llvm.org GIT mirror llvm / e7df36e lib / Transforms / Utils / LoopUnrollPeel.cpp
e7df36e

Tree @e7df36e (Download .tar.gz)

LoopUnrollPeel.cpp @e7df36eraw · 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
//===-- UnrollLoopPeel.cpp - Loop peeling utilities -----------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// 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/Statistic.h"
#include "llvm/Analysis/LoopIterator.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar.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 <algorithm>

using namespace llvm;

#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."));

// 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 = UINT_MAX;

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

  // 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 we want to peel off.
void llvm::computePeelCount(Loop *L, unsigned LoopSize,
                            TargetTransformInfo::UnrollingPreferences &UP,
                            unsigned &TripCount) {
  assert(LoopSize > 0 && "Zero loop size is not allowed!");
  UP.PeelCount = 0;
  if (!canPeel(L))
    return;

  // Only try to peel innermost loops.
  if (!L->empty())
    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.
    unsigned DesiredPeelCount = 0;
    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);
    }
    if (DesiredPeelCount > 0) {
      // 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::min(DesiredPeelCount, MaxPeelCount);
      // Consider max peel count limitation.
      assert(DesiredPeelCount > 0 && "Wrong loop size estimation?");
      DEBUG(dbgs() << "Peel " << DesiredPeelCount << " iteration(s) to turn"
                   << " some Phis into invariants.\n");
      UP.PeelCount = DesiredPeelCount;
      return;
    }
  }

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

  // If the user provided a peel count, use that.
  bool UserPeelCount = UnrollForcePeelCount.getNumOccurrences() > 0;
  if (UserPeelCount) {
    DEBUG(dbgs() << "Force-peeling first " << UnrollForcePeelCount
                 << " iterations.\n");
    UP.PeelCount = UnrollForcePeelCount;
    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 (UP.AllowPeeling && L->getHeader()->getParent()->getEntryCount()) {
    Optional<unsigned> PeelCount = getLoopEstimatedTripCount(L);
    if (!PeelCount)
      return;

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

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

  return;
}

/// \brief 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. 
/// Our goal is to make sure that:
/// a) The total weight of all the copies of the loop body is preserved.
/// b) The total weight of the loop exit is preserved.
/// c) The body weight is reasonably distributed between the peeled iterations.
///
/// \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 IterNumber The serial number of the iteration that was just
/// peeled off.
/// \param AvgIters The average number of iterations we expect the loop to have.
/// \param[in,out] PeeledHeaderWeight The total number of dynamic loop
/// iterations that are unaccounted for. As an input, it represents the number
/// of times we expect to enter the header of the iteration currently being
/// peeled off. The output is the number of times we expect to enter the
/// header of the next iteration.
static void updateBranchWeights(BasicBlock *Header, BranchInst *LatchBR,
                                unsigned IterNumber, unsigned AvgIters,
                                uint64_t &PeeledHeaderWeight) {

  // FIXME: Pick a more realistic distribution.
  // Currently the proportion of weight we assign to the fall-through
  // side of the branch drops linearly with the iteration number, and we use
  // a 0.9 fudge factor to make the drop-off less sharp...
  if (PeeledHeaderWeight) {
    uint64_t FallThruWeight =
        PeeledHeaderWeight * ((float)(AvgIters - IterNumber) / AvgIters * 0.9);
    uint64_t ExitWeight = PeeledHeaderWeight - FallThruWeight;
    PeeledHeaderWeight -= ExitWeight;

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

/// \brief 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 Exit The exit block of the original loop.
/// \param[out] NewBlocks A list of the 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, BasicBlock *Exit,
                            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());
  unsigned HeaderIdx = (LatchBR->getSuccessor(0) == Header ? 0 : 1);
  LatchBR->setSuccessor(HeaderIdx, InsertBot);
  LatchBR->setSuccessor(1 - HeaderIdx, Exit);
  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 (BasicBlock::iterator I = Exit->begin(); isa<PHINode>(I); ++I) {
    PHINode *PHI = cast<PHINode>(I);
    Value *LatchVal = PHI->getIncomingValueForBlock(Latch);
    Instruction *LatchInst = dyn_cast<Instruction>(LatchVal);
    if (LatchInst && L->contains(LatchInst))
      LatchVal = VMap[LatchVal];
    PHI->addIncoming(LatchVal, cast<BasicBlock>(VMap[Latch]));
  }

  // 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;
}

/// \brief 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) {
  if (!canPeel(L))
    return false;

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

  BasicBlock *Header = L->getHeader();
  BasicBlock *PreHeader = L->getLoopPreheader();
  BasicBlock *Latch = L->getLoopLatch();
  BasicBlock *Exit = L->getUniqueExitBlock();

  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());
  unsigned HeaderIdx = (LatchBR->getSuccessor(0) == Header ? 0 : 1);

  uint64_t TrueWeight, FalseWeight;
  uint64_t ExitWeight = 0, CurHeaderWeight = 0;
  if (LatchBR->extractProfMetadata(TrueWeight, FalseWeight)) {
    ExitWeight = HeaderIdx ? TrueWeight : FalseWeight;
    // The # of times the loop body executes is the sum of the exit block
    // weight and the # of times the backedges are taken.
    CurHeaderWeight = TrueWeight + FalseWeight;
  }

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

    // Subtract the exit weight from the current header weight -- the exit
    // weight is exactly the weight of the previous iteration's header.
    // FIXME: due to the way the distribution is constructed, we need a
    // guard here to make sure we don't end up with non-positive weights.
    if (ExitWeight < CurHeaderWeight)
      CurHeaderWeight -= ExitWeight;
    else
      CurHeaderWeight = 1;

    cloneLoopBlocks(L, Iter, InsertTop, InsertBot, Exit,
                    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)
        DT->changeImmediateDominator(Exit, cast<BasicBlock>(LVMap[Latch]));
#ifndef NDEBUG
      if (VerifyDomInfo)
        DT->verifyDomTree();
#endif
    }

    updateBranchWeights(InsertBot, cast<BranchInst>(VMap[LatchBR]), Iter,
                        PeelCount, ExitWeight);

    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->setIncomingValue(PHI->getBasicBlockIndex(NewPreHeader), NewVal);
  }

  // Adjust the branch weights on the loop exit.
  if (ExitWeight) {
    // The backedge count is the difference of current header weight and
    // current loop exit weight. If the current header weight is smaller than
    // the current loop exit weight, we mark the loop backedge weight as 1.
    uint64_t BackEdgeWeight = 0;
    if (ExitWeight < CurHeaderWeight)
      BackEdgeWeight = CurHeaderWeight - ExitWeight;
    else
      BackEdgeWeight = 1;
    MDBuilder MDB(LatchBR->getContext());
    MDNode *WeightNode =
        HeaderIdx ? MDB.createBranchWeights(ExitWeight, BackEdgeWeight)
                  : MDB.createBranchWeights(BackEdgeWeight, ExitWeight);
    LatchBR->setMetadata(LLVMContext::MD_prof, WeightNode);
  }

  // If the loop is nested, we changed the parent loop, update SE.
  if (Loop *ParentLoop = L->getParentLoop()) {
    SE->forgetLoop(ParentLoop);

    // FIXME: Incrementally update loop-simplify
    simplifyLoop(ParentLoop, DT, LI, SE, AC, PreserveLCSSA);
  } else {
    // FIXME: Incrementally update loop-simplify
    simplifyLoop(L, DT, LI, SE, AC, PreserveLCSSA);
  }

  NumPeeled++;

  return true;
}