NewRootLatency, RootLatency};
}

bool MachineCombiner::reduceRegisterPressure(
    MachineInstr &Root, MachineBasicBlock *MBB,
    SmallVectorImpl<MachineInstr *> &InsInstrs,
    SmallVectorImpl<MachineInstr *> &DelInstrs,
    MachineCombinerPattern Pattern) {
  // FIXME: for now, we don't do any check for the register pressure patterns.
  // We treat them as always profitable. But we can do better if we make
  // RegPressureTracker class be aware of TIE attribute. Then we can get an
  // accurate compare of register pressure with DelInstrs or InsInstrs.
  return true;
}

/// The DAGCombine code sequence ends in MI (Machine Instruction) Root.
/// The new code sequence ends in MI NewRoot. A necessary condition for the new
/// sequence to replace the old sequence is that it cannot lengthen the critical
/// path. The definition of "improve" may be restricted by specifying that the
/// new path improves the data dependency chain (MustReduceDepth).
bool MachineCombiner::improvesCriticalPathLen(
    MachineBasicBlock *MBB, MachineInstr *Root,
    MachineTraceMetrics::Trace BlockTrace,
    SmallVectorImpl<MachineInstr *> &InsInstrs,
    SmallVectorImpl<MachineInstr *> &DelInstrs,
    DenseMap<unsigned, unsigned> &InstrIdxForVirtReg,
    MachineCombinerPattern Pattern,
    bool SlackIsAccurate) {
  // Get depth and latency of NewRoot and Root.
  unsigned NewRootDepth = getDepth(InsInstrs, InstrIdxForVirtReg, BlockTrace);
  unsigned RootDepth = BlockTrace.getInstrCycles(*Root).Depth;

  LLVM_DEBUG(dbgs() << "  Dependence data for " << *Root << "\tNewRootDepth: "
                    << NewRootDepth << "\tRootDepth: " << RootDepth);

  // For a transform such as reassociation, the cost equation is
  // conservatively calculated so that we must improve the depth (data
  // dependency cycles) in the critical path to proceed with the transform.
  // Being conservative also protects against inaccuracies in the underlying
  // machine trace metrics and CPU models.
  if (getCombinerObjective(Pattern) == CombinerObjective::MustReduceDepth) {
    LLVM_DEBUG(dbgs() << "\tIt MustReduceDepth ");
    LLVM_DEBUG(NewRootDepth < RootDepth
                   ? dbgs() << "\t  and it does it\n"
                   : dbgs() << "\t  but it does NOT do it\n");
    return NewRootDepth < RootDepth;
  }

  // A more flexible cost calculation for the critical path includes the slack
  // of the original code sequence. This may allow the transform to proceed
  // even if the instruction depths (data dependency cycles) become worse.

  // Account for the latency of the inserted and deleted instructions by
  unsigned NewRootLatency, RootLatency;
  std::tie(NewRootLatency, RootLatency) =
      getLatenciesForInstrSequences(*Root, InsInstrs, DelInstrs, BlockTrace);

  unsigned RootSlack = BlockTrace.getInstrSlack(*Root);
  unsigned NewCycleCount = NewRootDepth + NewRootLatency;
  unsigned OldCycleCount =
      RootDepth + RootLatency + (SlackIsAccurate ? RootSlack : 0);
  LLVM_DEBUG(dbgs() << "\n\tNewRootLatency: " << NewRootLatency
                    << "\tRootLatency: " << RootLatency << "\n\tRootSlack: "
                    << RootSlack << " SlackIsAccurate=" << SlackIsAccurate
                    << "\n\tNewRootDepth + NewRootLatency = " << NewCycleCount
                    << "\n\tRootDepth + RootLatency + RootSlack = "
                    << OldCycleCount;);
  LLVM_DEBUG(NewCycleCount <= OldCycleCount
                 ? dbgs() << "\n\t  It IMPROVES PathLen because"
                 : dbgs() << "\n\t  It DOES NOT improve PathLen because");
  LLVM_DEBUG(dbgs() << "\n\t\tNewCycleCount = " << NewCycleCount
                    << ", OldCycleCount = " << OldCycleCount << "\n");

  return NewCycleCount <= OldCycleCount;
}

/// helper routine to convert instructions into SC
void MachineCombiner::instr2instrSC(
    SmallVectorImpl<MachineInstr *> &Instrs,
    SmallVectorImpl<const MCSchedClassDesc *> &InstrsSC) {
  for (auto *InstrPtr : Instrs) {
    unsigned Opc = InstrPtr->getOpcode();
    unsigned Idx = TII->get(Opc).getSchedClass();
    const MCSchedClassDesc *SC = SchedModel.getSchedClassDesc(Idx);
    InstrsSC.push_back(SC);
  }
}

/// True when the new instructions do not increase resource length
bool MachineCombiner::preservesResourceLen(
    MachineBasicBlock *MBB, MachineTraceMetrics::Trace BlockTrace,
    SmallVectorImpl<MachineInstr *> &InsInstrs,
    SmallVectorImpl<MachineInstr *> &DelInstrs) {
  if (!TSchedModel.hasInstrSchedModel())
    return true;

  // Compute current resource length

  //ArrayRef<const MachineBasicBlock *> MBBarr(MBB);
  SmallVector <const MachineBasicBlock *, 1> MBBarr;
  MBBarr.push_back(MBB);
  unsigned ResLenBeforeCombine = BlockTrace.getResourceLength(MBBarr);

  // Deal with SC rather than Instructions.
  SmallVector<const MCSchedClassDesc *, 16> InsInstrsSC;
  SmallVector<const MCSchedClassDesc *, 16> DelInstrsSC;

  instr2instrSC(InsInstrs, InsInstrsSC);
  instr2instrSC(DelInstrs, DelInstrsSC);

  ArrayRef<const MCSchedClassDesc *> MSCInsArr{InsInstrsSC};
  ArrayRef<const MCSchedClassDesc *> MSCDelArr{DelInstrsSC};

  // Compute new resource length.
  unsigned ResLenAfterCombine =
      BlockTrace.getResourceLength(MBBarr, MSCInsArr, MSCDelArr);

  LLVM_DEBUG(dbgs() << "\t\tResource length before replacement: "
                    << ResLenBeforeCombine
                    << " and after: " << ResLenAfterCombine << "\n";);
  LLVM_DEBUG(
      ResLenAfterCombine <=
      ResLenBeforeCombine + TII->getExtendResourceLenLimit()
          ? dbgs() << "\t\t  As result it IMPROVES/PRESERVES Resource Length\n"
          : dbgs() << "\t\t  As result it DOES NOT improve/preserve Resource "
                      "Length\n");

  return ResLenAfterCombine <=
         ResLenBeforeCombine + TII->getExtendResourceLenLimit();
}

/// Inserts InsInstrs and deletes DelInstrs. Incrementally updates instruction
/// depths if requested.
///
/// \param MBB basic block to insert instructions in
/// \param MI current machine instruction
/// \param InsInstrs new instructions to insert in \p MBB
/// \param DelInstrs instruction to delete from \p MBB
/// \param MinInstr is a pointer to the machine trace information
/// \param RegUnits set of live registers, needed to compute instruction depths
/// \param TII is target instruction info, used to call target hook
/// \param Pattern is used to call target hook finalizeInsInstrs
/// \param IncrementalUpdate if true, compute instruction depths incrementally,
///                          otherwise invalidate the trace
static void insertDeleteInstructions(MachineBasicBlock *MBB, MachineInstr &MI,
                                     SmallVector<MachineInstr *, 16> InsInstrs,
                                     SmallVector<MachineInstr *, 16> DelInstrs,
                                     MachineTraceMetrics::Ensemble *MinInstr,
                                     SparseSet<LiveRegUnit> &RegUnits,
                                     const TargetInstrInfo *TII,
                                     MachineCombinerPattern Pattern,
                                     bool IncrementalUpdate) {
  // If we want to fix up some placeholder for some target, do it now.
  // We need this because in genAlternativeCodeSequence, we have not decided the
  // better pattern InsInstrs or DelInstrs, so we don't want generate some
  // sideeffect to the function. For example we need to delay the constant pool
  // entry creation here after InsInstrs is selected as better pattern.
  // Otherwise the constant pool entry created for InsInstrs will not be deleted
  // even if InsInstrs is not the better pattern.
  TII->finalizeInsInstrs(MI, Pattern, InsInstrs);

  for (auto *InstrPtr : InsInstrs)
    MBB->insert((MachineBasicBlock::iterator)&MI, InstrPtr);

  for (auto *InstrPtr : DelInstrs) {
    InstrPtr->eraseFromParent();
    // Erase all LiveRegs defined by the removed instruction
    for (auto *I = RegUnits.begin(); I != RegUnits.end();) {
      if (I->MI == InstrPtr)
        I = RegUnits.erase(I);
      else
        I++;
    }
  }

  if (IncrementalUpdate)
    for (auto *InstrPtr : InsInstrs)
      MinInstr->updateDepth(MBB, *InstrPtr, RegUnits);
  else
    MinInstr->invalidate(MBB);

  NumInstCombined++;
}

// Check that the difference between original and new latency is decreasing for
// later patterns. This helps to discover sub-optimal pattern orderings.
void MachineCombiner::verifyPatternOrder(
    MachineBasicBlock *MBB, MachineInstr &Root,
    SmallVector<MachineCombinerPattern, 16> &Patterns) {
  long PrevLatencyDiff = std::numeric_limits<long>::max();
  (void)PrevLatencyDiff; // Variable is used in assert only.
  for (auto P : Patterns) {
    SmallVector<MachineInstr *, 16> InsInstrs;
    SmallVector<MachineInstr *, 16> DelInstrs;
    DenseMap<unsigned, unsigned> InstrIdxForVirtReg;
    TII->genAlternativeCodeSequence(Root, P, InsInstrs, DelInstrs,
                                    InstrIdxForVirtReg);
    // Found pattern, but did not generate alternative sequence.
    // This can happen e.g. when an immediate could not be materialized
    // in a single instruction.
    if (InsInstrs.empty() || !TSchedModel.hasInstrSchedModelOrItineraries())
      continue;

    unsigned NewRootLatency, RootLatency;
    std::tie(NewRootLatency, RootLatency) = getLatenciesForInstrSequences(
        Root, InsInstrs, DelInstrs, MinInstr->getTrace(MBB));
    long CurrentLatencyDiff = ((long)RootLatency) - ((long)NewRootLatency);
    assert(CurrentLatencyDiff <= PrevLatencyDiff &&
           "Current pattern is better than previous pattern.");
    PrevLatencyDiff = CurrentLatencyDiff;
  }
}

/// Substitute a slow code sequence with a faster one by
/// evaluating instruction combining pattern.
/// The prototype of such a pattern is MUl + ADD -> MADD. Performs instruction
/// combining based on machine trace metrics. Only combine a sequence of
/// instructions  when this neither lengthens the critical path nor increases
/// resource pressure. When optimizing for codesize always combine when the new
/// sequence is shorter.
bool MachineCombiner::combineInstructions(MachineBasicBlock *MBB) {
  bool Changed = false;
  LLVM_DEBUG(dbgs() << "Combining MBB " << MBB->getName() << "\n");

  bool IncrementalUpdate = false;
  auto BlockIter = MBB->begin();
  decltype(BlockIter) LastUpdate;
  // Check if the block is in a loop.
  const MachineLoop *ML = MLI->getLoopFor(MBB);
  if (!MinInstr)
    MinInstr = Traces->getEnsemble(MachineTraceMetrics::TS_MinInstrCount);

  SparseSet<LiveRegUnit> RegUnits;
  RegUnits.setUniverse(TRI->getNumRegUnits());

  bool OptForSize = OptSize || llvm::shouldOptimizeForSize(MBB, PSI, MBFI);

  bool DoRegPressureReduce =
      TII->shouldReduceRegisterPressure(MBB, &RegClassInfo);

  while (BlockIter != MBB->end()) {
    auto &MI = *BlockIter++;
    SmallVector<MachineCombinerPattern, 16> Patterns;
    // The motivating example is:
    //
    //     MUL  Other        MUL_op1 MUL_op2  Other
    //      \    /               \      |    /
    //      ADD/SUB      =>        MADD/MSUB
    //      (=Root)                (=NewRoot)

    // The DAGCombine code always replaced MUL + ADD/SUB by MADD. While this is
    // usually beneficial for code size it unfortunately can hurt performance
    // when the ADD is on the critical path, but the MUL is not. With the
    // substitution the MUL becomes part of the critical path (in form of the
    // MADD) and can lengthen it on architectures where the MADD latency is
    // longer than the ADD latency.
    //
    // For each instruction we check if it can be the root of a combiner
    // pattern. Then for each pattern the new code sequence in form of MI is
    // generated and evaluated. When the efficiency criteria (don't lengthen
    // critical path, don't use more resources) is met the new sequence gets
    // hooked up into the basic block before the old sequence is removed.
    //
    // The algorithm does not try to evaluate all patterns and pick the best.
    // This is only an artificial restriction though. In practice there is
    // mostly one pattern, and getMachineCombinerPatterns() can order patterns
    // based on an internal cost heuristic. If
    // machine-combiner-verify-pattern-order is enabled, all patterns are
    // checked to ensure later patterns do not provide better latency savings.

    if (!TII->getMachineCombinerPatterns(MI, Patterns, DoRegPressureReduce))
      continue;

    if (VerifyPatternOrder)
      verifyPatternOrder(MBB, MI, Patterns);

    for (const auto P : Patterns) {
      SmallVector<MachineInstr *, 16> InsInstrs;
      SmallVector<MachineInstr *, 16> DelInstrs;
      DenseMap<unsigned, unsigned> InstrIdxForVirtReg;
      TII->genAlternativeCodeSequence(MI, P, InsInstrs, DelInstrs,
                                      InstrIdxForVirtReg);
      // Found pattern, but did not generate alternative sequence.
      // This can happen e.g. when an immediate could not be materialized
      // in a single instruction.
      if (InsInstrs.empty())
        continue;

      LLVM_DEBUG(if (dump_intrs) {
        dbgs() << "\tFor the Pattern (" << (int)P
               << ") these instructions could be removed\n";
        for (auto const *InstrPtr : DelInstrs)
          InstrPtr->print(dbgs(), /*IsStandalone*/false, /*SkipOpers*/false,
                          /*SkipDebugLoc*/false, /*AddNewLine*/true, TII);
        dbgs() << "\tThese instructions could replace the removed ones\n";
        for (auto const *InstrPtr : InsInstrs)
          InstrPtr->print(dbgs(), /*IsStandalone*/false, /*SkipOpers*/false,
                          /*SkipDebugLoc*/false, /*AddNewLine*/true, TII);
      });

      if (IncrementalUpdate && LastUpdate != BlockIter) {
        // Update depths since the last incremental update.
        MinInstr->updateDepths(LastUpdate, BlockIter, RegUnits);
        LastUpdate = BlockIter;
      }

      if (DoRegPressureReduce &&
          getCombinerObjective(P) ==
              CombinerObjective::MustReduceRegisterPressure) {
        if (MBB->size() > inc_threshold) {
          // Use incremental depth updates for basic blocks above threshold
          IncrementalUpdate = true;
          LastUpdate = BlockIter;
        }
        if (reduceRegisterPressure(MI, MBB, InsInstrs, DelInstrs, P)) {
          // Replace DelInstrs with InsInstrs.
          insertDeleteInstructions(MBB, MI, InsInstrs, DelInstrs, MinInstr,
                                   RegUnits, TII, P, IncrementalUpdate);
          Changed |= true;

          // Go back to previous instruction as it may have ILP reassociation
          // opportunity.
          BlockIter--;
          break;
        }
      }

      if (ML && TII->isThroughputPattern(P)) {
        LLVM_DEBUG(dbgs() << "\t Replacing due to throughput pattern in loop\n");
        insertDeleteInstructions(MBB, MI, InsInstrs, DelInstrs, MinInstr,
                                 RegUnits, TII, P, IncrementalUpdate);
        // Eagerly stop after the first pattern fires.
        Changed = true;
        break;
      } else if (OptForSize && InsInstrs.size() < DelInstrs.size()) {
        LLVM_DEBUG(dbgs() << "\t Replacing due to OptForSize ("
                          << InsInstrs.size() << " < "
                          << DelInstrs.size() << ")\n");
        insertDeleteInstructions(MBB, MI, InsInstrs, DelInstrs, MinInstr,
                                 RegUnits, TII, P, IncrementalUpdate);
        // Eagerly stop after the first pattern fires.
        Changed = true;
        break;
      } else {
        // For big basic blocks, we only compute the full trace the first time
        // we hit this. We do not invalidate the trace, but instead update the
        // instruction depths incrementally.
        // NOTE: Only the instruction depths up to MI are accurate. All other
        // trace information is not updated.
        MachineTraceMetrics::Trace BlockTrace = MinInstr->getTrace(MBB);
        Traces->verifyAnalysis();
        if (improvesCriticalPathLen(MBB, &MI, BlockTrace, InsInstrs, DelInstrs,
                                    InstrIdxForVirtReg, P,
                                    !IncrementalUpdate) &&
            preservesResourceLen(MBB, BlockTrace, InsInstrs, DelInstrs)) {
          if (MBB->size() > inc_threshold) {
            // Use incremental depth updates for basic blocks above treshold
            IncrementalUpdate = true;
            LastUpdate = BlockIter;
          }

          insertDeleteInstructions(MBB, MI, InsInstrs, DelInstrs, MinInstr,
                                   RegUnits, TII, P, IncrementalUpdate);

          // Eagerly stop after the first pattern fires.
          Changed = true;
          break;
        }
        // Cleanup instructions of the alternative code sequence. There is no
        // use for them.
        MachineFunction *MF = MBB->getParent();
        for (auto *InstrPtr : InsInstrs)
          MF->deleteMachineInstr(InstrPtr);
      }
      InstrIdxForVirtReg.clear();
    }
  }

  if (Changed && IncrementalUpdate)
    Traces->invalidate(MBB);
  return Changed;
}

bool MachineCombiner::runOnMachineFunction(MachineFunction &MF) {
  STI = &MF.getSubtarget();
  TII = STI->getInstrInfo();
  TRI = STI->getRegisterInfo();
  SchedModel = STI->getSchedModel();
  TSchedModel.init(STI);
  MRI = &MF.getRegInfo();
  MLI = &getAnalysis<MachineLoopInfo>();
  Traces = &getAnalysis<MachineTraceMetrics>();
  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
  MBFI = (PSI && PSI->hasProfileSummary()) ?
         &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
         nullptr;
  MinInstr = nullptr;
  OptSize = MF.getFunction().hasOptSize();
  RegClassInfo.runOnMachineFunction(MF);

  LLVM_DEBUG(dbgs() << getPassName() << ": " << MF.getName() << '\n');
  if (!TII->useMachineCombiner()) {
    LLVM_DEBUG(
        dbgs()
        << "  Skipping pass: Target does not support machine combiner\n");
    return false;
  }

  bool Changed = false;

  // Try to combine instructions.
  for (auto &MBB : MF)
    Changed |= combineInstructions(&MBB);

  return Changed;
}