reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    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
//===- MachinePipeliner.h - Machine Software Pipeliner Pass -------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// An implementation of the Swing Modulo Scheduling (SMS) software pipeliner.
//
// Software pipelining (SWP) is an instruction scheduling technique for loops
// that overlap loop iterations and exploits ILP via a compiler transformation.
//
// Swing Modulo Scheduling is an implementation of software pipelining
// that generates schedules that are near optimal in terms of initiation
// interval, register requirements, and stage count. See the papers:
//
// "Swing Modulo Scheduling: A Lifetime-Sensitive Approach", by J. Llosa,
// A. Gonzalez, E. Ayguade, and M. Valero. In PACT '96 Proceedings of the 1996
// Conference on Parallel Architectures and Compilation Techiniques.
//
// "Lifetime-Sensitive Modulo Scheduling in a Production Environment", by J.
// Llosa, E. Ayguade, A. Gonzalez, M. Valero, and J. Eckhardt. In IEEE
// Transactions on Computers, Vol. 50, No. 3, 2001.
//
// "An Implementation of Swing Modulo Scheduling With Extensions for
// Superblocks", by T. Lattner, Master's Thesis, University of Illinois at
// Urbana-Champaign, 2005.
//
//
// The SMS algorithm consists of three main steps after computing the minimal
// initiation interval (MII).
// 1) Analyze the dependence graph and compute information about each
//    instruction in the graph.
// 2) Order the nodes (instructions) by priority based upon the heuristics
//    described in the algorithm.
// 3) Attempt to schedule the nodes in the specified order using the MII.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_CODEGEN_MACHINEPIPELINER_H
#define LLVM_LIB_CODEGEN_MACHINEPIPELINER_H

#include "llvm/Analysis/AliasAnalysis.h"

#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/RegisterClassInfo.h"
#include "llvm/CodeGen/ScheduleDAGInstrs.h"
#include "llvm/CodeGen/TargetInstrInfo.h"

namespace llvm {

class NodeSet;
class SMSchedule;

extern cl::opt<bool> SwpEnableCopyToPhi;

/// The main class in the implementation of the target independent
/// software pipeliner pass.
class MachinePipeliner : public MachineFunctionPass {
public:
  MachineFunction *MF = nullptr;
  const MachineLoopInfo *MLI = nullptr;
  const MachineDominatorTree *MDT = nullptr;
  const InstrItineraryData *InstrItins;
  const TargetInstrInfo *TII = nullptr;
  RegisterClassInfo RegClassInfo;
  bool disabledByPragma = false;
  unsigned II_setByPragma = 0;

#ifndef NDEBUG
  static int NumTries;
#endif

  /// Cache the target analysis information about the loop.
  struct LoopInfo {
    MachineBasicBlock *TBB = nullptr;
    MachineBasicBlock *FBB = nullptr;
    SmallVector<MachineOperand, 4> BrCond;
    MachineInstr *LoopInductionVar = nullptr;
    MachineInstr *LoopCompare = nullptr;
  };
  LoopInfo LI;

  static char ID;

  MachinePipeliner() : MachineFunctionPass(ID) {
    initializeMachinePipelinerPass(*PassRegistry::getPassRegistry());
  }

  bool runOnMachineFunction(MachineFunction &MF) override;

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

private:
  void preprocessPhiNodes(MachineBasicBlock &B);
  bool canPipelineLoop(MachineLoop &L);
  bool scheduleLoop(MachineLoop &L);
  bool swingModuloScheduler(MachineLoop &L);
  void setPragmaPipelineOptions(MachineLoop &L);
};

/// This class builds the dependence graph for the instructions in a loop,
/// and attempts to schedule the instructions using the SMS algorithm.
class SwingSchedulerDAG : public ScheduleDAGInstrs {
  MachinePipeliner &Pass;
  /// The minimum initiation interval between iterations for this schedule.
  unsigned MII = 0;
  /// The maximum initiation interval between iterations for this schedule.
  unsigned MAX_II = 0;
  /// Set to true if a valid pipelined schedule is found for the loop.
  bool Scheduled = false;
  MachineLoop &Loop;
  LiveIntervals &LIS;
  const RegisterClassInfo &RegClassInfo;
  unsigned II_setByPragma = 0;

  /// A toplogical ordering of the SUnits, which is needed for changing
  /// dependences and iterating over the SUnits.
  ScheduleDAGTopologicalSort Topo;

  struct NodeInfo {
    int ASAP = 0;
    int ALAP = 0;
    int ZeroLatencyDepth = 0;
    int ZeroLatencyHeight = 0;

    NodeInfo() = default;
  };
  /// Computed properties for each node in the graph.
  std::vector<NodeInfo> ScheduleInfo;

  enum OrderKind { BottomUp = 0, TopDown = 1 };
  /// Computed node ordering for scheduling.
  SetVector<SUnit *> NodeOrder;

  using NodeSetType = SmallVector<NodeSet, 8>;
  using ValueMapTy = DenseMap<unsigned, unsigned>;
  using MBBVectorTy = SmallVectorImpl<MachineBasicBlock *>;
  using InstrMapTy = DenseMap<MachineInstr *, MachineInstr *>;

  /// Instructions to change when emitting the final schedule.
  DenseMap<SUnit *, std::pair<unsigned, int64_t>> InstrChanges;

  /// We may create a new instruction, so remember it because it
  /// must be deleted when the pass is finished.
  DenseMap<MachineInstr*, MachineInstr *> NewMIs;

  /// Ordered list of DAG postprocessing steps.
  std::vector<std::unique_ptr<ScheduleDAGMutation>> Mutations;

  /// Helper class to implement Johnson's circuit finding algorithm.
  class Circuits {
    std::vector<SUnit> &SUnits;
    SetVector<SUnit *> Stack;
    BitVector Blocked;
    SmallVector<SmallPtrSet<SUnit *, 4>, 10> B;
    SmallVector<SmallVector<int, 4>, 16> AdjK;
    // Node to Index from ScheduleDAGTopologicalSort
    std::vector<int> *Node2Idx;
    unsigned NumPaths;
    static unsigned MaxPaths;

  public:
    Circuits(std::vector<SUnit> &SUs, ScheduleDAGTopologicalSort &Topo)
        : SUnits(SUs), Blocked(SUs.size()), B(SUs.size()), AdjK(SUs.size()) {
      Node2Idx = new std::vector<int>(SUs.size());
      unsigned Idx = 0;
      for (const auto &NodeNum : Topo)
        Node2Idx->at(NodeNum) = Idx++;
    }

    ~Circuits() { delete Node2Idx; }

    /// Reset the data structures used in the circuit algorithm.
    void reset() {
      Stack.clear();
      Blocked.reset();
      B.assign(SUnits.size(), SmallPtrSet<SUnit *, 4>());
      NumPaths = 0;
    }

    void createAdjacencyStructure(SwingSchedulerDAG *DAG);
    bool circuit(int V, int S, NodeSetType &NodeSets, bool HasBackedge = false);
    void unblock(int U);
  };

  struct CopyToPhiMutation : public ScheduleDAGMutation {
    void apply(ScheduleDAGInstrs *DAG) override;
  };

public:
  SwingSchedulerDAG(MachinePipeliner &P, MachineLoop &L, LiveIntervals &lis,
                    const RegisterClassInfo &rci, unsigned II)
      : ScheduleDAGInstrs(*P.MF, P.MLI, false), Pass(P), Loop(L), LIS(lis),
        RegClassInfo(rci), II_setByPragma(II), Topo(SUnits, &ExitSU) {
    P.MF->getSubtarget().getSMSMutations(Mutations);
    if (SwpEnableCopyToPhi)
      Mutations.push_back(std::make_unique<CopyToPhiMutation>());
  }

  void schedule() override;
  void finishBlock() override;

  /// Return true if the loop kernel has been scheduled.
  bool hasNewSchedule() { return Scheduled; }

  /// Return the earliest time an instruction may be scheduled.
  int getASAP(SUnit *Node) { return ScheduleInfo[Node->NodeNum].ASAP; }

  /// Return the latest time an instruction my be scheduled.
  int getALAP(SUnit *Node) { return ScheduleInfo[Node->NodeNum].ALAP; }

  /// The mobility function, which the number of slots in which
  /// an instruction may be scheduled.
  int getMOV(SUnit *Node) { return getALAP(Node) - getASAP(Node); }

  /// The depth, in the dependence graph, for a node.
  unsigned getDepth(SUnit *Node) { return Node->getDepth(); }

  /// The maximum unweighted length of a path from an arbitrary node to the
  /// given node in which each edge has latency 0
  int getZeroLatencyDepth(SUnit *Node) {
    return ScheduleInfo[Node->NodeNum].ZeroLatencyDepth;
  }

  /// The height, in the dependence graph, for a node.
  unsigned getHeight(SUnit *Node) { return Node->getHeight(); }

  /// The maximum unweighted length of a path from the given node to an
  /// arbitrary node in which each edge has latency 0
  int getZeroLatencyHeight(SUnit *Node) {
    return ScheduleInfo[Node->NodeNum].ZeroLatencyHeight;
  }

  /// Return true if the dependence is a back-edge in the data dependence graph.
  /// Since the DAG doesn't contain cycles, we represent a cycle in the graph
  /// using an anti dependence from a Phi to an instruction.
  bool isBackedge(SUnit *Source, const SDep &Dep) {
    if (Dep.getKind() != SDep::Anti)
      return false;
    return Source->getInstr()->isPHI() || Dep.getSUnit()->getInstr()->isPHI();
  }

  bool isLoopCarriedDep(SUnit *Source, const SDep &Dep, bool isSucc = true);

  /// The distance function, which indicates that operation V of iteration I
  /// depends on operations U of iteration I-distance.
  unsigned getDistance(SUnit *U, SUnit *V, const SDep &Dep) {
    // Instructions that feed a Phi have a distance of 1. Computing larger
    // values for arrays requires data dependence information.
    if (V->getInstr()->isPHI() && Dep.getKind() == SDep::Anti)
      return 1;
    return 0;
  }

  void applyInstrChange(MachineInstr *MI, SMSchedule &Schedule);

  void fixupRegisterOverlaps(std::deque<SUnit *> &Instrs);

  /// Return the new base register that was stored away for the changed
  /// instruction.
  unsigned getInstrBaseReg(SUnit *SU) {
    DenseMap<SUnit *, std::pair<unsigned, int64_t>>::iterator It =
        InstrChanges.find(SU);
    if (It != InstrChanges.end())
      return It->second.first;
    return 0;
  }

  void addMutation(std::unique_ptr<ScheduleDAGMutation> Mutation) {
    Mutations.push_back(std::move(Mutation));
  }

  static bool classof(const ScheduleDAGInstrs *DAG) { return true; }

private:
  void addLoopCarriedDependences(AliasAnalysis *AA);
  void updatePhiDependences();
  void changeDependences();
  unsigned calculateResMII();
  unsigned calculateRecMII(NodeSetType &RecNodeSets);
  void findCircuits(NodeSetType &NodeSets);
  void fuseRecs(NodeSetType &NodeSets);
  void removeDuplicateNodes(NodeSetType &NodeSets);
  void computeNodeFunctions(NodeSetType &NodeSets);
  void registerPressureFilter(NodeSetType &NodeSets);
  void colocateNodeSets(NodeSetType &NodeSets);
  void checkNodeSets(NodeSetType &NodeSets);
  void groupRemainingNodes(NodeSetType &NodeSets);
  void addConnectedNodes(SUnit *SU, NodeSet &NewSet,
                         SetVector<SUnit *> &NodesAdded);
  void computeNodeOrder(NodeSetType &NodeSets);
  void checkValidNodeOrder(const NodeSetType &Circuits) const;
  bool schedulePipeline(SMSchedule &Schedule);
  bool computeDelta(MachineInstr &MI, unsigned &Delta);
  MachineInstr *findDefInLoop(unsigned Reg);
  bool canUseLastOffsetValue(MachineInstr *MI, unsigned &BasePos,
                             unsigned &OffsetPos, unsigned &NewBase,
                             int64_t &NewOffset);
  void postprocessDAG();
  /// Set the Minimum Initiation Interval for this schedule attempt.
  void setMII(unsigned ResMII, unsigned RecMII);
  /// Set the Maximum Initiation Interval for this schedule attempt.
  void setMAX_II();
};

/// A NodeSet contains a set of SUnit DAG nodes with additional information
/// that assigns a priority to the set.
class NodeSet {
  SetVector<SUnit *> Nodes;
  bool HasRecurrence = false;
  unsigned RecMII = 0;
  int MaxMOV = 0;
  unsigned MaxDepth = 0;
  unsigned Colocate = 0;
  SUnit *ExceedPressure = nullptr;
  unsigned Latency = 0;

public:
  using iterator = SetVector<SUnit *>::const_iterator;

  NodeSet() = default;
  NodeSet(iterator S, iterator E) : Nodes(S, E), HasRecurrence(true) {
    Latency = 0;
    for (unsigned i = 0, e = Nodes.size(); i < e; ++i)
      for (const SDep &Succ : Nodes[i]->Succs)
        if (Nodes.count(Succ.getSUnit()))
          Latency += Succ.getLatency();
  }

  bool insert(SUnit *SU) { return Nodes.insert(SU); }

  void insert(iterator S, iterator E) { Nodes.insert(S, E); }

  template <typename UnaryPredicate> bool remove_if(UnaryPredicate P) {
    return Nodes.remove_if(P);
  }

  unsigned count(SUnit *SU) const { return Nodes.count(SU); }

  bool hasRecurrence() { return HasRecurrence; };

  unsigned size() const { return Nodes.size(); }

  bool empty() const { return Nodes.empty(); }

  SUnit *getNode(unsigned i) const { return Nodes[i]; };

  void setRecMII(unsigned mii) { RecMII = mii; };

  void setColocate(unsigned c) { Colocate = c; };

  void setExceedPressure(SUnit *SU) { ExceedPressure = SU; }

  bool isExceedSU(SUnit *SU) { return ExceedPressure == SU; }

  int compareRecMII(NodeSet &RHS) { return RecMII - RHS.RecMII; }

  int getRecMII() { return RecMII; }

  /// Summarize node functions for the entire node set.
  void computeNodeSetInfo(SwingSchedulerDAG *SSD) {
    for (SUnit *SU : *this) {
      MaxMOV = std::max(MaxMOV, SSD->getMOV(SU));
      MaxDepth = std::max(MaxDepth, SSD->getDepth(SU));
    }
  }

  unsigned getLatency() { return Latency; }

  unsigned getMaxDepth() { return MaxDepth; }

  void clear() {
    Nodes.clear();
    RecMII = 0;
    HasRecurrence = false;
    MaxMOV = 0;
    MaxDepth = 0;
    Colocate = 0;
    ExceedPressure = nullptr;
  }

  operator SetVector<SUnit *> &() { return Nodes; }

  /// Sort the node sets by importance. First, rank them by recurrence MII,
  /// then by mobility (least mobile done first), and finally by depth.
  /// Each node set may contain a colocate value which is used as the first
  /// tie breaker, if it's set.
  bool operator>(const NodeSet &RHS) const {
    if (RecMII == RHS.RecMII) {
      if (Colocate != 0 && RHS.Colocate != 0 && Colocate != RHS.Colocate)
        return Colocate < RHS.Colocate;
      if (MaxMOV == RHS.MaxMOV)
        return MaxDepth > RHS.MaxDepth;
      return MaxMOV < RHS.MaxMOV;
    }
    return RecMII > RHS.RecMII;
  }

  bool operator==(const NodeSet &RHS) const {
    return RecMII == RHS.RecMII && MaxMOV == RHS.MaxMOV &&
           MaxDepth == RHS.MaxDepth;
  }

  bool operator!=(const NodeSet &RHS) const { return !operator==(RHS); }

  iterator begin() { return Nodes.begin(); }
  iterator end() { return Nodes.end(); }
  void print(raw_ostream &os) const;

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
  LLVM_DUMP_METHOD void dump() const;
#endif
};

// 16 was selected based on the number of ProcResource kinds for all
// existing Subtargets, so that SmallVector don't need to resize too often.
static const int DefaultProcResSize = 16;

class ResourceManager {
private:
  const MCSubtargetInfo *STI;
  const MCSchedModel &SM;
  const bool UseDFA;
  std::unique_ptr<DFAPacketizer> DFAResources;
  /// Each processor resource is associated with a so-called processor resource
  /// mask. This vector allows to correlate processor resource IDs with
  /// processor resource masks. There is exactly one element per each processor
  /// resource declared by the scheduling model.
  llvm::SmallVector<uint64_t, DefaultProcResSize> ProcResourceMasks;

  llvm::SmallVector<uint64_t, DefaultProcResSize> ProcResourceCount;

public:
  ResourceManager(const TargetSubtargetInfo *ST)
      : STI(ST), SM(ST->getSchedModel()), UseDFA(ST->useDFAforSMS()),
        ProcResourceMasks(SM.getNumProcResourceKinds(), 0),
        ProcResourceCount(SM.getNumProcResourceKinds(), 0) {
    if (UseDFA)
      DFAResources.reset(ST->getInstrInfo()->CreateTargetScheduleState(*ST));
    initProcResourceVectors(SM, ProcResourceMasks);
  }

  void initProcResourceVectors(const MCSchedModel &SM,
                               SmallVectorImpl<uint64_t> &Masks);
  /// Check if the resources occupied by a MCInstrDesc are available in
  /// the current state.
  bool canReserveResources(const MCInstrDesc *MID) const;

  /// Reserve the resources occupied by a MCInstrDesc and change the current
  /// state to reflect that change.
  void reserveResources(const MCInstrDesc *MID);

  /// Check if the resources occupied by a machine instruction are available
  /// in the current state.
  bool canReserveResources(const MachineInstr &MI) const;

  /// Reserve the resources occupied by a machine instruction and change the
  /// current state to reflect that change.
  void reserveResources(const MachineInstr &MI);

  /// Reset the state
  void clearResources();
};

/// This class represents the scheduled code.  The main data structure is a
/// map from scheduled cycle to instructions.  During scheduling, the
/// data structure explicitly represents all stages/iterations.   When
/// the algorithm finshes, the schedule is collapsed into a single stage,
/// which represents instructions from different loop iterations.
///
/// The SMS algorithm allows negative values for cycles, so the first cycle
/// in the schedule is the smallest cycle value.
class SMSchedule {
private:
  /// Map from execution cycle to instructions.
  DenseMap<int, std::deque<SUnit *>> ScheduledInstrs;

  /// Map from instruction to execution cycle.
  std::map<SUnit *, int> InstrToCycle;

  /// Keep track of the first cycle value in the schedule.  It starts
  /// as zero, but the algorithm allows negative values.
  int FirstCycle = 0;

  /// Keep track of the last cycle value in the schedule.
  int LastCycle = 0;

  /// The initiation interval (II) for the schedule.
  int InitiationInterval = 0;

  /// Target machine information.
  const TargetSubtargetInfo &ST;

  /// Virtual register information.
  MachineRegisterInfo &MRI;

  ResourceManager ProcItinResources;

public:
  SMSchedule(MachineFunction *mf)
      : ST(mf->getSubtarget()), MRI(mf->getRegInfo()), ProcItinResources(&ST) {}

  void reset() {
    ScheduledInstrs.clear();
    InstrToCycle.clear();
    FirstCycle = 0;
    LastCycle = 0;
    InitiationInterval = 0;
  }

  /// Set the initiation interval for this schedule.
  void setInitiationInterval(int ii) { InitiationInterval = ii; }

  /// Return the first cycle in the completed schedule.  This
  /// can be a negative value.
  int getFirstCycle() const { return FirstCycle; }

  /// Return the last cycle in the finalized schedule.
  int getFinalCycle() const { return FirstCycle + InitiationInterval - 1; }

  /// Return the cycle of the earliest scheduled instruction in the dependence
  /// chain.
  int earliestCycleInChain(const SDep &Dep);

  /// Return the cycle of the latest scheduled instruction in the dependence
  /// chain.
  int latestCycleInChain(const SDep &Dep);

  void computeStart(SUnit *SU, int *MaxEarlyStart, int *MinLateStart,
                    int *MinEnd, int *MaxStart, int II, SwingSchedulerDAG *DAG);
  bool insert(SUnit *SU, int StartCycle, int EndCycle, int II);

  /// Iterators for the cycle to instruction map.
  using sched_iterator = DenseMap<int, std::deque<SUnit *>>::iterator;
  using const_sched_iterator =
      DenseMap<int, std::deque<SUnit *>>::const_iterator;

  /// Return true if the instruction is scheduled at the specified stage.
  bool isScheduledAtStage(SUnit *SU, unsigned StageNum) {
    return (stageScheduled(SU) == (int)StageNum);
  }

  /// Return the stage for a scheduled instruction.  Return -1 if
  /// the instruction has not been scheduled.
  int stageScheduled(SUnit *SU) const {
    std::map<SUnit *, int>::const_iterator it = InstrToCycle.find(SU);
    if (it == InstrToCycle.end())
      return -1;
    return (it->second - FirstCycle) / InitiationInterval;
  }

  /// Return the cycle for a scheduled instruction. This function normalizes
  /// the first cycle to be 0.
  unsigned cycleScheduled(SUnit *SU) const {
    std::map<SUnit *, int>::const_iterator it = InstrToCycle.find(SU);
    assert(it != InstrToCycle.end() && "Instruction hasn't been scheduled.");
    return (it->second - FirstCycle) % InitiationInterval;
  }

  /// Return the maximum stage count needed for this schedule.
  unsigned getMaxStageCount() {
    return (LastCycle - FirstCycle) / InitiationInterval;
  }

  /// Return the instructions that are scheduled at the specified cycle.
  std::deque<SUnit *> &getInstructions(int cycle) {
    return ScheduledInstrs[cycle];
  }

  bool isValidSchedule(SwingSchedulerDAG *SSD);
  void finalizeSchedule(SwingSchedulerDAG *SSD);
  void orderDependence(SwingSchedulerDAG *SSD, SUnit *SU,
                       std::deque<SUnit *> &Insts);
  bool isLoopCarried(SwingSchedulerDAG *SSD, MachineInstr &Phi);
  bool isLoopCarriedDefOfUse(SwingSchedulerDAG *SSD, MachineInstr *Def,
                             MachineOperand &MO);
  void print(raw_ostream &os) const;
  void dump() const;
};

} // end namespace llvm

#endif // LLVM_LIB_CODEGEN_MACHINEPIPELINER_H