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

Tree @0392724 (Download .tar.gz)

GCNIterativeScheduler.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
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
//===- GCNIterativeScheduler.cpp ------------------------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//

#include "GCNIterativeScheduler.h"
#include "AMDGPUSubtarget.h"
#include "GCNRegPressure.h"
#include "GCNSchedStrategy.h"
#include "SIMachineFunctionInfo.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/CodeGen/LiveIntervals.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/RegisterPressure.h"
#include "llvm/CodeGen/ScheduleDAG.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cassert>
#include <iterator>
#include <limits>
#include <memory>
#include <type_traits>
#include <vector>

using namespace llvm;

#define DEBUG_TYPE "machine-scheduler"

namespace llvm {

std::vector<const SUnit *> makeMinRegSchedule(ArrayRef<const SUnit *> TopRoots,
                                              const ScheduleDAG &DAG);

  std::vector<const SUnit*> makeGCNILPScheduler(ArrayRef<const SUnit*> BotRoots,
    const ScheduleDAG &DAG);
}

// shim accessors for different order containers
static inline MachineInstr *getMachineInstr(MachineInstr *MI) {
  return MI;
}
static inline MachineInstr *getMachineInstr(const SUnit *SU) {
  return SU->getInstr();
}
static inline MachineInstr *getMachineInstr(const SUnit &SU) {
  return SU.getInstr();
}

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD
static void printRegion(raw_ostream &OS,
                        MachineBasicBlock::iterator Begin,
                        MachineBasicBlock::iterator End,
                        const LiveIntervals *LIS,
                        unsigned MaxInstNum =
                          std::numeric_limits<unsigned>::max()) {
  auto BB = Begin->getParent();
  OS << BB->getParent()->getName() << ":" << printMBBReference(*BB) << ' '
     << BB->getName() << ":\n";
  auto I = Begin;
  MaxInstNum = std::max(MaxInstNum, 1u);
  for (; I != End && MaxInstNum; ++I, --MaxInstNum) {
    if (!I->isDebugInstr() && LIS)
      OS << LIS->getInstructionIndex(*I);
    OS << '\t' << *I;
  }
  if (I != End) {
    OS << "\t...\n";
    I = std::prev(End);
    if (!I->isDebugInstr() && LIS)
      OS << LIS->getInstructionIndex(*I);
    OS << '\t' << *I;
  }
  if (End != BB->end()) { // print boundary inst if present
    OS << "----\n";
    if (LIS) OS << LIS->getInstructionIndex(*End) << '\t';
    OS << *End;
  }
}

LLVM_DUMP_METHOD
static void printLivenessInfo(raw_ostream &OS,
                              MachineBasicBlock::iterator Begin,
                              MachineBasicBlock::iterator End,
                              const LiveIntervals *LIS) {
  const auto BB = Begin->getParent();
  const auto &MRI = BB->getParent()->getRegInfo();

  const auto LiveIns = getLiveRegsBefore(*Begin, *LIS);
  OS << "LIn RP: ";
  getRegPressure(MRI, LiveIns).print(OS);

  const auto BottomMI = End == BB->end() ? std::prev(End) : End;
  const auto LiveOuts = getLiveRegsAfter(*BottomMI, *LIS);
  OS << "LOt RP: ";
  getRegPressure(MRI, LiveOuts).print(OS);
}

LLVM_DUMP_METHOD
void GCNIterativeScheduler::printRegions(raw_ostream &OS) const {
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
  for (const auto R : Regions) {
    OS << "Region to schedule ";
    printRegion(OS, R->Begin, R->End, LIS, 1);
    printLivenessInfo(OS, R->Begin, R->End, LIS);
    OS << "Max RP: ";
    R->MaxPressure.print(OS, &ST);
  }
}

LLVM_DUMP_METHOD
void GCNIterativeScheduler::printSchedResult(raw_ostream &OS,
                                             const Region *R,
                                             const GCNRegPressure &RP) const {
  OS << "\nAfter scheduling ";
  printRegion(OS, R->Begin, R->End, LIS);
  printSchedRP(OS, R->MaxPressure, RP);
  OS << '\n';
}

LLVM_DUMP_METHOD
void GCNIterativeScheduler::printSchedRP(raw_ostream &OS,
                                         const GCNRegPressure &Before,
                                         const GCNRegPressure &After) const {
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
  OS << "RP before: ";
  Before.print(OS, &ST);
  OS << "RP after:  ";
  After.print(OS, &ST);
}
#endif

// DAG builder helper
class GCNIterativeScheduler::BuildDAG {
  GCNIterativeScheduler &Sch;
  SmallVector<SUnit *, 8> TopRoots;

  SmallVector<SUnit*, 8> BotRoots;
public:
  BuildDAG(const Region &R, GCNIterativeScheduler &_Sch)
    : Sch(_Sch) {
    auto BB = R.Begin->getParent();
    Sch.BaseClass::startBlock(BB);
    Sch.BaseClass::enterRegion(BB, R.Begin, R.End, R.NumRegionInstrs);

    Sch.buildSchedGraph(Sch.AA, nullptr, nullptr, nullptr,
                        /*TrackLaneMask*/true);
    Sch.Topo.InitDAGTopologicalSorting();
    Sch.findRootsAndBiasEdges(TopRoots, BotRoots);
  }

  ~BuildDAG() {
    Sch.BaseClass::exitRegion();
    Sch.BaseClass::finishBlock();
  }

  ArrayRef<const SUnit *> getTopRoots() const {
    return TopRoots;
  }
  ArrayRef<SUnit*> getBottomRoots() const {
    return BotRoots;
  }
};

class GCNIterativeScheduler::OverrideLegacyStrategy {
  GCNIterativeScheduler &Sch;
  Region &Rgn;
  std::unique_ptr<MachineSchedStrategy> SaveSchedImpl;
  GCNRegPressure SaveMaxRP;

public:
  OverrideLegacyStrategy(Region &R,
                         MachineSchedStrategy &OverrideStrategy,
                         GCNIterativeScheduler &_Sch)
    : Sch(_Sch)
    , Rgn(R)
    , SaveSchedImpl(std::move(_Sch.SchedImpl))
    , SaveMaxRP(R.MaxPressure) {
    Sch.SchedImpl.reset(&OverrideStrategy);
    auto BB = R.Begin->getParent();
    Sch.BaseClass::startBlock(BB);
    Sch.BaseClass::enterRegion(BB, R.Begin, R.End, R.NumRegionInstrs);
  }

  ~OverrideLegacyStrategy() {
    Sch.BaseClass::exitRegion();
    Sch.BaseClass::finishBlock();
    Sch.SchedImpl.release();
    Sch.SchedImpl = std::move(SaveSchedImpl);
  }

  void schedule() {
    assert(Sch.RegionBegin == Rgn.Begin && Sch.RegionEnd == Rgn.End);
    LLVM_DEBUG(dbgs() << "\nScheduling ";
               printRegion(dbgs(), Rgn.Begin, Rgn.End, Sch.LIS, 2));
    Sch.BaseClass::schedule();

    // Unfortunatelly placeDebugValues incorrectly modifies RegionEnd, restore
    Sch.RegionEnd = Rgn.End;
    //assert(Rgn.End == Sch.RegionEnd);
    Rgn.Begin = Sch.RegionBegin;
    Rgn.MaxPressure.clear();
  }

  void restoreOrder() {
    assert(Sch.RegionBegin == Rgn.Begin && Sch.RegionEnd == Rgn.End);
    // DAG SUnits are stored using original region's order
    // so just use SUnits as the restoring schedule
    Sch.scheduleRegion(Rgn, Sch.SUnits, SaveMaxRP);
  }
};

namespace {

// just a stub to make base class happy
class SchedStrategyStub : public MachineSchedStrategy {
public:
  bool shouldTrackPressure() const override { return false; }
  bool shouldTrackLaneMasks() const override { return false; }
  void initialize(ScheduleDAGMI *DAG) override {}
  SUnit *pickNode(bool &IsTopNode) override { return nullptr; }
  void schedNode(SUnit *SU, bool IsTopNode) override {}
  void releaseTopNode(SUnit *SU) override {}
  void releaseBottomNode(SUnit *SU) override {}
};

} // end anonymous namespace

GCNIterativeScheduler::GCNIterativeScheduler(MachineSchedContext *C,
                                             StrategyKind S)
  : BaseClass(C, llvm::make_unique<SchedStrategyStub>())
  , Context(C)
  , Strategy(S)
  , UPTracker(*LIS) {
}

// returns max pressure for a region
GCNRegPressure
GCNIterativeScheduler::getRegionPressure(MachineBasicBlock::iterator Begin,
                                         MachineBasicBlock::iterator End)
  const {
  // For the purpose of pressure tracking bottom inst of the region should
  // be also processed. End is either BB end, BB terminator inst or sched
  // boundary inst.
  auto const BBEnd = Begin->getParent()->end();
  auto const BottomMI = End == BBEnd ? std::prev(End) : End;

  // scheduleRegions walks bottom to top, so its likely we just get next
  // instruction to track
  auto AfterBottomMI = std::next(BottomMI);
  if (AfterBottomMI == BBEnd ||
      &*AfterBottomMI != UPTracker.getLastTrackedMI()) {
    UPTracker.reset(*BottomMI);
  } else {
    assert(UPTracker.isValid());
  }

  for (auto I = BottomMI; I != Begin; --I)
    UPTracker.recede(*I);

  UPTracker.recede(*Begin);

  assert(UPTracker.isValid() ||
         (dbgs() << "Tracked region ",
          printRegion(dbgs(), Begin, End, LIS), false));
  return UPTracker.moveMaxPressure();
}

// returns max pressure for a tentative schedule
template <typename Range> GCNRegPressure
GCNIterativeScheduler::getSchedulePressure(const Region &R,
                                           Range &&Schedule) const {
  auto const BBEnd = R.Begin->getParent()->end();
  GCNUpwardRPTracker RPTracker(*LIS);
  if (R.End != BBEnd) {
    // R.End points to the boundary instruction but the
    // schedule doesn't include it
    RPTracker.reset(*R.End);
    RPTracker.recede(*R.End);
  } else {
    // R.End doesn't point to the boundary instruction
    RPTracker.reset(*std::prev(BBEnd));
  }
  for (auto I = Schedule.end(), B = Schedule.begin(); I != B;) {
    RPTracker.recede(*getMachineInstr(*--I));
  }
  return RPTracker.moveMaxPressure();
}

void GCNIterativeScheduler::enterRegion(MachineBasicBlock *BB, // overriden
                                        MachineBasicBlock::iterator Begin,
                                        MachineBasicBlock::iterator End,
                                        unsigned NumRegionInstrs) {
  BaseClass::enterRegion(BB, Begin, End, NumRegionInstrs);
  if (NumRegionInstrs > 2) {
    Regions.push_back(
      new (Alloc.Allocate())
      Region { Begin, End, NumRegionInstrs,
               getRegionPressure(Begin, End), nullptr });
  }
}

void GCNIterativeScheduler::schedule() { // overriden
  // do nothing
  LLVM_DEBUG(printLivenessInfo(dbgs(), RegionBegin, RegionEnd, LIS);
             if (!Regions.empty() && Regions.back()->Begin == RegionBegin) {
               dbgs() << "Max RP: ";
               Regions.back()->MaxPressure.print(
                   dbgs(), &MF.getSubtarget<GCNSubtarget>());
             } dbgs()
             << '\n';);
}

void GCNIterativeScheduler::finalizeSchedule() { // overriden
  if (Regions.empty())
    return;
  switch (Strategy) {
  case SCHEDULE_MINREGONLY: scheduleMinReg(); break;
  case SCHEDULE_MINREGFORCED: scheduleMinReg(true); break;
  case SCHEDULE_LEGACYMAXOCCUPANCY: scheduleLegacyMaxOccupancy(); break;
  case SCHEDULE_ILP: scheduleILP(false); break;
  }
}

// Detach schedule from SUnits and interleave it with debug values.
// Returned schedule becomes independent of DAG state.
std::vector<MachineInstr*>
GCNIterativeScheduler::detachSchedule(ScheduleRef Schedule) const {
  std::vector<MachineInstr*> Res;
  Res.reserve(Schedule.size() * 2);

  if (FirstDbgValue)
    Res.push_back(FirstDbgValue);

  const auto DbgB = DbgValues.begin(), DbgE = DbgValues.end();
  for (auto SU : Schedule) {
    Res.push_back(SU->getInstr());
    const auto &D = std::find_if(DbgB, DbgE, [SU](decltype(*DbgB) &P) {
      return P.second == SU->getInstr();
    });
    if (D != DbgE)
      Res.push_back(D->first);
  }
  return Res;
}

void GCNIterativeScheduler::setBestSchedule(Region &R,
                                            ScheduleRef Schedule,
                                            const GCNRegPressure &MaxRP) {
  R.BestSchedule.reset(
    new TentativeSchedule{ detachSchedule(Schedule), MaxRP });
}

void GCNIterativeScheduler::scheduleBest(Region &R) {
  assert(R.BestSchedule.get() && "No schedule specified");
  scheduleRegion(R, R.BestSchedule->Schedule, R.BestSchedule->MaxPressure);
  R.BestSchedule.reset();
}

// minimal required region scheduler, works for ranges of SUnits*,
// SUnits or MachineIntrs*
template <typename Range>
void GCNIterativeScheduler::scheduleRegion(Region &R, Range &&Schedule,
                                           const GCNRegPressure &MaxRP) {
  assert(RegionBegin == R.Begin && RegionEnd == R.End);
  assert(LIS != nullptr);
#ifndef NDEBUG
  const auto SchedMaxRP = getSchedulePressure(R, Schedule);
#endif
  auto BB = R.Begin->getParent();
  auto Top = R.Begin;
  for (const auto &I : Schedule) {
    auto MI = getMachineInstr(I);
    if (MI != &*Top) {
      BB->remove(MI);
      BB->insert(Top, MI);
      if (!MI->isDebugInstr())
        LIS->handleMove(*MI, true);
    }
    if (!MI->isDebugInstr()) {
      // 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*/true,
                                       /*IgnoreDead*/false);
      // Adjust liveness and add missing dead+read-undef flags.
      auto SlotIdx = LIS->getInstructionIndex(*MI).getRegSlot();
      RegOpers.adjustLaneLiveness(*LIS, MRI, SlotIdx, MI);
    }
    Top = std::next(MI->getIterator());
  }
  RegionBegin = getMachineInstr(Schedule.front());

  // Schedule consisting of MachineInstr* is considered 'detached'
  // and already interleaved with debug values
  if (!std::is_same<decltype(*Schedule.begin()), MachineInstr*>::value) {
    placeDebugValues();
    // Unfortunatelly placeDebugValues incorrectly modifies RegionEnd, restore
    //assert(R.End == RegionEnd);
    RegionEnd = R.End;
  }

  R.Begin = RegionBegin;
  R.MaxPressure = MaxRP;

#ifndef NDEBUG
  const auto RegionMaxRP = getRegionPressure(R);
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
#endif
  assert((SchedMaxRP == RegionMaxRP && (MaxRP.empty() || SchedMaxRP == MaxRP))
  || (dbgs() << "Max RP mismatch!!!\n"
                "RP for schedule (calculated): ",
      SchedMaxRP.print(dbgs(), &ST),
      dbgs() << "RP for schedule (reported): ",
      MaxRP.print(dbgs(), &ST),
      dbgs() << "RP after scheduling: ",
      RegionMaxRP.print(dbgs(), &ST),
      false));
}

// Sort recorded regions by pressure - highest at the front
void GCNIterativeScheduler::sortRegionsByPressure(unsigned TargetOcc) {
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
  llvm::sort(Regions, [&ST, TargetOcc](const Region *R1, const Region *R2) {
    return R2->MaxPressure.less(ST, R1->MaxPressure, TargetOcc);
  });
}

///////////////////////////////////////////////////////////////////////////////
// Legacy MaxOccupancy Strategy

// Tries to increase occupancy applying minreg scheduler for a sequence of
// most demanding regions. Obtained schedules are saved as BestSchedule for a
// region.
// TargetOcc is the best achievable occupancy for a kernel.
// Returns better occupancy on success or current occupancy on fail.
// BestSchedules aren't deleted on fail.
unsigned GCNIterativeScheduler::tryMaximizeOccupancy(unsigned TargetOcc) {
  // TODO: assert Regions are sorted descending by pressure
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
  const auto Occ = Regions.front()->MaxPressure.getOccupancy(ST);
  LLVM_DEBUG(dbgs() << "Trying to improve occupancy, target = " << TargetOcc
                    << ", current = " << Occ << '\n');

  auto NewOcc = TargetOcc;
  for (auto R : Regions) {
    if (R->MaxPressure.getOccupancy(ST) >= NewOcc)
      break;

    LLVM_DEBUG(printRegion(dbgs(), R->Begin, R->End, LIS, 3);
               printLivenessInfo(dbgs(), R->Begin, R->End, LIS));

    BuildDAG DAG(*R, *this);
    const auto MinSchedule = makeMinRegSchedule(DAG.getTopRoots(), *this);
    const auto MaxRP = getSchedulePressure(*R, MinSchedule);
    LLVM_DEBUG(dbgs() << "Occupancy improvement attempt:\n";
               printSchedRP(dbgs(), R->MaxPressure, MaxRP));

    NewOcc = std::min(NewOcc, MaxRP.getOccupancy(ST));
    if (NewOcc <= Occ)
      break;

    setBestSchedule(*R, MinSchedule, MaxRP);
  }
  LLVM_DEBUG(dbgs() << "New occupancy = " << NewOcc
                    << ", prev occupancy = " << Occ << '\n');
  if (NewOcc > Occ) {
    SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
    MFI->increaseOccupancy(MF, NewOcc);
  }

  return std::max(NewOcc, Occ);
}

void GCNIterativeScheduler::scheduleLegacyMaxOccupancy(
  bool TryMaximizeOccupancy) {
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
  SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
  auto TgtOcc = MFI->getMinAllowedOccupancy();

  sortRegionsByPressure(TgtOcc);
  auto Occ = Regions.front()->MaxPressure.getOccupancy(ST);

  if (TryMaximizeOccupancy && Occ < TgtOcc)
    Occ = tryMaximizeOccupancy(TgtOcc);

  // This is really weird but for some magic scheduling regions twice
  // gives performance improvement
  const int NumPasses = Occ < TgtOcc ? 2 : 1;

  TgtOcc = std::min(Occ, TgtOcc);
  LLVM_DEBUG(dbgs() << "Scheduling using default scheduler, "
                       "target occupancy = "
                    << TgtOcc << '\n');
  GCNMaxOccupancySchedStrategy LStrgy(Context);
  unsigned FinalOccupancy = std::min(Occ, MFI->getOccupancy());

  for (int I = 0; I < NumPasses; ++I) {
    // running first pass with TargetOccupancy = 0 mimics previous scheduling
    // approach and is a performance magic
    LStrgy.setTargetOccupancy(I == 0 ? 0 : TgtOcc);
    for (auto R : Regions) {
      OverrideLegacyStrategy Ovr(*R, LStrgy, *this);

      Ovr.schedule();
      const auto RP = getRegionPressure(*R);
      LLVM_DEBUG(printSchedRP(dbgs(), R->MaxPressure, RP));

      if (RP.getOccupancy(ST) < TgtOcc) {
        LLVM_DEBUG(dbgs() << "Didn't fit into target occupancy O" << TgtOcc);
        if (R->BestSchedule.get() &&
            R->BestSchedule->MaxPressure.getOccupancy(ST) >= TgtOcc) {
          LLVM_DEBUG(dbgs() << ", scheduling minimal register\n");
          scheduleBest(*R);
        } else {
          LLVM_DEBUG(dbgs() << ", restoring\n");
          Ovr.restoreOrder();
          assert(R->MaxPressure.getOccupancy(ST) >= TgtOcc);
        }
      }
      FinalOccupancy = std::min(FinalOccupancy, RP.getOccupancy(ST));
    }
  }
  MFI->limitOccupancy(FinalOccupancy);
}

///////////////////////////////////////////////////////////////////////////////
// Minimal Register Strategy

void GCNIterativeScheduler::scheduleMinReg(bool force) {
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
  const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
  const auto TgtOcc = MFI->getOccupancy();
  sortRegionsByPressure(TgtOcc);

  auto MaxPressure = Regions.front()->MaxPressure;
  for (auto R : Regions) {
    if (!force && R->MaxPressure.less(ST, MaxPressure, TgtOcc))
      break;

    BuildDAG DAG(*R, *this);
    const auto MinSchedule = makeMinRegSchedule(DAG.getTopRoots(), *this);

    const auto RP = getSchedulePressure(*R, MinSchedule);
    LLVM_DEBUG(if (R->MaxPressure.less(ST, RP, TgtOcc)) {
      dbgs() << "\nWarning: Pressure becomes worse after minreg!";
      printSchedRP(dbgs(), R->MaxPressure, RP);
    });

    if (!force && MaxPressure.less(ST, RP, TgtOcc))
      break;

    scheduleRegion(*R, MinSchedule, RP);
    LLVM_DEBUG(printSchedResult(dbgs(), R, RP));

    MaxPressure = RP;
  }
}

///////////////////////////////////////////////////////////////////////////////
// ILP scheduler port

void GCNIterativeScheduler::scheduleILP(
  bool TryMaximizeOccupancy) {
  const auto &ST = MF.getSubtarget<GCNSubtarget>();
  SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
  auto TgtOcc = MFI->getMinAllowedOccupancy();

  sortRegionsByPressure(TgtOcc);
  auto Occ = Regions.front()->MaxPressure.getOccupancy(ST);

  if (TryMaximizeOccupancy && Occ < TgtOcc)
    Occ = tryMaximizeOccupancy(TgtOcc);

  TgtOcc = std::min(Occ, TgtOcc);
  LLVM_DEBUG(dbgs() << "Scheduling using default scheduler, "
                       "target occupancy = "
                    << TgtOcc << '\n');

  unsigned FinalOccupancy = std::min(Occ, MFI->getOccupancy());
  for (auto R : Regions) {
    BuildDAG DAG(*R, *this);
    const auto ILPSchedule = makeGCNILPScheduler(DAG.getBottomRoots(), *this);

    const auto RP = getSchedulePressure(*R, ILPSchedule);
    LLVM_DEBUG(printSchedRP(dbgs(), R->MaxPressure, RP));

    if (RP.getOccupancy(ST) < TgtOcc) {
      LLVM_DEBUG(dbgs() << "Didn't fit into target occupancy O" << TgtOcc);
      if (R->BestSchedule.get() &&
        R->BestSchedule->MaxPressure.getOccupancy(ST) >= TgtOcc) {
        LLVM_DEBUG(dbgs() << ", scheduling minimal register\n");
        scheduleBest(*R);
      }
    } else {
      scheduleRegion(*R, ILPSchedule, RP);
      LLVM_DEBUG(printSchedResult(dbgs(), R, RP));
      FinalOccupancy = std::min(FinalOccupancy, RP.getOccupancy(ST));
    }
  }
  MFI->limitOccupancy(FinalOccupancy);
}