llvm.org GIT mirror llvm / master lib / Transforms / Utils / LoopUnrollPeel.cpp
master

Tree @master (Download .tar.gz)

LoopUnrollPeel.cpp @masterraw · 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
//===- UnrollLoopPeel.cpp - Loop peeling utilities ------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file implements some loop unrolling utilities for peeling loops
// with dynamically inferred (from PGO) trip counts. See LoopUnroll.cpp for
// unrolling loops with compile-time constant trip counts.
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopIterator.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Cloning.h"
#include "llvm/Transforms/Utils/LoopSimplify.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include "llvm/Transforms/Utils/UnrollLoop.h"
#include "llvm/Transforms/Utils/ValueMapper.h"
#include <algorithm>
#include <cassert>
#include <cstdint>
#include <limits>

using namespace llvm;
using namespace llvm::PatternMatch;

#define DEBUG_TYPE "loop-unroll"

STATISTIC(NumPeeled, "Number of loops peeled");

static cl::opt<unsigned> UnrollPeelMaxCount(
    "unroll-peel-max-count", cl::init(7), cl::Hidden,
    cl::desc("Max average trip count which will cause loop peeling."));

static cl::opt<unsigned> UnrollForcePeelCount(
    "unroll-force-peel-count", cl::init(0), cl::Hidden,
    cl::desc("Force a peel count regardless of profiling information."));

static cl::opt<bool> UnrollPeelMultiDeoptExit(
    "unroll-peel-multi-deopt-exit", cl::init(true), cl::Hidden,
    cl::desc("Allow peeling of loops with multiple deopt exits."));

static const char *PeeledCountMetaData = "llvm.loop.peeled.count";

// Designates that a Phi is estimated to become invariant after an "infinite"
// number of loop iterations (i.e. only may become an invariant if the loop is
// fully unrolled).
static const unsigned InfiniteIterationsToInvariance =
    std::numeric_limits<unsigned>::max();

// Check whether we are capable of peeling this loop.
bool llvm::canPeel(Loop *L) {
  // Make sure the loop is in simplified form
  if (!L->isLoopSimplifyForm())
    return false;

  if (UnrollPeelMultiDeoptExit) {
    SmallVector<BasicBlock *, 4> Exits;
    L->getUniqueNonLatchExitBlocks(Exits);

    if (!Exits.empty()) {
      // Latch's terminator is a conditional branch, Latch is exiting and
      // all non Latch exits ends up with deoptimize.
      const BasicBlock *Latch = L->getLoopLatch();
      const BranchInst *T = dyn_cast<BranchInst>(Latch->getTerminator());
      return T && T->isConditional() && L->isLoopExiting(Latch) &&
             all_of(Exits, [](const BasicBlock *BB) {
               return BB->getTerminatingDeoptimizeCall();
             });
    }
  }

  // Only peel loops that contain a single exit
  if (!L->getExitingBlock() || !L->getUniqueExitBlock())
    return false;

  // Don't try to peel loops where the latch is not the exiting block.
  // This can be an indication of two different things:
  // 1) The loop is not rotated.
  // 2) The loop contains irreducible control flow that involves the latch.
  if (L->getLoopLatch() != L->getExitingBlock())
    return false;

  return true;
}

// This function calculates the number of iterations after which the given Phi
// becomes an invariant. The pre-calculated values are memorized in the map. The
// function (shortcut is I) is calculated according to the following definition:
// Given %x = phi <Inputs from above the loop>, ..., [%y, %back.edge].
//   If %y is a loop invariant, then I(%x) = 1.
//   If %y is a Phi from the loop header, I(%x) = I(%y) + 1.
//   Otherwise, I(%x) is infinite.
// TODO: Actually if %y is an expression that depends only on Phi %z and some
//       loop invariants, we can estimate I(%x) = I(%z) + 1. The example
//       looks like:
//         %x = phi(0, %a),  <-- becomes invariant starting from 3rd iteration.
//         %y = phi(0, 5),
//         %a = %y + 1.
static unsigned calculateIterationsToInvariance(
    PHINode *Phi, Loop *L, BasicBlock *BackEdge,
    SmallDenseMap<PHINode *, unsigned> &IterationsToInvariance) {
  assert(Phi->getParent() == L->getHeader() &&
         "Non-loop Phi should not be checked for turning into invariant.");
  assert(BackEdge == L->getLoopLatch() && "Wrong latch?");
  // If we already know the answer, take it from the map.
  auto I = IterationsToInvariance.find(Phi);
  if (I != IterationsToInvariance.end())
    return I->second;

  // Otherwise we need to analyze the input from the back edge.
  Value *Input = Phi->getIncomingValueForBlock(BackEdge);
  // Place infinity to map to avoid infinite recursion for cycled Phis. Such
  // cycles can never stop on an invariant.
  IterationsToInvariance[Phi] = InfiniteIterationsToInvariance;
  unsigned ToInvariance = InfiniteIterationsToInvariance;

  if (L->isLoopInvariant(Input))
    ToInvariance = 1u;
  else if (PHINode *IncPhi = dyn_cast<PHINode>(Input)) {
    // Only consider Phis in header block.
    if (IncPhi->getParent() != L->getHeader())
      return InfiniteIterationsToInvariance;
    // If the input becomes an invariant after X iterations, then our Phi
    // becomes an invariant after X + 1 iterations.
    unsigned InputToInvariance = calculateIterationsToInvariance(
        IncPhi, L, BackEdge, IterationsToInvariance);
    if (InputToInvariance != InfiniteIterationsToInvariance)
      ToInvariance = InputToInvariance + 1u;
  }

  // If we found that this Phi lies in an invariant chain, update the map.
  if (ToInvariance != InfiniteIterationsToInvariance)
    IterationsToInvariance[Phi] = ToInvariance;
  return ToInvariance;
}

// Return the number of iterations to peel off that make conditions in the
// body true/false. For example, if we peel 2 iterations off the loop below,
// the condition i < 2 can be evaluated at compile time.
//  for (i = 0; i < n; i++)
//    if (i < 2)
//      ..
//    else
//      ..
//   }
static unsigned countToEliminateCompares(Loop &L, unsigned MaxPeelCount,
                                         ScalarEvolution &SE) {
  assert(L.isLoopSimplifyForm() && "Loop needs to be in loop simplify form");
  unsigned DesiredPeelCount = 0;

  for (auto *BB : L.blocks()) {
    auto *BI = dyn_cast<BranchInst>(BB->getTerminator());
    if (!BI || BI->isUnconditional())
      continue;

    // Ignore loop exit condition.
    if (L.getLoopLatch() == BB)
      continue;

    Value *Condition = BI->getCondition();
    Value *LeftVal, *RightVal;
    CmpInst::Predicate Pred;
    if (!match(Condition, m_ICmp(Pred, m_Value(LeftVal), m_Value(RightVal))))
      continue;

    const SCEV *LeftSCEV = SE.getSCEV(LeftVal);
    const SCEV *RightSCEV = SE.getSCEV(RightVal);

    // Do not consider predicates that are known to be true or false
    // independently of the loop iteration.
    if (SE.isKnownPredicate(Pred, LeftSCEV, RightSCEV) ||
        SE.isKnownPredicate(ICmpInst::getInversePredicate(Pred), LeftSCEV,
                            RightSCEV))
      continue;

    // Check if we have a condition with one AddRec and one non AddRec
    // expression. Normalize LeftSCEV to be the AddRec.
    if (!isa<SCEVAddRecExpr>(LeftSCEV)) {
      if (isa<SCEVAddRecExpr>(RightSCEV)) {
        std::swap(LeftSCEV, RightSCEV);
        Pred = ICmpInst::getSwappedPredicate(Pred);
      } else
        continue;
    }

    const SCEVAddRecExpr *LeftAR = cast<SCEVAddRecExpr>(LeftSCEV);

    // Avoid huge SCEV computations in the loop below, make sure we only
    // consider AddRecs of the loop we are trying to peel and avoid
    // non-monotonic predicates, as we will not be able to simplify the loop
    // body.
    // FIXME: For the non-monotonic predicates ICMP_EQ and ICMP_NE we can
    //        simplify the loop, if we peel 1 additional iteration, if there
    //        is no wrapping.
    bool Increasing;
    if (!LeftAR->isAffine() || LeftAR->getLoop() != &L ||
        !SE.isMonotonicPredicate(LeftAR, Pred, Increasing))
      continue;
    (void)Increasing;

    // Check if extending the current DesiredPeelCount lets us evaluate Pred
    // or !Pred in the loop body statically.
    unsigned NewPeelCount = DesiredPeelCount;

    const SCEV *IterVal = LeftAR->evaluateAtIteration(
        SE.getConstant(LeftSCEV->getType(), NewPeelCount), SE);

    // If the original condition is not known, get the negated predicate
    // (which holds on the else branch) and check if it is known. This allows
    // us to peel of iterations that make the original condition false.
    if (!SE.isKnownPredicate(Pred, IterVal, RightSCEV))
      Pred = ICmpInst::getInversePredicate(Pred);

    const SCEV *Step = LeftAR->getStepRecurrence(SE);
    while (NewPeelCount < MaxPeelCount &&
           SE.isKnownPredicate(Pred, IterVal, RightSCEV)) {
      IterVal = SE.getAddExpr(IterVal, Step);
      NewPeelCount++;
    }

    // Only peel the loop if the monotonic predicate !Pred becomes known in the
    // first iteration of the loop body after peeling.
    if (NewPeelCount > DesiredPeelCount &&
        SE.isKnownPredicate(ICmpInst::getInversePredicate(Pred), IterVal,
                            RightSCEV))
      DesiredPeelCount = NewPeelCount;
  }

  return DesiredPeelCount;
}

// Return the number of iterations we want to peel off.
void llvm::computePeelCount(Loop *L, unsigned LoopSize,
                            TargetTransformInfo::UnrollingPreferences &UP,
                            unsigned &TripCount, ScalarEvolution &SE) {
  assert(LoopSize > 0 && "Zero loop size is not allowed!");
  // Save the UP.PeelCount value set by the target in
  // TTI.getUnrollingPreferences or by the flag -unroll-peel-count.
  unsigned TargetPeelCount = UP.PeelCount;
  UP.PeelCount = 0;
  if (!canPeel(L))
    return;

  // Only try to peel innermost loops.
  if (!L->empty())
    return;

  // If the user provided a peel count, use that.
  bool UserPeelCount = UnrollForcePeelCount.getNumOccurrences() > 0;
  if (UserPeelCount) {
    LLVM_DEBUG(dbgs() << "Force-peeling first " << UnrollForcePeelCount
                      << " iterations.\n");
    UP.PeelCount = UnrollForcePeelCount;
    UP.PeelProfiledIterations = true;
    return;
  }

  // Skip peeling if it's disabled.
  if (!UP.AllowPeeling)
    return;

  unsigned AlreadyPeeled = 0;
  if (auto Peeled = getOptionalIntLoopAttribute(L, PeeledCountMetaData))
    AlreadyPeeled = *Peeled;
  // Stop if we already peeled off the maximum number of iterations.
  if (AlreadyPeeled >= UnrollPeelMaxCount)
    return;

  // Here we try to get rid of Phis which become invariants after 1, 2, ..., N
  // iterations of the loop. For this we compute the number for iterations after
  // which every Phi is guaranteed to become an invariant, and try to peel the
  // maximum number of iterations among these values, thus turning all those
  // Phis into invariants.
  // First, check that we can peel at least one iteration.
  if (2 * LoopSize <= UP.Threshold && UnrollPeelMaxCount > 0) {
    // Store the pre-calculated values here.
    SmallDenseMap<PHINode *, unsigned> IterationsToInvariance;
    // Now go through all Phis to calculate their the number of iterations they
    // need to become invariants.
    // Start the max computation with the UP.PeelCount value set by the target
    // in TTI.getUnrollingPreferences or by the flag -unroll-peel-count.
    unsigned DesiredPeelCount = TargetPeelCount;
    BasicBlock *BackEdge = L->getLoopLatch();
    assert(BackEdge && "Loop is not in simplified form?");
    for (auto BI = L->getHeader()->begin(); isa<PHINode>(&*BI); ++BI) {
      PHINode *Phi = cast<PHINode>(&*BI);
      unsigned ToInvariance = calculateIterationsToInvariance(
          Phi, L, BackEdge, IterationsToInvariance);
      if (ToInvariance != InfiniteIterationsToInvariance)
        DesiredPeelCount = std::max(DesiredPeelCount, ToInvariance);
    }

    // Pay respect to limitations implied by loop size and the max peel count.
    unsigned MaxPeelCount = UnrollPeelMaxCount;
    MaxPeelCount = std::min(MaxPeelCount, UP.Threshold / LoopSize - 1);

    DesiredPeelCount = std::max(DesiredPeelCount,
                                countToEliminateCompares(*L, MaxPeelCount, SE));

    if (DesiredPeelCount > 0) {
      DesiredPeelCount = std::min(DesiredPeelCount, MaxPeelCount);
      // Consider max peel count limitation.
      assert(DesiredPeelCount > 0 && "Wrong loop size estimation?");
      if (DesiredPeelCount + AlreadyPeeled <= UnrollPeelMaxCount) {
        LLVM_DEBUG(dbgs() << "Peel " << DesiredPeelCount
                          << " iteration(s) to turn"
                          << " some Phis into invariants.\n");
        UP.PeelCount = DesiredPeelCount;
        UP.PeelProfiledIterations = false;
        return;
      }
    }
  }

  // Bail if we know the statically calculated trip count.
  // In this case we rather prefer partial unrolling.
  if (TripCount)
    return;

  // Do not apply profile base peeling if it is disabled.
  if (!UP.PeelProfiledIterations)
    return;
  // If we don't know the trip count, but have reason to believe the average
  // trip count is low, peeling should be beneficial, since we will usually
  // hit the peeled section.
  // We only do this in the presence of profile information, since otherwise
  // our estimates of the trip count are not reliable enough.
  if (L->getHeader()->getParent()->hasProfileData()) {
    Optional<unsigned> PeelCount = getLoopEstimatedTripCount(L);
    if (!PeelCount)
      return;

    LLVM_DEBUG(dbgs() << "Profile-based estimated trip count is " << *PeelCount
                      << "\n");

    if (*PeelCount) {
      if ((*PeelCount + AlreadyPeeled <= UnrollPeelMaxCount) &&
          (LoopSize * (*PeelCount + 1) <= UP.Threshold)) {
        LLVM_DEBUG(dbgs() << "Peeling first " << *PeelCount
                          << " iterations.\n");
        UP.PeelCount = *PeelCount;
        return;
      }
      LLVM_DEBUG(dbgs() << "Requested peel count: " << *PeelCount << "\n");
      LLVM_DEBUG(dbgs() << "Already peel count: " << AlreadyPeeled << "\n");
      LLVM_DEBUG(dbgs() << "Max peel count: " << UnrollPeelMaxCount << "\n");
      LLVM_DEBUG(dbgs() << "Peel cost: " << LoopSize * (*PeelCount + 1)
                        << "\n");
      LLVM_DEBUG(dbgs() << "Max peel cost: " << UP.Threshold << "\n");
    }
  }
}

/// Update the branch weights of the latch of a peeled-off loop
/// iteration.
/// This sets the branch weights for the latch of the recently peeled off loop
/// iteration correctly.
/// Let F is a weight of the edge from latch to header.
/// Let E is a weight of the edge from latch to exit.
/// F/(F+E) is a probability to go to loop and E/(F+E) is a probability to
/// go to exit.
/// Then, Estimated TripCount = F / E.
/// For I-th (counting from 0) peeled off iteration we set the the weights for
/// the peeled latch as (TC - I, 1). It gives us reasonable distribution,
/// The probability to go to exit 1/(TC-I) increases. At the same time
/// the estimated trip count of remaining loop reduces by I.
/// To avoid dealing with division rounding we can just multiple both part
/// of weights to E and use weight as (F - I * E, E).
///
/// \param Header The copy of the header block that belongs to next iteration.
/// \param LatchBR The copy of the latch branch that belongs to this iteration.
/// \param[in,out] FallThroughWeight The weight of the edge from latch to
/// header before peeling (in) and after peeled off one iteration (out).
static void updateBranchWeights(BasicBlock *Header, BranchInst *LatchBR,
                                uint64_t ExitWeight,
                                uint64_t &FallThroughWeight) {
  // FallThroughWeight is 0 means that there is no branch weights on original
  // latch block or estimated trip count is zero.
  if (!FallThroughWeight)
    return;

  unsigned HeaderIdx = (LatchBR->getSuccessor(0) == Header ? 0 : 1);
  MDBuilder MDB(LatchBR->getContext());
  MDNode *WeightNode =
      HeaderIdx ? MDB.createBranchWeights(ExitWeight, FallThroughWeight)
                : MDB.createBranchWeights(FallThroughWeight, ExitWeight);
  LatchBR->setMetadata(LLVMContext::MD_prof, WeightNode);
  FallThroughWeight =
      FallThroughWeight > ExitWeight ? FallThroughWeight - ExitWeight : 1;
}

/// Initialize the weights.
///
/// \param Header The header block.
/// \param LatchBR The latch branch.
/// \param[out] ExitWeight The weight of the edge from Latch to Exit.
/// \param[out] FallThroughWeight The weight of the edge from Latch to Header.
static void initBranchWeights(BasicBlock *Header, BranchInst *LatchBR,
                              uint64_t &ExitWeight,
                              uint64_t &FallThroughWeight) {
  uint64_t TrueWeight, FalseWeight;
  if (!LatchBR->extractProfMetadata(TrueWeight, FalseWeight))
    return;
  unsigned HeaderIdx = LatchBR->getSuccessor(0) == Header ? 0 : 1;
  ExitWeight = HeaderIdx ? TrueWeight : FalseWeight;
  FallThroughWeight = HeaderIdx ? FalseWeight : TrueWeight;
}

/// Update the weights of original Latch block after peeling off all iterations.
///
/// \param Header The header block.
/// \param LatchBR The latch branch.
/// \param ExitWeight The weight of the edge from Latch to Exit.
/// \param FallThroughWeight The weight of the edge from Latch to Header.
static void fixupBranchWeights(BasicBlock *Header, BranchInst *LatchBR,
                               uint64_t ExitWeight,
                               uint64_t FallThroughWeight) {
  // FallThroughWeight is 0 means that there is no branch weights on original
  // latch block or estimated trip count is zero.
  if (!FallThroughWeight)
    return;

  // Sets the branch weights on the loop exit.
  MDBuilder MDB(LatchBR->getContext());
  unsigned HeaderIdx = LatchBR->getSuccessor(0) == Header ? 0 : 1;
  MDNode *WeightNode =
      HeaderIdx ? MDB.createBranchWeights(ExitWeight, FallThroughWeight)
                : MDB.createBranchWeights(FallThroughWeight, ExitWeight);
  LatchBR->setMetadata(LLVMContext::MD_prof, WeightNode);
}

/// Clones the body of the loop L, putting it between \p InsertTop and \p
/// InsertBot.
/// \param IterNumber The serial number of the iteration currently being
/// peeled off.
/// \param ExitEdges The exit edges of the original loop.
/// \param[out] NewBlocks A list of the blocks in the newly created clone
/// \param[out] VMap The value map between the loop and the new clone.
/// \param LoopBlocks A helper for DFS-traversal of the loop.
/// \param LVMap A value-map that maps instructions from the original loop to
/// instructions in the last peeled-off iteration.
static void cloneLoopBlocks(
    Loop *L, unsigned IterNumber, BasicBlock *InsertTop, BasicBlock *InsertBot,
    SmallVectorImpl<std::pair<BasicBlock *, BasicBlock *> > &ExitEdges,
    SmallVectorImpl<BasicBlock *> &NewBlocks, LoopBlocksDFS &LoopBlocks,
    ValueToValueMapTy &VMap, ValueToValueMapTy &LVMap, DominatorTree *DT,
    LoopInfo *LI) {
  BasicBlock *Header = L->getHeader();
  BasicBlock *Latch = L->getLoopLatch();
  BasicBlock *PreHeader = L->getLoopPreheader();

  Function *F = Header->getParent();
  LoopBlocksDFS::RPOIterator BlockBegin = LoopBlocks.beginRPO();
  LoopBlocksDFS::RPOIterator BlockEnd = LoopBlocks.endRPO();
  Loop *ParentLoop = L->getParentLoop();

  // For each block in the original loop, create a new copy,
  // and update the value map with the newly created values.
  for (LoopBlocksDFS::RPOIterator BB = BlockBegin; BB != BlockEnd; ++BB) {
    BasicBlock *NewBB = CloneBasicBlock(*BB, VMap, ".peel", F);
    NewBlocks.push_back(NewBB);

    if (ParentLoop)
      ParentLoop->addBasicBlockToLoop(NewBB, *LI);

    VMap[*BB] = NewBB;

    // If dominator tree is available, insert nodes to represent cloned blocks.
    if (DT) {
      if (Header == *BB)
        DT->addNewBlock(NewBB, InsertTop);
      else {
        DomTreeNode *IDom = DT->getNode(*BB)->getIDom();
        // VMap must contain entry for IDom, as the iteration order is RPO.
        DT->addNewBlock(NewBB, cast<BasicBlock>(VMap[IDom->getBlock()]));
      }
    }
  }

  // Hook-up the control flow for the newly inserted blocks.
  // The new header is hooked up directly to the "top", which is either
  // the original loop preheader (for the first iteration) or the previous
  // iteration's exiting block (for every other iteration)
  InsertTop->getTerminator()->setSuccessor(0, cast<BasicBlock>(VMap[Header]));

  // Similarly, for the latch:
  // The original exiting edge is still hooked up to the loop exit.
  // The backedge now goes to the "bottom", which is either the loop's real
  // header (for the last peeled iteration) or the copied header of the next
  // iteration (for every other iteration)
  BasicBlock *NewLatch = cast<BasicBlock>(VMap[Latch]);
  BranchInst *LatchBR = cast<BranchInst>(NewLatch->getTerminator());
  for (unsigned idx = 0, e = LatchBR->getNumSuccessors(); idx < e; ++idx)
    if (LatchBR->getSuccessor(idx) == Header) {
      LatchBR->setSuccessor(idx, InsertBot);
      break;
    }
  if (DT)
    DT->changeImmediateDominator(InsertBot, NewLatch);

  // The new copy of the loop body starts with a bunch of PHI nodes
  // that pick an incoming value from either the preheader, or the previous
  // loop iteration. Since this copy is no longer part of the loop, we
  // resolve this statically:
  // For the first iteration, we use the value from the preheader directly.
  // For any other iteration, we replace the phi with the value generated by
  // the immediately preceding clone of the loop body (which represents
  // the previous iteration).
  for (BasicBlock::iterator I = Header->begin(); isa<PHINode>(I); ++I) {
    PHINode *NewPHI = cast<PHINode>(VMap[&*I]);
    if (IterNumber == 0) {
      VMap[&*I] = NewPHI->getIncomingValueForBlock(PreHeader);
    } else {
      Value *LatchVal = NewPHI->getIncomingValueForBlock(Latch);
      Instruction *LatchInst = dyn_cast<Instruction>(LatchVal);
      if (LatchInst && L->contains(LatchInst))
        VMap[&*I] = LVMap[LatchInst];
      else
        VMap[&*I] = LatchVal;
    }
    cast<BasicBlock>(VMap[Header])->getInstList().erase(NewPHI);
  }

  // Fix up the outgoing values - we need to add a value for the iteration
  // we've just created. Note that this must happen *after* the incoming
  // values are adjusted, since the value going out of the latch may also be
  // a value coming into the header.
  for (auto Edge : ExitEdges)
    for (PHINode &PHI : Edge.second->phis()) {
      Value *LatchVal = PHI.getIncomingValueForBlock(Edge.first);
      Instruction *LatchInst = dyn_cast<Instruction>(LatchVal);
      if (LatchInst && L->contains(LatchInst))
        LatchVal = VMap[LatchVal];
      PHI.addIncoming(LatchVal, cast<BasicBlock>(VMap[Edge.first]));
    }

  // LastValueMap is updated with the values for the current loop
  // which are used the next time this function is called.
  for (const auto &KV : VMap)
    LVMap[KV.first] = KV.second;
}

/// Peel off the first \p PeelCount iterations of loop \p L.
///
/// Note that this does not peel them off as a single straight-line block.
/// Rather, each iteration is peeled off separately, and needs to check the
/// exit condition.
/// For loops that dynamically execute \p PeelCount iterations or less
/// this provides a benefit, since the peeled off iterations, which account
/// for the bulk of dynamic execution, can be further simplified by scalar
/// optimizations.
bool llvm::peelLoop(Loop *L, unsigned PeelCount, LoopInfo *LI,
                    ScalarEvolution *SE, DominatorTree *DT,
                    AssumptionCache *AC, bool PreserveLCSSA) {
  assert(PeelCount > 0 && "Attempt to peel out zero iterations?");
  assert(canPeel(L) && "Attempt to peel a loop which is not peelable?");

  LoopBlocksDFS LoopBlocks(L);
  LoopBlocks.perform(LI);

  BasicBlock *Header = L->getHeader();
  BasicBlock *PreHeader = L->getLoopPreheader();
  BasicBlock *Latch = L->getLoopLatch();
  SmallVector<std::pair<BasicBlock *, BasicBlock *>, 4> ExitEdges;
  L->getExitEdges(ExitEdges);

  DenseMap<BasicBlock *, BasicBlock *> ExitIDom;
  if (DT) {
    // We'd like to determine the idom of exit block after peeling one
    // iteration.
    // Let Exit is exit block.
    // Let ExitingSet - is a set of predecessors of Exit block. They are exiting
    // blocks.
    // Let Latch' and ExitingSet' are copies after a peeling.
    // We'd like to find an idom'(Exit) - idom of Exit after peeling.
    // It is an evident that idom'(Exit) will be the nearest common dominator
    // of ExitingSet and ExitingSet'.
    // idom(Exit) is a nearest common dominator of ExitingSet.
    // idom(Exit)' is a nearest common dominator of ExitingSet'.
    // Taking into account that we have a single Latch, Latch' will dominate
    // Header and idom(Exit).
    // So the idom'(Exit) is nearest common dominator of idom(Exit)' and Latch'.
    // All these basic blocks are in the same loop, so what we find is
    // (nearest common dominator of idom(Exit) and Latch)'.
    // In the loop below we remember nearest common dominator of idom(Exit) and
    // Latch to update idom of Exit later.
    assert(L->hasDedicatedExits() && "No dedicated exits?");
    for (auto Edge : ExitEdges) {
      if (ExitIDom.count(Edge.second))
        continue;
      BasicBlock *BB = DT->findNearestCommonDominator(
          DT->getNode(Edge.second)->getIDom()->getBlock(), Latch);
      assert(L->contains(BB) && "IDom is not in a loop");
      ExitIDom[Edge.second] = BB;
    }
  }

  Function *F = Header->getParent();

  // Set up all the necessary basic blocks. It is convenient to split the
  // preheader into 3 parts - two blocks to anchor the peeled copy of the loop
  // body, and a new preheader for the "real" loop.

  // Peeling the first iteration transforms.
  //
  // PreHeader:
  // ...
  // Header:
  //   LoopBody
  //   If (cond) goto Header
  // Exit:
  //
  // into
  //
  // InsertTop:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot:
  // NewPreHeader:
  // ...
  // Header:
  //  LoopBody
  //  If (cond) goto Header
  // Exit:
  //
  // Each following iteration will split the current bottom anchor in two,
  // and put the new copy of the loop body between these two blocks. That is,
  // after peeling another iteration from the example above, we'll split
  // InsertBot, and get:
  //
  // InsertTop:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot:
  //   LoopBody
  //   If (!cond) goto Exit
  // InsertBot.next:
  // NewPreHeader:
  // ...
  // Header:
  //  LoopBody
  //  If (cond) goto Header
  // Exit:

  BasicBlock *InsertTop = SplitEdge(PreHeader, Header, DT, LI);
  BasicBlock *InsertBot =
      SplitBlock(InsertTop, InsertTop->getTerminator(), DT, LI);
  BasicBlock *NewPreHeader =
      SplitBlock(InsertBot, InsertBot->getTerminator(), DT, LI);

  InsertTop->setName(Header->getName() + ".peel.begin");
  InsertBot->setName(Header->getName() + ".peel.next");
  NewPreHeader->setName(PreHeader->getName() + ".peel.newph");

  ValueToValueMapTy LVMap;

  // If we have branch weight information, we'll want to update it for the
  // newly created branches.
  BranchInst *LatchBR =
      cast<BranchInst>(cast<BasicBlock>(Latch)->getTerminator());
  uint64_t ExitWeight = 0, FallThroughWeight = 0;
  initBranchWeights(Header, LatchBR, ExitWeight, FallThroughWeight);

  // For each peeled-off iteration, make a copy of the loop.
  for (unsigned Iter = 0; Iter < PeelCount; ++Iter) {
    SmallVector<BasicBlock *, 8> NewBlocks;
    ValueToValueMapTy VMap;

    cloneLoopBlocks(L, Iter, InsertTop, InsertBot, ExitEdges, NewBlocks,
                    LoopBlocks, VMap, LVMap, DT, LI);

    // Remap to use values from the current iteration instead of the
    // previous one.
    remapInstructionsInBlocks(NewBlocks, VMap);

    if (DT) {
      // Latches of the cloned loops dominate over the loop exit, so idom of the
      // latter is the first cloned loop body, as original PreHeader dominates
      // the original loop body.
      if (Iter == 0)
        for (auto Exit : ExitIDom)
          DT->changeImmediateDominator(Exit.first,
                                       cast<BasicBlock>(LVMap[Exit.second]));
#ifdef EXPENSIVE_CHECKS
      assert(DT->verify(DominatorTree::VerificationLevel::Fast));
#endif
    }

    auto *LatchBRCopy = cast<BranchInst>(VMap[LatchBR]);
    updateBranchWeights(InsertBot, LatchBRCopy, ExitWeight, FallThroughWeight);
    // Remove Loop metadata from the latch branch instruction
    // because it is not the Loop's latch branch anymore.
    LatchBRCopy->setMetadata(LLVMContext::MD_loop, nullptr);

    InsertTop = InsertBot;
    InsertBot = SplitBlock(InsertBot, InsertBot->getTerminator(), DT, LI);
    InsertBot->setName(Header->getName() + ".peel.next");

    F->getBasicBlockList().splice(InsertTop->getIterator(),
                                  F->getBasicBlockList(),
                                  NewBlocks[0]->getIterator(), F->end());
  }

  // Now adjust the phi nodes in the loop header to get their initial values
  // from the last peeled-off iteration instead of the preheader.
  for (BasicBlock::iterator I = Header->begin(); isa<PHINode>(I); ++I) {
    PHINode *PHI = cast<PHINode>(I);
    Value *NewVal = PHI->getIncomingValueForBlock(Latch);
    Instruction *LatchInst = dyn_cast<Instruction>(NewVal);
    if (LatchInst && L->contains(LatchInst))
      NewVal = LVMap[LatchInst];

    PHI->setIncomingValueForBlock(NewPreHeader, NewVal);
  }

  fixupBranchWeights(Header, LatchBR, ExitWeight, FallThroughWeight);

  // Update Metadata for count of peeled off iterations.
  unsigned AlreadyPeeled = 0;
  if (auto Peeled = getOptionalIntLoopAttribute(L, PeeledCountMetaData))
    AlreadyPeeled = *Peeled;
  addStringMetadataToLoop(L, PeeledCountMetaData, AlreadyPeeled + PeelCount);

  if (Loop *ParentLoop = L->getParentLoop())
    L = ParentLoop;

  // We modified the loop, update SE.
  SE->forgetTopmostLoop(L);

  // Finally DomtTree must be correct.
  assert(DT->verify(DominatorTree::VerificationLevel::Fast));

  // FIXME: Incrementally update loop-simplify
  simplifyLoop(L, DT, LI, SE, AC, nullptr, PreserveLCSSA);

  NumPeeled++;

  return true;
}