llvm.org GIT mirror llvm / 0392724 lib / Target / AMDGPU / GCNSchedStrategy.cpp
0392724

Tree @0392724 (Download .tar.gz)

GCNSchedStrategy.cpp @0392724raw · 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
//===-- GCNSchedStrategy.cpp - GCN Scheduler Strategy ---------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
/// \file
/// This contains a MachineSchedStrategy implementation for maximizing wave
/// occupancy on GCN hardware.
//===----------------------------------------------------------------------===//

#include "GCNSchedStrategy.h"
#include "AMDGPUSubtarget.h"
#include "SIInstrInfo.h"
#include "SIMachineFunctionInfo.h"
#include "SIRegisterInfo.h"
#include "llvm/CodeGen/RegisterClassInfo.h"
#include "llvm/Support/MathExtras.h"

#define DEBUG_TYPE "machine-scheduler"

using namespace llvm;

GCNMaxOccupancySchedStrategy::GCNMaxOccupancySchedStrategy(
    const MachineSchedContext *C) :
    GenericScheduler(C), TargetOccupancy(0), MF(nullptr) { }

void GCNMaxOccupancySchedStrategy::initialize(ScheduleDAGMI *DAG) {
  GenericScheduler::initialize(DAG);

  const SIRegisterInfo *SRI = static_cast<const SIRegisterInfo*>(TRI);

  MF = &DAG->MF;

  const GCNSubtarget &ST = MF->getSubtarget<GCNSubtarget>();

  // FIXME: This is also necessary, because some passes that run after
  // scheduling and before regalloc increase register pressure.
  const int ErrorMargin = 3;

  SGPRExcessLimit = Context->RegClassInfo
    ->getNumAllocatableRegs(&AMDGPU::SGPR_32RegClass) - ErrorMargin;
  VGPRExcessLimit = Context->RegClassInfo
    ->getNumAllocatableRegs(&AMDGPU::VGPR_32RegClass) - ErrorMargin;
  if (TargetOccupancy) {
    SGPRCriticalLimit = ST.getMaxNumSGPRs(TargetOccupancy, true);
    VGPRCriticalLimit = ST.getMaxNumVGPRs(TargetOccupancy);
  } else {
    SGPRCriticalLimit = SRI->getRegPressureSetLimit(DAG->MF,
                                                    SRI->getSGPRPressureSet());
    VGPRCriticalLimit = SRI->getRegPressureSetLimit(DAG->MF,
                                                    SRI->getVGPRPressureSet());
  }

  SGPRCriticalLimit -= ErrorMargin;
  VGPRCriticalLimit -= ErrorMargin;
}

void GCNMaxOccupancySchedStrategy::initCandidate(SchedCandidate &Cand, SUnit *SU,
                                     bool AtTop, const RegPressureTracker &RPTracker,
                                     const SIRegisterInfo *SRI,
                                     unsigned SGPRPressure,
                                     unsigned VGPRPressure) {

  Cand.SU = SU;
  Cand.AtTop = AtTop;

  // getDownwardPressure() and getUpwardPressure() make temporary changes to
  // the tracker, so we need to pass those function a non-const copy.
  RegPressureTracker &TempTracker = const_cast<RegPressureTracker&>(RPTracker);

  std::vector<unsigned> Pressure;
  std::vector<unsigned> MaxPressure;

  if (AtTop)
    TempTracker.getDownwardPressure(SU->getInstr(), Pressure, MaxPressure);
  else {
    // FIXME: I think for bottom up scheduling, the register pressure is cached
    // and can be retrieved by DAG->getPressureDif(SU).
    TempTracker.getUpwardPressure(SU->getInstr(), Pressure, MaxPressure);
  }

  unsigned NewSGPRPressure = Pressure[SRI->getSGPRPressureSet()];
  unsigned NewVGPRPressure = Pressure[SRI->getVGPRPressureSet()];

  // If two instructions increase the pressure of different register sets
  // by the same amount, the generic scheduler will prefer to schedule the
  // instruction that increases the set with the least amount of registers,
  // which in our case would be SGPRs.  This is rarely what we want, so
  // when we report excess/critical register pressure, we do it either
  // only for VGPRs or only for SGPRs.

  // FIXME: Better heuristics to determine whether to prefer SGPRs or VGPRs.
  const unsigned MaxVGPRPressureInc = 16;
  bool ShouldTrackVGPRs = VGPRPressure + MaxVGPRPressureInc >= VGPRExcessLimit;
  bool ShouldTrackSGPRs = !ShouldTrackVGPRs && SGPRPressure >= SGPRExcessLimit;


  // FIXME: We have to enter REG-EXCESS before we reach the actual threshold
  // to increase the likelihood we don't go over the limits.  We should improve
  // the analysis to look through dependencies to find the path with the least
  // register pressure.

  // We only need to update the RPDelata for instructions that increase
  // register pressure.  Instructions that decrease or keep reg pressure
  // the same will be marked as RegExcess in tryCandidate() when they
  // are compared with instructions that increase the register pressure.
  if (ShouldTrackVGPRs && NewVGPRPressure >= VGPRExcessLimit) {
    Cand.RPDelta.Excess = PressureChange(SRI->getVGPRPressureSet());
    Cand.RPDelta.Excess.setUnitInc(NewVGPRPressure - VGPRExcessLimit);
  }

  if (ShouldTrackSGPRs && NewSGPRPressure >= SGPRExcessLimit) {
    Cand.RPDelta.Excess = PressureChange(SRI->getSGPRPressureSet());
    Cand.RPDelta.Excess.setUnitInc(NewSGPRPressure - SGPRExcessLimit);
  }

  // Register pressure is considered 'CRITICAL' if it is approaching a value
  // that would reduce the wave occupancy for the execution unit.  When
  // register pressure is 'CRITICAL', increading SGPR and VGPR pressure both
  // has the same cost, so we don't need to prefer one over the other.

  int SGPRDelta = NewSGPRPressure - SGPRCriticalLimit;
  int VGPRDelta = NewVGPRPressure - VGPRCriticalLimit;

  if (SGPRDelta >= 0 || VGPRDelta >= 0) {
    if (SGPRDelta > VGPRDelta) {
      Cand.RPDelta.CriticalMax = PressureChange(SRI->getSGPRPressureSet());
      Cand.RPDelta.CriticalMax.setUnitInc(SGPRDelta);
    } else {
      Cand.RPDelta.CriticalMax = PressureChange(SRI->getVGPRPressureSet());
      Cand.RPDelta.CriticalMax.setUnitInc(VGPRDelta);
    }
  }
}

// This function is mostly cut and pasted from
// GenericScheduler::pickNodeFromQueue()
void GCNMaxOccupancySchedStrategy::pickNodeFromQueue(SchedBoundary &Zone,
                                         const CandPolicy &ZonePolicy,
                                         const RegPressureTracker &RPTracker,
                                         SchedCandidate &Cand) {
  const SIRegisterInfo *SRI = static_cast<const SIRegisterInfo*>(TRI);
  ArrayRef<unsigned> Pressure = RPTracker.getRegSetPressureAtPos();
  unsigned SGPRPressure = Pressure[SRI->getSGPRPressureSet()];
  unsigned VGPRPressure = Pressure[SRI->getVGPRPressureSet()];
  ReadyQueue &Q = Zone.Available;
  for (SUnit *SU : Q) {

    SchedCandidate TryCand(ZonePolicy);
    initCandidate(TryCand, SU, Zone.isTop(), RPTracker, SRI,
                  SGPRPressure, VGPRPressure);
    // Pass SchedBoundary only when comparing nodes from the same boundary.
    SchedBoundary *ZoneArg = Cand.AtTop == TryCand.AtTop ? &Zone : nullptr;
    GenericScheduler::tryCandidate(Cand, TryCand, ZoneArg);
    if (TryCand.Reason != NoCand) {
      // Initialize resource delta if needed in case future heuristics query it.
      if (TryCand.ResDelta == SchedResourceDelta())
        TryCand.initResourceDelta(Zone.DAG, SchedModel);
      Cand.setBest(TryCand);
    }
  }
}

// This function is mostly cut and pasted from
// GenericScheduler::pickNodeBidirectional()
SUnit *GCNMaxOccupancySchedStrategy::pickNodeBidirectional(bool &IsTopNode) {
  // Schedule as far as possible in the direction of no choice. This is most
  // efficient, but also provides the best heuristics for CriticalPSets.
  if (SUnit *SU = Bot.pickOnlyChoice()) {
    IsTopNode = false;
    return SU;
  }
  if (SUnit *SU = Top.pickOnlyChoice()) {
    IsTopNode = true;
    return SU;
  }
  // Set the bottom-up policy based on the state of the current bottom zone and
  // the instructions outside the zone, including the top zone.
  CandPolicy BotPolicy;
  setPolicy(BotPolicy, /*IsPostRA=*/false, Bot, &Top);
  // Set the top-down policy based on the state of the current top zone and
  // the instructions outside the zone, including the bottom zone.
  CandPolicy TopPolicy;
  setPolicy(TopPolicy, /*IsPostRA=*/false, Top, &Bot);

  // See if BotCand is still valid (because we previously scheduled from Top).
  LLVM_DEBUG(dbgs() << "Picking from Bot:\n");
  if (!BotCand.isValid() || BotCand.SU->isScheduled ||
      BotCand.Policy != BotPolicy) {
    BotCand.reset(CandPolicy());
    pickNodeFromQueue(Bot, BotPolicy, DAG->getBotRPTracker(), BotCand);
    assert(BotCand.Reason != NoCand && "failed to find the first candidate");
  } else {
    LLVM_DEBUG(traceCandidate(BotCand));
  }

  // Check if the top Q has a better candidate.
  LLVM_DEBUG(dbgs() << "Picking from Top:\n");
  if (!TopCand.isValid() || TopCand.SU->isScheduled ||
      TopCand.Policy != TopPolicy) {
    TopCand.reset(CandPolicy());
    pickNodeFromQueue(Top, TopPolicy, DAG->getTopRPTracker(), TopCand);
    assert(TopCand.Reason != NoCand && "failed to find the first candidate");
  } else {
    LLVM_DEBUG(traceCandidate(TopCand));
  }

  // Pick best from BotCand and TopCand.
  LLVM_DEBUG(dbgs() << "Top Cand: "; traceCandidate(TopCand);
             dbgs() << "Bot Cand: "; traceCandidate(BotCand););
  SchedCandidate Cand;
  if (TopCand.Reason == BotCand.Reason) {
    Cand = BotCand;
    GenericSchedulerBase::CandReason TopReason = TopCand.Reason;
    TopCand.Reason = NoCand;
    GenericScheduler::tryCandidate(Cand, TopCand, nullptr);
    if (TopCand.Reason != NoCand) {
      Cand.setBest(TopCand);
    } else {
      TopCand.Reason = TopReason;
    }
  } else {
    if (TopCand.Reason == RegExcess && TopCand.RPDelta.Excess.getUnitInc() <= 0) {
      Cand = TopCand;
    } else if (BotCand.Reason == RegExcess && BotCand.RPDelta.Excess.getUnitInc() <= 0) {
      Cand = BotCand;
    } else if (TopCand.Reason == RegCritical && TopCand.RPDelta.CriticalMax.getUnitInc() <= 0) {
      Cand = TopCand;
    } else if (BotCand.Reason == RegCritical && BotCand.RPDelta.CriticalMax.getUnitInc() <= 0) {
      Cand = BotCand;
    } else {
      if (BotCand.Reason > TopCand.Reason) {
        Cand = TopCand;
      } else {
        Cand = BotCand;
      }
    }
  }
  LLVM_DEBUG(dbgs() << "Picking: "; traceCandidate(Cand););

  IsTopNode = Cand.AtTop;
  return Cand.SU;
}

// This function is mostly cut and pasted from
// GenericScheduler::pickNode()
SUnit *GCNMaxOccupancySchedStrategy::pickNode(bool &IsTopNode) {
  if (DAG->top() == DAG->bottom()) {
    assert(Top.Available.empty() && Top.Pending.empty() &&
           Bot.Available.empty() && Bot.Pending.empty() && "ReadyQ garbage");
    return nullptr;
  }
  SUnit *SU;
  do {
    if (RegionPolicy.OnlyTopDown) {
      SU = Top.pickOnlyChoice();
      if (!SU) {
        CandPolicy NoPolicy;
        TopCand.reset(NoPolicy);
        pickNodeFromQueue(Top, NoPolicy, DAG->getTopRPTracker(), TopCand);
        assert(TopCand.Reason != NoCand && "failed to find a candidate");
        SU = TopCand.SU;
      }
      IsTopNode = true;
    } else if (RegionPolicy.OnlyBottomUp) {
      SU = Bot.pickOnlyChoice();
      if (!SU) {
        CandPolicy NoPolicy;
        BotCand.reset(NoPolicy);
        pickNodeFromQueue(Bot, NoPolicy, DAG->getBotRPTracker(), BotCand);
        assert(BotCand.Reason != NoCand && "failed to find a candidate");
        SU = BotCand.SU;
      }
      IsTopNode = false;
    } else {
      SU = pickNodeBidirectional(IsTopNode);
    }
  } while (SU->isScheduled);

  if (SU->isTopReady())
    Top.removeReady(SU);
  if (SU->isBottomReady())
    Bot.removeReady(SU);

  LLVM_DEBUG(dbgs() << "Scheduling SU(" << SU->NodeNum << ") "
                    << *SU->getInstr());
  return SU;
}

GCNScheduleDAGMILive::GCNScheduleDAGMILive(MachineSchedContext *C,
                        std::unique_ptr<MachineSchedStrategy> S) :
  ScheduleDAGMILive(C, std::move(S)),
  ST(MF.getSubtarget<GCNSubtarget>()),
  MFI(*MF.getInfo<SIMachineFunctionInfo>()),
  StartingOccupancy(MFI.getOccupancy()),
  MinOccupancy(StartingOccupancy), Stage(0), RegionIdx(0) {

  LLVM_DEBUG(dbgs() << "Starting occupancy is " << StartingOccupancy << ".\n");
}

void GCNScheduleDAGMILive::schedule() {
  if (Stage == 0) {
    // Just record regions at the first pass.
    Regions.push_back(std::make_pair(RegionBegin, RegionEnd));
    return;
  }

  std::vector<MachineInstr*> Unsched;
  Unsched.reserve(NumRegionInstrs);
  for (auto &I : *this) {
    Unsched.push_back(&I);
  }

  GCNRegPressure PressureBefore;
  if (LIS) {
    PressureBefore = Pressure[RegionIdx];

    LLVM_DEBUG(dbgs() << "Pressure before scheduling:\nRegion live-ins:";
               GCNRPTracker::printLiveRegs(dbgs(), LiveIns[RegionIdx], MRI);
               dbgs() << "Region live-in pressure:  ";
               llvm::getRegPressure(MRI, LiveIns[RegionIdx]).print(dbgs());
               dbgs() << "Region register pressure: ";
               PressureBefore.print(dbgs()));
  }

  ScheduleDAGMILive::schedule();
  Regions[RegionIdx] = std::make_pair(RegionBegin, RegionEnd);

  if (!LIS)
    return;

  // Check the results of scheduling.
  GCNMaxOccupancySchedStrategy &S = (GCNMaxOccupancySchedStrategy&)*SchedImpl;
  auto PressureAfter = getRealRegPressure();

  LLVM_DEBUG(dbgs() << "Pressure after scheduling: ";
             PressureAfter.print(dbgs()));

  if (PressureAfter.getSGPRNum() <= S.SGPRCriticalLimit &&
      PressureAfter.getVGPRNum() <= S.VGPRCriticalLimit) {
    Pressure[RegionIdx] = PressureAfter;
    LLVM_DEBUG(dbgs() << "Pressure in desired limits, done.\n");
    return;
  }
  unsigned Occ = MFI.getOccupancy();
  unsigned WavesAfter = std::min(Occ, PressureAfter.getOccupancy(ST));
  unsigned WavesBefore = std::min(Occ, PressureBefore.getOccupancy(ST));
  LLVM_DEBUG(dbgs() << "Occupancy before scheduling: " << WavesBefore
                    << ", after " << WavesAfter << ".\n");

  // We could not keep current target occupancy because of the just scheduled
  // region. Record new occupancy for next scheduling cycle.
  unsigned NewOccupancy = std::max(WavesAfter, WavesBefore);
  // Allow memory bound functions to drop to 4 waves if not limited by an
  // attribute.
  if (WavesAfter < WavesBefore && WavesAfter < MinOccupancy &&
      WavesAfter >= MFI.getMinAllowedOccupancy()) {
    LLVM_DEBUG(dbgs() << "Function is memory bound, allow occupancy drop up to "
                      << MFI.getMinAllowedOccupancy() << " waves\n");
    NewOccupancy = WavesAfter;
  }
  if (NewOccupancy < MinOccupancy) {
    MinOccupancy = NewOccupancy;
    MFI.limitOccupancy(MinOccupancy);
    LLVM_DEBUG(dbgs() << "Occupancy lowered for the function to "
                      << MinOccupancy << ".\n");
  }

  if (WavesAfter >= MinOccupancy) {
    Pressure[RegionIdx] = PressureAfter;
    return;
  }

  LLVM_DEBUG(dbgs() << "Attempting to revert scheduling.\n");
  RegionEnd = RegionBegin;
  for (MachineInstr *MI : Unsched) {
    if (MI->isDebugInstr())
      continue;

    if (MI->getIterator() != RegionEnd) {
      BB->remove(MI);
      BB->insert(RegionEnd, MI);
      if (!MI->isDebugInstr())
        LIS->handleMove(*MI, true);
    }
    // Reset read-undef flags and update them later.
    for (auto &Op : MI->operands())
      if (Op.isReg() && Op.isDef())
        Op.setIsUndef(false);
    RegisterOperands RegOpers;
    RegOpers.collect(*MI, *TRI, MRI, ShouldTrackLaneMasks, false);
    if (!MI->isDebugInstr()) {
      if (ShouldTrackLaneMasks) {
        // Adjust liveness and add missing dead+read-undef flags.
        SlotIndex SlotIdx = LIS->getInstructionIndex(*MI).getRegSlot();
        RegOpers.adjustLaneLiveness(*LIS, MRI, SlotIdx, MI);
      } else {
        // Adjust for missing dead-def flags.
        RegOpers.detectDeadDefs(*MI, *LIS);
      }
    }
    RegionEnd = MI->getIterator();
    ++RegionEnd;
    LLVM_DEBUG(dbgs() << "Scheduling " << *MI);
  }
  RegionBegin = Unsched.front()->getIterator();
  Regions[RegionIdx] = std::make_pair(RegionBegin, RegionEnd);

  placeDebugValues();
}

GCNRegPressure GCNScheduleDAGMILive::getRealRegPressure() const {
  GCNDownwardRPTracker RPTracker(*LIS);
  RPTracker.advance(begin(), end(), &LiveIns[RegionIdx]);
  return RPTracker.moveMaxPressure();
}

void GCNScheduleDAGMILive::computeBlockPressure(const MachineBasicBlock *MBB) {
  GCNDownwardRPTracker RPTracker(*LIS);

  // If the block has the only successor then live-ins of that successor are
  // live-outs of the current block. We can reuse calculated live set if the
  // successor will be sent to scheduling past current block.
  const MachineBasicBlock *OnlySucc = nullptr;
  if (MBB->succ_size() == 1 && !(*MBB->succ_begin())->empty()) {
    SlotIndexes *Ind = LIS->getSlotIndexes();
    if (Ind->getMBBStartIdx(MBB) < Ind->getMBBStartIdx(*MBB->succ_begin()))
      OnlySucc = *MBB->succ_begin();
  }

  // Scheduler sends regions from the end of the block upwards.
  size_t CurRegion = RegionIdx;
  for (size_t E = Regions.size(); CurRegion != E; ++CurRegion)
    if (Regions[CurRegion].first->getParent() != MBB)
      break;
  --CurRegion;

  auto I = MBB->begin();
  auto LiveInIt = MBBLiveIns.find(MBB);
  if (LiveInIt != MBBLiveIns.end()) {
    auto LiveIn = std::move(LiveInIt->second);
    RPTracker.reset(*MBB->begin(), &LiveIn);
    MBBLiveIns.erase(LiveInIt);
  } else {
    auto &Rgn = Regions[CurRegion];
    I = Rgn.first;
    auto *NonDbgMI = &*skipDebugInstructionsForward(Rgn.first, Rgn.second);
    auto LRS = BBLiveInMap.lookup(NonDbgMI);
    assert(isEqual(getLiveRegsBefore(*NonDbgMI, *LIS), LRS));
    RPTracker.reset(*I, &LRS);
  }

  for ( ; ; ) {
    I = RPTracker.getNext();

    if (Regions[CurRegion].first == I) {
      LiveIns[CurRegion] = RPTracker.getLiveRegs();
      RPTracker.clearMaxPressure();
    }

    if (Regions[CurRegion].second == I) {
      Pressure[CurRegion] = RPTracker.moveMaxPressure();
      if (CurRegion-- == RegionIdx)
        break;
    }
    RPTracker.advanceToNext();
    RPTracker.advanceBeforeNext();
  }

  if (OnlySucc) {
    if (I != MBB->end()) {
      RPTracker.advanceToNext();
      RPTracker.advance(MBB->end());
    }
    RPTracker.reset(*OnlySucc->begin(), &RPTracker.getLiveRegs());
    RPTracker.advanceBeforeNext();
    MBBLiveIns[OnlySucc] = RPTracker.moveLiveRegs();
  }
}

DenseMap<MachineInstr *, GCNRPTracker::LiveRegSet>
GCNScheduleDAGMILive::getBBLiveInMap() const {
  assert(!Regions.empty());
  std::vector<MachineInstr *> BBStarters;
  BBStarters.reserve(Regions.size());
  auto I = Regions.rbegin(), E = Regions.rend();
  auto *BB = I->first->getParent();
  do {
    auto *MI = &*skipDebugInstructionsForward(I->first, I->second);
    BBStarters.push_back(MI);
    do {
      ++I;
    } while (I != E && I->first->getParent() == BB);
  } while (I != E);
  return getLiveRegMap(BBStarters, false /*After*/, *LIS);
}

void GCNScheduleDAGMILive::finalizeSchedule() {
  GCNMaxOccupancySchedStrategy &S = (GCNMaxOccupancySchedStrategy&)*SchedImpl;
  LLVM_DEBUG(dbgs() << "All regions recorded, starting actual scheduling.\n");

  LiveIns.resize(Regions.size());
  Pressure.resize(Regions.size());

  if (!Regions.empty())
    BBLiveInMap = getBBLiveInMap();

  do {
    Stage++;
    RegionIdx = 0;
    MachineBasicBlock *MBB = nullptr;

    if (Stage > 1) {
      // Retry function scheduling if we found resulting occupancy and it is
      // lower than used for first pass scheduling. This will give more freedom
      // to schedule low register pressure blocks.
      // Code is partially copied from MachineSchedulerBase::scheduleRegions().

      if (!LIS || StartingOccupancy <= MinOccupancy)
        break;

      LLVM_DEBUG(
          dbgs()
          << "Retrying function scheduling with lowest recorded occupancy "
          << MinOccupancy << ".\n");

      S.setTargetOccupancy(MinOccupancy);
    }

    for (auto Region : Regions) {
      RegionBegin = Region.first;
      RegionEnd = Region.second;

      if (RegionBegin->getParent() != MBB) {
        if (MBB) finishBlock();
        MBB = RegionBegin->getParent();
        startBlock(MBB);
        if (Stage == 1)
          computeBlockPressure(MBB);
      }

      unsigned NumRegionInstrs = std::distance(begin(), end());
      enterRegion(MBB, begin(), end(), NumRegionInstrs);

      // Skip empty scheduling regions (0 or 1 schedulable instructions).
      if (begin() == end() || begin() == std::prev(end())) {
        exitRegion();
        continue;
      }

      LLVM_DEBUG(dbgs() << "********** MI Scheduling **********\n");
      LLVM_DEBUG(dbgs() << MF.getName() << ":" << printMBBReference(*MBB) << " "
                        << MBB->getName() << "\n  From: " << *begin()
                        << "    To: ";
                 if (RegionEnd != MBB->end()) dbgs() << *RegionEnd;
                 else dbgs() << "End";
                 dbgs() << " RegionInstrs: " << NumRegionInstrs << '\n');

      schedule();

      exitRegion();
      ++RegionIdx;
    }
    finishBlock();

  } while (Stage < 2);
}