llvm.org GIT mirror llvm / 1a4e1d8 lib / Target / PowerPC / PPCCTRLoops.cpp
1a4e1d8

Tree @1a4e1d8 (Download .tar.gz)

PPCCTRLoops.cpp @1a4e1d8raw · 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
//===-- PPCCTRLoops.cpp - Identify and generate CTR loops -----------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass identifies loops where we can generate the PPC branch instructions
// that decrement and test the count register (CTR) (bdnz and friends).
//
// The pattern that defines the induction variable can changed depending on
// prior optimizations.  For example, the IndVarSimplify phase run by 'opt'
// normalizes induction variables, and the Loop Strength Reduction pass
// run by 'llc' may also make changes to the induction variable.
//
// Criteria for CTR loops:
//  - Countable loops (w/ ind. var for a trip count)
//  - Try inner-most loops first
//  - No nested CTR loops.
//  - No function calls in loops.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar.h"
#include "PPC.h"
#include "PPCTargetMachine.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/ScalarEvolutionExpander.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/ValueHandle.h"
#include "llvm/PassSupport.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/Local.h"
#include "llvm/Transforms/Utils/LoopUtils.h"

#ifndef NDEBUG
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#endif

using namespace llvm;

#define DEBUG_TYPE "ctrloops"

#ifndef NDEBUG
static cl::opt<int> CTRLoopLimit("ppc-max-ctrloop", cl::Hidden, cl::init(-1));
#endif

STATISTIC(NumCTRLoops, "Number of loops converted to CTR loops");

namespace llvm {
  void initializePPCCTRLoopsPass(PassRegistry&);
#ifndef NDEBUG
  void initializePPCCTRLoopsVerifyPass(PassRegistry&);
#endif
}

namespace {
  struct PPCCTRLoops : public FunctionPass {

#ifndef NDEBUG
    static int Counter;
#endif

  public:
    static char ID;

    PPCCTRLoops() : FunctionPass(ID), TM(nullptr) {
      initializePPCCTRLoopsPass(*PassRegistry::getPassRegistry());
    }
    PPCCTRLoops(PPCTargetMachine &TM) : FunctionPass(ID), TM(&TM) {
      initializePPCCTRLoopsPass(*PassRegistry::getPassRegistry());
    }

    bool runOnFunction(Function &F) override;

    void getAnalysisUsage(AnalysisUsage &AU) const override {
      AU.addRequired<LoopInfoWrapperPass>();
      AU.addPreserved<LoopInfoWrapperPass>();
      AU.addRequired<DominatorTreeWrapperPass>();
      AU.addPreserved<DominatorTreeWrapperPass>();
      AU.addRequired<ScalarEvolutionWrapperPass>();
    }

  private:
    bool mightUseCTR(const Triple &TT, BasicBlock *BB);
    bool convertToCTRLoop(Loop *L);

  private:
    PPCTargetMachine *TM;
    LoopInfo *LI;
    ScalarEvolution *SE;
    const DataLayout *DL;
    DominatorTree *DT;
    const TargetLibraryInfo *LibInfo;
    bool PreserveLCSSA;
  };

  char PPCCTRLoops::ID = 0;
#ifndef NDEBUG
  int PPCCTRLoops::Counter = 0;
#endif

#ifndef NDEBUG
  struct PPCCTRLoopsVerify : public MachineFunctionPass {
  public:
    static char ID;

    PPCCTRLoopsVerify() : MachineFunctionPass(ID) {
      initializePPCCTRLoopsVerifyPass(*PassRegistry::getPassRegistry());
    }

    void getAnalysisUsage(AnalysisUsage &AU) const override {
      AU.addRequired<MachineDominatorTree>();
      MachineFunctionPass::getAnalysisUsage(AU);
    }

    bool runOnMachineFunction(MachineFunction &MF) override;

  private:
    MachineDominatorTree *MDT;
  };

  char PPCCTRLoopsVerify::ID = 0;
#endif // NDEBUG
} // end anonymous namespace

INITIALIZE_PASS_BEGIN(PPCCTRLoops, "ppc-ctr-loops", "PowerPC CTR Loops",
                      false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
INITIALIZE_PASS_END(PPCCTRLoops, "ppc-ctr-loops", "PowerPC CTR Loops",
                    false, false)

FunctionPass *llvm::createPPCCTRLoops(PPCTargetMachine &TM) {
  return new PPCCTRLoops(TM);
}

#ifndef NDEBUG
INITIALIZE_PASS_BEGIN(PPCCTRLoopsVerify, "ppc-ctr-loops-verify",
                      "PowerPC CTR Loops Verify", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
INITIALIZE_PASS_END(PPCCTRLoopsVerify, "ppc-ctr-loops-verify",
                    "PowerPC CTR Loops Verify", false, false)

FunctionPass *llvm::createPPCCTRLoopsVerify() {
  return new PPCCTRLoopsVerify();
}
#endif // NDEBUG

bool PPCCTRLoops::runOnFunction(Function &F) {
  if (skipFunction(F))
    return false;

  LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
  SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
  DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
  DL = &F.getParent()->getDataLayout();
  auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
  LibInfo = TLIP ? &TLIP->getTLI() : nullptr;
  PreserveLCSSA = mustPreserveAnalysisID(LCSSAID);

  bool MadeChange = false;

  for (LoopInfo::iterator I = LI->begin(), E = LI->end();
       I != E; ++I) {
    Loop *L = *I;
    if (!L->getParentLoop())
      MadeChange |= convertToCTRLoop(L);
  }

  return MadeChange;
}

static bool isLargeIntegerTy(bool Is32Bit, Type *Ty) {
  if (IntegerType *ITy = dyn_cast<IntegerType>(Ty))
    return ITy->getBitWidth() > (Is32Bit ? 32U : 64U);

  return false;
}

// Determining the address of a TLS variable results in a function call in
// certain TLS models.
static bool memAddrUsesCTR(const PPCTargetMachine *TM,
                           const Value *MemAddr) {
  const auto *GV = dyn_cast<GlobalValue>(MemAddr);
  if (!GV) {
    // Recurse to check for constants that refer to TLS global variables.
    if (const auto *CV = dyn_cast<Constant>(MemAddr))
      for (const auto &CO : CV->operands())
        if (memAddrUsesCTR(TM, CO))
          return true;

    return false;
  }

  if (!GV->isThreadLocal())
    return false;
  if (!TM)
    return true;
  TLSModel::Model Model = TM->getTLSModel(GV);
  return Model == TLSModel::GeneralDynamic || Model == TLSModel::LocalDynamic;
}

bool PPCCTRLoops::mightUseCTR(const Triple &TT, BasicBlock *BB) {
  for (BasicBlock::iterator J = BB->begin(), JE = BB->end();
       J != JE; ++J) {
    if (CallInst *CI = dyn_cast<CallInst>(J)) {
      if (InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue())) {
        // Inline ASM is okay, unless it clobbers the ctr register.
        InlineAsm::ConstraintInfoVector CIV = IA->ParseConstraints();
        for (unsigned i = 0, ie = CIV.size(); i < ie; ++i) {
          InlineAsm::ConstraintInfo &C = CIV[i];
          if (C.Type != InlineAsm::isInput)
            for (unsigned j = 0, je = C.Codes.size(); j < je; ++j)
              if (StringRef(C.Codes[j]).equals_lower("{ctr}"))
                return true;
        }

        continue;
      }

      if (!TM)
        return true;
      const TargetLowering *TLI =
          TM->getSubtargetImpl(*BB->getParent())->getTargetLowering();

      if (Function *F = CI->getCalledFunction()) {
        // Most intrinsics don't become function calls, but some might.
        // sin, cos, exp and log are always calls.
        unsigned Opcode = 0;
        if (F->getIntrinsicID() != Intrinsic::not_intrinsic) {
          switch (F->getIntrinsicID()) {
          default: continue;
          // If we have a call to ppc_is_decremented_ctr_nonzero, or ppc_mtctr
          // we're definitely using CTR.
          case Intrinsic::ppc_is_decremented_ctr_nonzero:
          case Intrinsic::ppc_mtctr:
            return true;

// VisualStudio defines setjmp as _setjmp
#if defined(_MSC_VER) && defined(setjmp) && \
                       !defined(setjmp_undefined_for_msvc)
#  pragma push_macro("setjmp")
#  undef setjmp
#  define setjmp_undefined_for_msvc
#endif

          case Intrinsic::setjmp:

#if defined(_MSC_VER) && defined(setjmp_undefined_for_msvc)
 // let's return it to _setjmp state
#  pragma pop_macro("setjmp")
#  undef setjmp_undefined_for_msvc
#endif

          case Intrinsic::longjmp:

          // Exclude eh_sjlj_setjmp; we don't need to exclude eh_sjlj_longjmp
          // because, although it does clobber the counter register, the
          // control can't then return to inside the loop unless there is also
          // an eh_sjlj_setjmp.
          case Intrinsic::eh_sjlj_setjmp:

          case Intrinsic::memcpy:
          case Intrinsic::memmove:
          case Intrinsic::memset:
          case Intrinsic::powi:
          case Intrinsic::log:
          case Intrinsic::log2:
          case Intrinsic::log10:
          case Intrinsic::exp:
          case Intrinsic::exp2:
          case Intrinsic::pow:
          case Intrinsic::sin:
          case Intrinsic::cos:
            return true;
          case Intrinsic::copysign:
            if (CI->getArgOperand(0)->getType()->getScalarType()->
                isPPC_FP128Ty())
              return true;
            else
              continue; // ISD::FCOPYSIGN is never a library call.
          case Intrinsic::sqrt:      Opcode = ISD::FSQRT;      break;
          case Intrinsic::floor:     Opcode = ISD::FFLOOR;     break;
          case Intrinsic::ceil:      Opcode = ISD::FCEIL;      break;
          case Intrinsic::trunc:     Opcode = ISD::FTRUNC;     break;
          case Intrinsic::rint:      Opcode = ISD::FRINT;      break;
          case Intrinsic::nearbyint: Opcode = ISD::FNEARBYINT; break;
          case Intrinsic::round:     Opcode = ISD::FROUND;     break;
          case Intrinsic::minnum:    Opcode = ISD::FMINNUM;    break;
          case Intrinsic::maxnum:    Opcode = ISD::FMAXNUM;    break;
          }
        }

        // PowerPC does not use [US]DIVREM or other library calls for
        // operations on regular types which are not otherwise library calls
        // (i.e. soft float or atomics). If adapting for targets that do,
        // additional care is required here.

        LibFunc::Func Func;
        if (!F->hasLocalLinkage() && F->hasName() && LibInfo &&
            LibInfo->getLibFunc(F->getName(), Func) &&
            LibInfo->hasOptimizedCodeGen(Func)) {
          // Non-read-only functions are never treated as intrinsics.
          if (!CI->onlyReadsMemory())
            return true;

          // Conversion happens only for FP calls.
          if (!CI->getArgOperand(0)->getType()->isFloatingPointTy())
            return true;

          switch (Func) {
          default: return true;
          case LibFunc::copysign:
          case LibFunc::copysignf:
            continue; // ISD::FCOPYSIGN is never a library call.
          case LibFunc::copysignl:
            return true;
          case LibFunc::fabs:
          case LibFunc::fabsf:
          case LibFunc::fabsl:
            continue; // ISD::FABS is never a library call.
          case LibFunc::sqrt:
          case LibFunc::sqrtf:
          case LibFunc::sqrtl:
            Opcode = ISD::FSQRT; break;
          case LibFunc::floor:
          case LibFunc::floorf:
          case LibFunc::floorl:
            Opcode = ISD::FFLOOR; break;
          case LibFunc::nearbyint:
          case LibFunc::nearbyintf:
          case LibFunc::nearbyintl:
            Opcode = ISD::FNEARBYINT; break;
          case LibFunc::ceil:
          case LibFunc::ceilf:
          case LibFunc::ceill:
            Opcode = ISD::FCEIL; break;
          case LibFunc::rint:
          case LibFunc::rintf:
          case LibFunc::rintl:
            Opcode = ISD::FRINT; break;
          case LibFunc::round:
          case LibFunc::roundf:
          case LibFunc::roundl:
            Opcode = ISD::FROUND; break;
          case LibFunc::trunc:
          case LibFunc::truncf:
          case LibFunc::truncl:
            Opcode = ISD::FTRUNC; break;
          case LibFunc::fmin:
          case LibFunc::fminf:
          case LibFunc::fminl:
            Opcode = ISD::FMINNUM; break;
          case LibFunc::fmax:
          case LibFunc::fmaxf:
          case LibFunc::fmaxl:
            Opcode = ISD::FMAXNUM; break;
          }
        }

        if (Opcode) {
          auto &DL = CI->getModule()->getDataLayout();
          MVT VTy = TLI->getSimpleValueType(DL, CI->getArgOperand(0)->getType(),
                                            true);
          if (VTy == MVT::Other)
            return true;

          if (TLI->isOperationLegalOrCustom(Opcode, VTy))
            continue;
          else if (VTy.isVector() &&
                   TLI->isOperationLegalOrCustom(Opcode, VTy.getScalarType()))
            continue;

          return true;
        }
      }

      return true;
    } else if (isa<BinaryOperator>(J) &&
               J->getType()->getScalarType()->isPPC_FP128Ty()) {
      // Most operations on ppc_f128 values become calls.
      return true;
    } else if (isa<UIToFPInst>(J) || isa<SIToFPInst>(J) ||
               isa<FPToUIInst>(J) || isa<FPToSIInst>(J)) {
      CastInst *CI = cast<CastInst>(J);
      if (CI->getSrcTy()->getScalarType()->isPPC_FP128Ty() ||
          CI->getDestTy()->getScalarType()->isPPC_FP128Ty() ||
          isLargeIntegerTy(TT.isArch32Bit(), CI->getSrcTy()->getScalarType()) ||
          isLargeIntegerTy(TT.isArch32Bit(), CI->getDestTy()->getScalarType()))
        return true;
    } else if (isLargeIntegerTy(TT.isArch32Bit(),
                                J->getType()->getScalarType()) &&
               (J->getOpcode() == Instruction::UDiv ||
                J->getOpcode() == Instruction::SDiv ||
                J->getOpcode() == Instruction::URem ||
                J->getOpcode() == Instruction::SRem)) {
      return true;
    } else if (TT.isArch32Bit() &&
               isLargeIntegerTy(false, J->getType()->getScalarType()) &&
               (J->getOpcode() == Instruction::Shl ||
                J->getOpcode() == Instruction::AShr ||
                J->getOpcode() == Instruction::LShr)) {
      // Only on PPC32, for 128-bit integers (specifically not 64-bit
      // integers), these might be runtime calls.
      return true;
    } else if (isa<IndirectBrInst>(J) || isa<InvokeInst>(J)) {
      // On PowerPC, indirect jumps use the counter register.
      return true;
    } else if (SwitchInst *SI = dyn_cast<SwitchInst>(J)) {
      if (!TM)
        return true;
      const TargetLowering *TLI =
          TM->getSubtargetImpl(*BB->getParent())->getTargetLowering();

      if (SI->getNumCases() + 1 >= (unsigned)TLI->getMinimumJumpTableEntries())
        return true;
    }

    if (TM->getSubtargetImpl(*BB->getParent())->getTargetLowering()->useSoftFloat()) {
      switch(J->getOpcode()) {
      case Instruction::FAdd:
      case Instruction::FSub:
      case Instruction::FMul:
      case Instruction::FDiv:
      case Instruction::FRem:
      case Instruction::FPTrunc:
      case Instruction::FPExt:
      case Instruction::FPToUI:
      case Instruction::FPToSI:
      case Instruction::UIToFP:
      case Instruction::SIToFP:
      case Instruction::FCmp:
        return true;
      }
    }

    for (Value *Operand : J->operands())
      if (memAddrUsesCTR(TM, Operand))
        return true;
  }

  return false;
}

bool PPCCTRLoops::convertToCTRLoop(Loop *L) {
  bool MadeChange = false;

  const Triple TT =
      Triple(L->getHeader()->getParent()->getParent()->getTargetTriple());
  if (!TT.isArch32Bit() && !TT.isArch64Bit())
    return MadeChange; // Unknown arch. type.

  // Process nested loops first.
  for (Loop::iterator I = L->begin(), E = L->end(); I != E; ++I) {
    MadeChange |= convertToCTRLoop(*I);
    DEBUG(dbgs() << "Nested loop converted\n");
  }

  // If a nested loop has been converted, then we can't convert this loop.
  if (MadeChange)
    return MadeChange;

#ifndef NDEBUG
  // Stop trying after reaching the limit (if any).
  int Limit = CTRLoopLimit;
  if (Limit >= 0) {
    if (Counter >= CTRLoopLimit)
      return false;
    Counter++;
  }
#endif

  // We don't want to spill/restore the counter register, and so we don't
  // want to use the counter register if the loop contains calls.
  for (Loop::block_iterator I = L->block_begin(), IE = L->block_end();
       I != IE; ++I)
    if (mightUseCTR(TT, *I))
      return MadeChange;

  SmallVector<BasicBlock*, 4> ExitingBlocks;
  L->getExitingBlocks(ExitingBlocks);

  BasicBlock *CountedExitBlock = nullptr;
  const SCEV *ExitCount = nullptr;
  BranchInst *CountedExitBranch = nullptr;
  for (SmallVectorImpl<BasicBlock *>::iterator I = ExitingBlocks.begin(),
       IE = ExitingBlocks.end(); I != IE; ++I) {
    const SCEV *EC = SE->getExitCount(L, *I);
    DEBUG(dbgs() << "Exit Count for " << *L << " from block " <<
                    (*I)->getName() << ": " << *EC << "\n");
    if (isa<SCEVCouldNotCompute>(EC))
      continue;
    if (const SCEVConstant *ConstEC = dyn_cast<SCEVConstant>(EC)) {
      if (ConstEC->getValue()->isZero())
        continue;
    } else if (!SE->isLoopInvariant(EC, L))
      continue;

    if (SE->getTypeSizeInBits(EC->getType()) > (TT.isArch64Bit() ? 64 : 32))
      continue;

    // We now have a loop-invariant count of loop iterations (which is not the
    // constant zero) for which we know that this loop will not exit via this
    // exisiting block.

    // We need to make sure that this block will run on every loop iteration.
    // For this to be true, we must dominate all blocks with backedges. Such
    // blocks are in-loop predecessors to the header block.
    bool NotAlways = false;
    for (pred_iterator PI = pred_begin(L->getHeader()),
         PIE = pred_end(L->getHeader()); PI != PIE; ++PI) {
      if (!L->contains(*PI))
        continue;

      if (!DT->dominates(*I, *PI)) {
        NotAlways = true;
        break;
      }
    }

    if (NotAlways)
      continue;

    // Make sure this blocks ends with a conditional branch.
    Instruction *TI = (*I)->getTerminator();
    if (!TI)
      continue;

    if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
      if (!BI->isConditional())
        continue;

      CountedExitBranch = BI;
    } else
      continue;

    // Note that this block may not be the loop latch block, even if the loop
    // has a latch block.
    CountedExitBlock = *I;
    ExitCount = EC;
    break;
  }

  if (!CountedExitBlock)
    return MadeChange;

  BasicBlock *Preheader = L->getLoopPreheader();

  // If we don't have a preheader, then insert one. If we already have a
  // preheader, then we can use it (except if the preheader contains a use of
  // the CTR register because some such uses might be reordered by the
  // selection DAG after the mtctr instruction).
  if (!Preheader || mightUseCTR(TT, Preheader))
    Preheader = InsertPreheaderForLoop(L, DT, LI, PreserveLCSSA);
  if (!Preheader)
    return MadeChange;

  DEBUG(dbgs() << "Preheader for exit count: " << Preheader->getName() << "\n");

  // Insert the count into the preheader and replace the condition used by the
  // selected branch.
  MadeChange = true;

  SCEVExpander SCEVE(*SE, Preheader->getModule()->getDataLayout(), "loopcnt");
  LLVMContext &C = SE->getContext();
  Type *CountType = TT.isArch64Bit() ? Type::getInt64Ty(C) :
                                       Type::getInt32Ty(C);
  if (!ExitCount->getType()->isPointerTy() &&
      ExitCount->getType() != CountType)
    ExitCount = SE->getZeroExtendExpr(ExitCount, CountType);
  ExitCount = SE->getAddExpr(ExitCount, SE->getOne(CountType));
  Value *ECValue =
      SCEVE.expandCodeFor(ExitCount, CountType, Preheader->getTerminator());

  IRBuilder<> CountBuilder(Preheader->getTerminator());
  Module *M = Preheader->getParent()->getParent();
  Value *MTCTRFunc = Intrinsic::getDeclaration(M, Intrinsic::ppc_mtctr,
                                               CountType);
  CountBuilder.CreateCall(MTCTRFunc, ECValue);

  IRBuilder<> CondBuilder(CountedExitBranch);
  Value *DecFunc =
    Intrinsic::getDeclaration(M, Intrinsic::ppc_is_decremented_ctr_nonzero);
  Value *NewCond = CondBuilder.CreateCall(DecFunc, {});
  Value *OldCond = CountedExitBranch->getCondition();
  CountedExitBranch->setCondition(NewCond);

  // The false branch must exit the loop.
  if (!L->contains(CountedExitBranch->getSuccessor(0)))
    CountedExitBranch->swapSuccessors();

  // The old condition may be dead now, and may have even created a dead PHI
  // (the original induction variable).
  RecursivelyDeleteTriviallyDeadInstructions(OldCond);
  DeleteDeadPHIs(CountedExitBlock);

  ++NumCTRLoops;
  return MadeChange;
}

#ifndef NDEBUG
static bool clobbersCTR(const MachineInstr *MI) {
  for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
    const MachineOperand &MO = MI->getOperand(i);
    if (MO.isReg()) {
      if (MO.isDef() && (MO.getReg() == PPC::CTR || MO.getReg() == PPC::CTR8))
        return true;
    } else if (MO.isRegMask()) {
      if (MO.clobbersPhysReg(PPC::CTR) || MO.clobbersPhysReg(PPC::CTR8))
        return true;
    }
  }

  return false;
}

static bool verifyCTRBranch(MachineBasicBlock *MBB,
                            MachineBasicBlock::iterator I) {
  MachineBasicBlock::iterator BI = I;
  SmallSet<MachineBasicBlock *, 16>   Visited;
  SmallVector<MachineBasicBlock *, 8> Preds;
  bool CheckPreds;

  if (I == MBB->begin()) {
    Visited.insert(MBB);
    goto queue_preds;
  } else
    --I;

check_block:
  Visited.insert(MBB);
  if (I == MBB->end())
    goto queue_preds;

  CheckPreds = true;
  for (MachineBasicBlock::iterator IE = MBB->begin();; --I) {
    unsigned Opc = I->getOpcode();
    if (Opc == PPC::MTCTRloop || Opc == PPC::MTCTR8loop) {
      CheckPreds = false;
      break;
    }

    if (I != BI && clobbersCTR(I)) {
      DEBUG(dbgs() << "BB#" << MBB->getNumber() << " (" <<
                      MBB->getFullName() << ") instruction " << *I <<
                      " clobbers CTR, invalidating " << "BB#" <<
                      BI->getParent()->getNumber() << " (" <<
                      BI->getParent()->getFullName() << ") instruction " <<
                      *BI << "\n");
      return false;
    }

    if (I == IE)
      break;
  }

  if (!CheckPreds && Preds.empty())
    return true;

  if (CheckPreds) {
queue_preds:
    if (MachineFunction::iterator(MBB) == MBB->getParent()->begin()) {
      DEBUG(dbgs() << "Unable to find a MTCTR instruction for BB#" <<
                      BI->getParent()->getNumber() << " (" <<
                      BI->getParent()->getFullName() << ") instruction " <<
                      *BI << "\n");
      return false;
    }

    for (MachineBasicBlock::pred_iterator PI = MBB->pred_begin(),
         PIE = MBB->pred_end(); PI != PIE; ++PI)
      Preds.push_back(*PI);
  }

  do {
    MBB = Preds.pop_back_val();
    if (!Visited.count(MBB)) {
      I = MBB->getLastNonDebugInstr();
      goto check_block;
    }
  } while (!Preds.empty());

  return true;
}

bool PPCCTRLoopsVerify::runOnMachineFunction(MachineFunction &MF) {
  MDT = &getAnalysis<MachineDominatorTree>();

  // Verify that all bdnz/bdz instructions are dominated by a loop mtctr before
  // any other instructions that might clobber the ctr register.
  for (MachineFunction::iterator I = MF.begin(), IE = MF.end();
       I != IE; ++I) {
    MachineBasicBlock *MBB = &*I;
    if (!MDT->isReachableFromEntry(MBB))
      continue;

    for (MachineBasicBlock::iterator MII = MBB->getFirstTerminator(),
      MIIE = MBB->end(); MII != MIIE; ++MII) {
      unsigned Opc = MII->getOpcode();
      if (Opc == PPC::BDNZ8 || Opc == PPC::BDNZ ||
          Opc == PPC::BDZ8  || Opc == PPC::BDZ)
        if (!verifyCTRBranch(MBB, MII))
          llvm_unreachable("Invalid PPC CTR loop!");
    }
  }

  return false;
}
#endif // NDEBUG