llvm.org GIT mirror llvm / release_70 lib / CodeGen / MIRCanonicalizerPass.cpp
release_70

Tree @release_70 (Download .tar.gz)

MIRCanonicalizerPass.cpp @release_70raw · history · 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
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
//===-------------- MIRCanonicalizer.cpp - MIR Canonicalizer --------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// The purpose of this pass is to employ a canonical code transformation so
// that code compiled with slightly different IR passes can be diffed more
// effectively than otherwise. This is done by renaming vregs in a given
// LiveRange in a canonical way. This pass also does a pseudo-scheduling to
// move defs closer to their use inorder to reduce diffs caused by slightly
// different schedules.
//
// Basic Usage:
//
// llc -o - -run-pass mir-canonicalizer example.mir
//
// Reorders instructions canonically.
// Renames virtual register operands canonically.
// Strips certain MIR artifacts (optionally).
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/PostOrderIterator.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/Support/raw_ostream.h"

#include <queue>

using namespace llvm;

namespace llvm {
extern char &MIRCanonicalizerID;
} // namespace llvm

#define DEBUG_TYPE "mir-canonicalizer"

static cl::opt<unsigned>
    CanonicalizeFunctionNumber("canon-nth-function", cl::Hidden, cl::init(~0u),
                               cl::value_desc("N"),
                               cl::desc("Function number to canonicalize."));

static cl::opt<unsigned> CanonicalizeBasicBlockNumber(
    "canon-nth-basicblock", cl::Hidden, cl::init(~0u), cl::value_desc("N"),
    cl::desc("BasicBlock number to canonicalize."));

namespace {

class MIRCanonicalizer : public MachineFunctionPass {
public:
  static char ID;
  MIRCanonicalizer() : MachineFunctionPass(ID) {}

  StringRef getPassName() const override {
    return "Rename register operands in a canonical ordering.";
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.setPreservesCFG();
    MachineFunctionPass::getAnalysisUsage(AU);
  }

  bool runOnMachineFunction(MachineFunction &MF) override;
};

} // end anonymous namespace

enum VRType { RSE_Reg = 0, RSE_FrameIndex, RSE_NewCandidate };
class TypedVReg {
  VRType type;
  unsigned reg;

public:
  TypedVReg(unsigned reg) : type(RSE_Reg), reg(reg) {}
  TypedVReg(VRType type) : type(type), reg(~0U) {
    assert(type != RSE_Reg && "Expected a non-register type.");
  }

  bool isReg() const { return type == RSE_Reg; }
  bool isFrameIndex() const { return type == RSE_FrameIndex; }
  bool isCandidate() const { return type == RSE_NewCandidate; }

  VRType getType() const { return type; }
  unsigned getReg() const {
    assert(this->isReg() && "Expected a virtual or physical register.");
    return reg;
  }
};

char MIRCanonicalizer::ID;

char &llvm::MIRCanonicalizerID = MIRCanonicalizer::ID;

INITIALIZE_PASS_BEGIN(MIRCanonicalizer, "mir-canonicalizer",
                      "Rename Register Operands Canonically", false, false)

INITIALIZE_PASS_END(MIRCanonicalizer, "mir-canonicalizer",
                    "Rename Register Operands Canonically", false, false)

static std::vector<MachineBasicBlock *> GetRPOList(MachineFunction &MF) {
  ReversePostOrderTraversal<MachineBasicBlock *> RPOT(&*MF.begin());
  std::vector<MachineBasicBlock *> RPOList;
  for (auto MBB : RPOT) {
    RPOList.push_back(MBB);
  }

  return RPOList;
}

static bool
rescheduleLexographically(std::vector<MachineInstr *> instructions,
                          MachineBasicBlock *MBB,
                          std::function<MachineBasicBlock::iterator()> getPos) {

  bool Changed = false;
  using StringInstrPair = std::pair<std::string, MachineInstr *>;
  std::vector<StringInstrPair> StringInstrMap;

  for (auto *II : instructions) {
    std::string S;
    raw_string_ostream OS(S);
    II->print(OS);
    OS.flush();

    // Trim the assignment, or start from the begining in the case of a store.
    const size_t i = S.find("=");
    StringInstrMap.push_back({(i == std::string::npos) ? S : S.substr(i), II});
  }

  llvm::sort(StringInstrMap.begin(), StringInstrMap.end(),
            [](const StringInstrPair &a, const StringInstrPair &b) -> bool {
              return (a.first < b.first);
            });

  for (auto &II : StringInstrMap) {

    LLVM_DEBUG({
      dbgs() << "Splicing ";
      II.second->dump();
      dbgs() << " right before: ";
      getPos()->dump();
    });

    Changed = true;
    MBB->splice(getPos(), MBB, II.second);
  }

  return Changed;
}

static bool rescheduleCanonically(unsigned &PseudoIdempotentInstCount,
                                  MachineBasicBlock *MBB) {

  bool Changed = false;

  // Calculates the distance of MI from the begining of its parent BB.
  auto getInstrIdx = [](const MachineInstr &MI) {
    unsigned i = 0;
    for (auto &CurMI : *MI.getParent()) {
      if (&CurMI == &MI)
        return i;
      i++;
    }
    return ~0U;
  };

  // Pre-Populate vector of instructions to reschedule so that we don't
  // clobber the iterator.
  std::vector<MachineInstr *> Instructions;
  for (auto &MI : *MBB) {
    Instructions.push_back(&MI);
  }

  std::map<MachineInstr *, std::vector<MachineInstr *>> MultiUsers;
  std::vector<MachineInstr *> PseudoIdempotentInstructions;
  std::vector<unsigned> PhysRegDefs;
  for (auto *II : Instructions) {
    for (unsigned i = 1; i < II->getNumOperands(); i++) {
      MachineOperand &MO = II->getOperand(i);
      if (!MO.isReg())
        continue;

      if (TargetRegisterInfo::isVirtualRegister(MO.getReg()))
        continue;

      if (!MO.isDef())
        continue;

      PhysRegDefs.push_back(MO.getReg());
    }
  }

  for (auto *II : Instructions) {
    if (II->getNumOperands() == 0)
      continue;
    if (II->mayLoadOrStore())
      continue;

    MachineOperand &MO = II->getOperand(0);
    if (!MO.isReg() || !TargetRegisterInfo::isVirtualRegister(MO.getReg()))
      continue;
    if (!MO.isDef())
      continue;

    bool IsPseudoIdempotent = true;
    for (unsigned i = 1; i < II->getNumOperands(); i++) {

      if (II->getOperand(i).isImm()) {
        continue;
      }

      if (II->getOperand(i).isReg()) {
        if (!TargetRegisterInfo::isVirtualRegister(II->getOperand(i).getReg()))
          if (llvm::find(PhysRegDefs, II->getOperand(i).getReg()) ==
              PhysRegDefs.end()) {
            continue;
          }
      }

      IsPseudoIdempotent = false;
      break;
    }

    if (IsPseudoIdempotent) {
      PseudoIdempotentInstructions.push_back(II);
      continue;
    }

    LLVM_DEBUG(dbgs() << "Operand " << 0 << " of "; II->dump(); MO.dump(););

    MachineInstr *Def = II;
    unsigned Distance = ~0U;
    MachineInstr *UseToBringDefCloserTo = nullptr;
    MachineRegisterInfo *MRI = &MBB->getParent()->getRegInfo();
    for (auto &UO : MRI->use_nodbg_operands(MO.getReg())) {
      MachineInstr *UseInst = UO.getParent();

      const unsigned DefLoc = getInstrIdx(*Def);
      const unsigned UseLoc = getInstrIdx(*UseInst);
      const unsigned Delta = (UseLoc - DefLoc);

      if (UseInst->getParent() != Def->getParent())
        continue;
      if (DefLoc >= UseLoc)
        continue;

      if (Delta < Distance) {
        Distance = Delta;
        UseToBringDefCloserTo = UseInst;
      }
    }

    const auto BBE = MBB->instr_end();
    MachineBasicBlock::iterator DefI = BBE;
    MachineBasicBlock::iterator UseI = BBE;

    for (auto BBI = MBB->instr_begin(); BBI != BBE; ++BBI) {

      if (DefI != BBE && UseI != BBE)
        break;

      if (&*BBI == Def) {
        DefI = BBI;
        continue;
      }

      if (&*BBI == UseToBringDefCloserTo) {
        UseI = BBI;
        continue;
      }
    }

    if (DefI == BBE || UseI == BBE)
      continue;

    LLVM_DEBUG({
      dbgs() << "Splicing ";
      DefI->dump();
      dbgs() << " right before: ";
      UseI->dump();
    });

    MultiUsers[UseToBringDefCloserTo].push_back(Def);
    Changed = true;
    MBB->splice(UseI, MBB, DefI);
  }

  // Sort the defs for users of multiple defs lexographically.
  for (const auto &E : MultiUsers) {

    auto UseI =
        std::find_if(MBB->instr_begin(), MBB->instr_end(),
                     [&](MachineInstr &MI) -> bool { return &MI == E.first; });

    if (UseI == MBB->instr_end())
      continue;

    LLVM_DEBUG(
        dbgs() << "Rescheduling Multi-Use Instructions Lexographically.";);
    Changed |= rescheduleLexographically(
        E.second, MBB, [&]() -> MachineBasicBlock::iterator { return UseI; });
  }

  PseudoIdempotentInstCount = PseudoIdempotentInstructions.size();
  LLVM_DEBUG(
      dbgs() << "Rescheduling Idempotent Instructions Lexographically.";);
  Changed |= rescheduleLexographically(
      PseudoIdempotentInstructions, MBB,
      [&]() -> MachineBasicBlock::iterator { return MBB->begin(); });

  return Changed;
}

static bool propagateLocalCopies(MachineBasicBlock *MBB) {
  bool Changed = false;
  MachineRegisterInfo &MRI = MBB->getParent()->getRegInfo();

  std::vector<MachineInstr *> Copies;
  for (MachineInstr &MI : MBB->instrs()) {
    if (MI.isCopy())
      Copies.push_back(&MI);
  }

  for (MachineInstr *MI : Copies) {

    if (!MI->getOperand(0).isReg())
      continue;
    if (!MI->getOperand(1).isReg())
      continue;

    const unsigned Dst = MI->getOperand(0).getReg();
    const unsigned Src = MI->getOperand(1).getReg();

    if (!TargetRegisterInfo::isVirtualRegister(Dst))
      continue;
    if (!TargetRegisterInfo::isVirtualRegister(Src))
      continue;
    if (MRI.getRegClass(Dst) != MRI.getRegClass(Src))
      continue;

    for (auto UI = MRI.use_begin(Dst); UI != MRI.use_end(); ++UI) {
      MachineOperand *MO = &*UI;
      MO->setReg(Src);
      Changed = true;
    }

    MI->eraseFromParent();
  }

  return Changed;
}

/// Here we find our candidates. What makes an interesting candidate?
/// An candidate for a canonicalization tree root is normally any kind of
/// instruction that causes side effects such as a store to memory or a copy to
/// a physical register or a return instruction. We use these as an expression
/// tree root that we walk inorder to build a canonical walk which should result
/// in canoncal vreg renaming.
static std::vector<MachineInstr *> populateCandidates(MachineBasicBlock *MBB) {
  std::vector<MachineInstr *> Candidates;
  MachineRegisterInfo &MRI = MBB->getParent()->getRegInfo();

  for (auto II = MBB->begin(), IE = MBB->end(); II != IE; ++II) {
    MachineInstr *MI = &*II;

    bool DoesMISideEffect = false;

    if (MI->getNumOperands() > 0 && MI->getOperand(0).isReg()) {
      const unsigned Dst = MI->getOperand(0).getReg();
      DoesMISideEffect |= !TargetRegisterInfo::isVirtualRegister(Dst);

      for (auto UI = MRI.use_begin(Dst); UI != MRI.use_end(); ++UI) {
        if (DoesMISideEffect)
          break;
        DoesMISideEffect |= (UI->getParent()->getParent() != MI->getParent());
      }
    }

    if (!MI->mayStore() && !MI->isBranch() && !DoesMISideEffect)
      continue;

    LLVM_DEBUG(dbgs() << "Found Candidate:  "; MI->dump(););
    Candidates.push_back(MI);
  }

  return Candidates;
}

static void doCandidateWalk(std::vector<TypedVReg> &VRegs,
                            std::queue<TypedVReg> &RegQueue,
                            std::vector<MachineInstr *> &VisitedMIs,
                            const MachineBasicBlock *MBB) {

  const MachineFunction &MF = *MBB->getParent();
  const MachineRegisterInfo &MRI = MF.getRegInfo();

  while (!RegQueue.empty()) {

    auto TReg = RegQueue.front();
    RegQueue.pop();

    if (TReg.isFrameIndex()) {
      LLVM_DEBUG(dbgs() << "Popping frame index.\n";);
      VRegs.push_back(TypedVReg(RSE_FrameIndex));
      continue;
    }

    assert(TReg.isReg() && "Expected vreg or physreg.");
    unsigned Reg = TReg.getReg();

    if (TargetRegisterInfo::isVirtualRegister(Reg)) {
      LLVM_DEBUG({
        dbgs() << "Popping vreg ";
        MRI.def_begin(Reg)->dump();
        dbgs() << "\n";
      });

      if (!llvm::any_of(VRegs, [&](const TypedVReg &TR) {
            return TR.isReg() && TR.getReg() == Reg;
          })) {
        VRegs.push_back(TypedVReg(Reg));
      }
    } else {
      LLVM_DEBUG(dbgs() << "Popping physreg.\n";);
      VRegs.push_back(TypedVReg(Reg));
      continue;
    }

    for (auto RI = MRI.def_begin(Reg), RE = MRI.def_end(); RI != RE; ++RI) {
      MachineInstr *Def = RI->getParent();

      if (Def->getParent() != MBB)
        continue;

      if (llvm::any_of(VisitedMIs,
                       [&](const MachineInstr *VMI) { return Def == VMI; })) {
        break;
      }

      LLVM_DEBUG({
        dbgs() << "\n========================\n";
        dbgs() << "Visited MI: ";
        Def->dump();
        dbgs() << "BB Name: " << Def->getParent()->getName() << "\n";
        dbgs() << "\n========================\n";
      });
      VisitedMIs.push_back(Def);
      for (unsigned I = 1, E = Def->getNumOperands(); I != E; ++I) {

        MachineOperand &MO = Def->getOperand(I);
        if (MO.isFI()) {
          LLVM_DEBUG(dbgs() << "Pushing frame index.\n";);
          RegQueue.push(TypedVReg(RSE_FrameIndex));
        }

        if (!MO.isReg())
          continue;
        RegQueue.push(TypedVReg(MO.getReg()));
      }
    }
  }
}

namespace {
class NamedVRegCursor {
  MachineRegisterInfo &MRI;
  unsigned virtualVRegNumber;

public:
  NamedVRegCursor(MachineRegisterInfo &MRI) : MRI(MRI) {
    unsigned VRegGapIndex = 0;
    const unsigned VR_GAP = (++VRegGapIndex * 1000);

    unsigned I = MRI.createIncompleteVirtualRegister();
    const unsigned E = (((I + VR_GAP) / VR_GAP) + 1) * VR_GAP;

    virtualVRegNumber = E;
  }

  void SkipVRegs() {
    unsigned VRegGapIndex = 1;
    const unsigned VR_GAP = (++VRegGapIndex * 1000);

    unsigned I = virtualVRegNumber;
    const unsigned E = (((I + VR_GAP) / VR_GAP) + 1) * VR_GAP;

    virtualVRegNumber = E;
  }

  unsigned getVirtualVReg() const { return virtualVRegNumber; }

  unsigned incrementVirtualVReg(unsigned incr = 1) {
    virtualVRegNumber += incr;
    return virtualVRegNumber;
  }

  unsigned createVirtualRegister(const TargetRegisterClass *RC) {
    std::string S;
    raw_string_ostream OS(S);
    OS << "namedVReg" << (virtualVRegNumber & ~0x80000000);
    OS.flush();
    virtualVRegNumber++;

    return MRI.createVirtualRegister(RC, OS.str());
  }
};
} // namespace

static std::map<unsigned, unsigned>
GetVRegRenameMap(const std::vector<TypedVReg> &VRegs,
                 const std::vector<unsigned> &renamedInOtherBB,
                 MachineRegisterInfo &MRI, NamedVRegCursor &NVC) {
  std::map<unsigned, unsigned> VRegRenameMap;
  bool FirstCandidate = true;

  for (auto &vreg : VRegs) {
    if (vreg.isFrameIndex()) {
      // We skip one vreg for any frame index because there is a good chance
      // (especially when comparing SelectionDAG to GlobalISel generated MIR)
      // that in the other file we are just getting an incoming vreg that comes
      // from a copy from a frame index. So it's safe to skip by one.
      unsigned LastRenameReg = NVC.incrementVirtualVReg();
      (void)LastRenameReg;
      LLVM_DEBUG(dbgs() << "Skipping rename for FI " << LastRenameReg << "\n";);
      continue;
    } else if (vreg.isCandidate()) {

      // After the first candidate, for every subsequent candidate, we skip mod
      // 10 registers so that the candidates are more likely to start at the
      // same vreg number making it more likely that the canonical walk from the
      // candidate insruction. We don't need to skip from the first candidate of
      // the BasicBlock because we already skip ahead several vregs for each BB.
      unsigned LastRenameReg = NVC.getVirtualVReg();
      if (FirstCandidate)
        NVC.incrementVirtualVReg(LastRenameReg % 10);
      FirstCandidate = false;
      continue;
    } else if (!TargetRegisterInfo::isVirtualRegister(vreg.getReg())) {
      unsigned LastRenameReg = NVC.incrementVirtualVReg();
      (void)LastRenameReg;
      LLVM_DEBUG({
        dbgs() << "Skipping rename for Phys Reg " << LastRenameReg << "\n";
      });
      continue;
    }

    auto Reg = vreg.getReg();
    if (llvm::find(renamedInOtherBB, Reg) != renamedInOtherBB.end()) {
      LLVM_DEBUG(dbgs() << "Vreg " << Reg
                        << " already renamed in other BB.\n";);
      continue;
    }

    auto Rename = NVC.createVirtualRegister(MRI.getRegClass(Reg));

    if (VRegRenameMap.find(Reg) == VRegRenameMap.end()) {
      LLVM_DEBUG(dbgs() << "Mapping vreg ";);
      if (MRI.reg_begin(Reg) != MRI.reg_end()) {
        LLVM_DEBUG(auto foo = &*MRI.reg_begin(Reg); foo->dump(););
      } else {
        LLVM_DEBUG(dbgs() << Reg;);
      }
      LLVM_DEBUG(dbgs() << " to ";);
      if (MRI.reg_begin(Rename) != MRI.reg_end()) {
        LLVM_DEBUG(auto foo = &*MRI.reg_begin(Rename); foo->dump(););
      } else {
        LLVM_DEBUG(dbgs() << Rename;);
      }
      LLVM_DEBUG(dbgs() << "\n";);

      VRegRenameMap.insert(std::pair<unsigned, unsigned>(Reg, Rename));
    }
  }

  return VRegRenameMap;
}

static bool doVRegRenaming(std::vector<unsigned> &RenamedInOtherBB,
                           const std::map<unsigned, unsigned> &VRegRenameMap,
                           MachineRegisterInfo &MRI) {
  bool Changed = false;
  for (auto I = VRegRenameMap.begin(), E = VRegRenameMap.end(); I != E; ++I) {

    auto VReg = I->first;
    auto Rename = I->second;

    RenamedInOtherBB.push_back(Rename);

    std::vector<MachineOperand *> RenameMOs;
    for (auto &MO : MRI.reg_operands(VReg)) {
      RenameMOs.push_back(&MO);
    }

    for (auto *MO : RenameMOs) {
      Changed = true;
      MO->setReg(Rename);

      if (!MO->isDef())
        MO->setIsKill(false);
    }
  }

  return Changed;
}

static bool doDefKillClear(MachineBasicBlock *MBB) {
  bool Changed = false;

  for (auto &MI : *MBB) {
    for (auto &MO : MI.operands()) {
      if (!MO.isReg())
        continue;
      if (!MO.isDef() && MO.isKill()) {
        Changed = true;
        MO.setIsKill(false);
      }

      if (MO.isDef() && MO.isDead()) {
        Changed = true;
        MO.setIsDead(false);
      }
    }
  }

  return Changed;
}

static bool runOnBasicBlock(MachineBasicBlock *MBB,
                            std::vector<StringRef> &bbNames,
                            std::vector<unsigned> &renamedInOtherBB,
                            unsigned &basicBlockNum, unsigned &VRegGapIndex,
                            NamedVRegCursor &NVC) {

  if (CanonicalizeBasicBlockNumber != ~0U) {
    if (CanonicalizeBasicBlockNumber != basicBlockNum++)
      return false;
    LLVM_DEBUG(dbgs() << "\n Canonicalizing BasicBlock " << MBB->getName()
                      << "\n";);
  }

  if (llvm::find(bbNames, MBB->getName()) != bbNames.end()) {
    LLVM_DEBUG({
      dbgs() << "Found potentially duplicate BasicBlocks: " << MBB->getName()
             << "\n";
    });
    return false;
  }

  LLVM_DEBUG({
    dbgs() << "\n\n  NEW BASIC BLOCK: " << MBB->getName() << "  \n\n";
    dbgs() << "\n\n================================================\n\n";
  });

  bool Changed = false;
  MachineFunction &MF = *MBB->getParent();
  MachineRegisterInfo &MRI = MF.getRegInfo();

  bbNames.push_back(MBB->getName());
  LLVM_DEBUG(dbgs() << "\n\n NEW BASIC BLOCK: " << MBB->getName() << "\n\n";);

  LLVM_DEBUG(dbgs() << "MBB Before Canonical Copy Propagation:\n";
             MBB->dump(););
  Changed |= propagateLocalCopies(MBB);
  LLVM_DEBUG(dbgs() << "MBB After Canonical Copy Propagation:\n"; MBB->dump(););

  LLVM_DEBUG(dbgs() << "MBB Before Scheduling:\n"; MBB->dump(););
  unsigned IdempotentInstCount = 0;
  Changed |= rescheduleCanonically(IdempotentInstCount, MBB);
  LLVM_DEBUG(dbgs() << "MBB After Scheduling:\n"; MBB->dump(););

  std::vector<MachineInstr *> Candidates = populateCandidates(MBB);
  std::vector<MachineInstr *> VisitedMIs;
  std::copy(Candidates.begin(), Candidates.end(),
            std::back_inserter(VisitedMIs));

  std::vector<TypedVReg> VRegs;
  for (auto candidate : Candidates) {
    VRegs.push_back(TypedVReg(RSE_NewCandidate));

    std::queue<TypedVReg> RegQueue;

    // Here we walk the vreg operands of a non-root node along our walk.
    // The root nodes are the original candidates (stores normally).
    // These are normally not the root nodes (except for the case of copies to
    // physical registers).
    for (unsigned i = 1; i < candidate->getNumOperands(); i++) {
      if (candidate->mayStore() || candidate->isBranch())
        break;

      MachineOperand &MO = candidate->getOperand(i);
      if (!(MO.isReg() && TargetRegisterInfo::isVirtualRegister(MO.getReg())))
        continue;

      LLVM_DEBUG(dbgs() << "Enqueue register"; MO.dump(); dbgs() << "\n";);
      RegQueue.push(TypedVReg(MO.getReg()));
    }

    // Here we walk the root candidates. We start from the 0th operand because
    // the root is normally a store to a vreg.
    for (unsigned i = 0; i < candidate->getNumOperands(); i++) {

      if (!candidate->mayStore() && !candidate->isBranch())
        break;

      MachineOperand &MO = candidate->getOperand(i);

      // TODO: Do we want to only add vregs here?
      if (!MO.isReg() && !MO.isFI())
        continue;

      LLVM_DEBUG(dbgs() << "Enqueue Reg/FI"; MO.dump(); dbgs() << "\n";);

      RegQueue.push(MO.isReg() ? TypedVReg(MO.getReg())
                               : TypedVReg(RSE_FrameIndex));
    }

    doCandidateWalk(VRegs, RegQueue, VisitedMIs, MBB);
  }

  // If we have populated no vregs to rename then bail.
  // The rest of this function does the vreg remaping.
  if (VRegs.size() == 0)
    return Changed;

  auto VRegRenameMap = GetVRegRenameMap(VRegs, renamedInOtherBB, MRI, NVC);
  Changed |= doVRegRenaming(renamedInOtherBB, VRegRenameMap, MRI);

  // Here we renumber the def vregs for the idempotent instructions from the top
  // of the MachineBasicBlock so that they are named in the order that we sorted
  // them alphabetically. Eventually we wont need SkipVRegs because we will use
  // named vregs instead.
  NVC.SkipVRegs();

  auto MII = MBB->begin();
  for (unsigned i = 0; i < IdempotentInstCount && MII != MBB->end(); ++i) {
    MachineInstr &MI = *MII++;
    Changed = true;
    unsigned vRegToRename = MI.getOperand(0).getReg();
    auto Rename = NVC.createVirtualRegister(MRI.getRegClass(vRegToRename));

    std::vector<MachineOperand *> RenameMOs;
    for (auto &MO : MRI.reg_operands(vRegToRename)) {
      RenameMOs.push_back(&MO);
    }

    for (auto *MO : RenameMOs) {
      MO->setReg(Rename);
    }
  }

  Changed |= doDefKillClear(MBB);

  LLVM_DEBUG(dbgs() << "Updated MachineBasicBlock:\n"; MBB->dump();
             dbgs() << "\n";);
  LLVM_DEBUG(
      dbgs() << "\n\n================================================\n\n");
  return Changed;
}

bool MIRCanonicalizer::runOnMachineFunction(MachineFunction &MF) {

  static unsigned functionNum = 0;
  if (CanonicalizeFunctionNumber != ~0U) {
    if (CanonicalizeFunctionNumber != functionNum++)
      return false;
    LLVM_DEBUG(dbgs() << "\n Canonicalizing Function " << MF.getName()
                      << "\n";);
  }

  // we need a valid vreg to create a vreg type for skipping all those
  // stray vreg numbers so reach alignment/canonical vreg values.
  std::vector<MachineBasicBlock *> RPOList = GetRPOList(MF);

  LLVM_DEBUG(
      dbgs() << "\n\n  NEW MACHINE FUNCTION: " << MF.getName() << "  \n\n";
      dbgs() << "\n\n================================================\n\n";
      dbgs() << "Total Basic Blocks: " << RPOList.size() << "\n";
      for (auto MBB
           : RPOList) { dbgs() << MBB->getName() << "\n"; } dbgs()
      << "\n\n================================================\n\n";);

  std::vector<StringRef> BBNames;
  std::vector<unsigned> RenamedInOtherBB;

  unsigned GapIdx = 0;
  unsigned BBNum = 0;

  bool Changed = false;

  MachineRegisterInfo &MRI = MF.getRegInfo();
  NamedVRegCursor NVC(MRI);
  for (auto MBB : RPOList)
    Changed |=
        runOnBasicBlock(MBB, BBNames, RenamedInOtherBB, BBNum, GapIdx, NVC);

  return Changed;
}