LLVM API Documentation

PostRASchedulerList.cpp

Go to the documentation of this file.
00001 //===----- SchedulePostRAList.cpp - list scheduler ------------------------===//
00002 //
00003 //                     The LLVM Compiler Infrastructure
00004 //
00005 // This file is distributed under the University of Illinois Open Source
00006 // License. See LICENSE.TXT for details.
00007 //
00008 //===----------------------------------------------------------------------===//
00009 //
00010 // This implements a top-down list scheduler, using standard algorithms.
00011 // The basic approach uses a priority queue of available nodes to schedule.
00012 // One at a time, nodes are taken from the priority queue (thus in priority
00013 // order), checked for legality to schedule, and emitted if legal.
00014 //
00015 // Nodes may not be legal to schedule either due to structural hazards (e.g.
00016 // pipeline or resource constraints) or because an input to the instruction has
00017 // not completed execution.
00018 //
00019 //===----------------------------------------------------------------------===//
00020 
00021 #define DEBUG_TYPE "post-RA-sched"
00022 #include "ExactHazardRecognizer.h"
00023 #include "SimpleHazardRecognizer.h"
00024 #include "ScheduleDAGInstrs.h"
00025 #include "llvm/CodeGen/Passes.h"
00026 #include "llvm/CodeGen/LatencyPriorityQueue.h"
00027 #include "llvm/CodeGen/SchedulerRegistry.h"
00028 #include "llvm/CodeGen/MachineDominators.h"
00029 #include "llvm/CodeGen/MachineFunctionPass.h"
00030 #include "llvm/CodeGen/MachineLoopInfo.h"
00031 #include "llvm/CodeGen/MachineRegisterInfo.h"
00032 #include "llvm/CodeGen/ScheduleHazardRecognizer.h"
00033 #include "llvm/Target/TargetLowering.h"
00034 #include "llvm/Target/TargetMachine.h"
00035 #include "llvm/Target/TargetInstrInfo.h"
00036 #include "llvm/Target/TargetRegisterInfo.h"
00037 #include "llvm/Support/Compiler.h"
00038 #include "llvm/Support/Debug.h"
00039 #include "llvm/Support/ErrorHandling.h"
00040 #include "llvm/Support/raw_ostream.h"
00041 #include "llvm/ADT/Statistic.h"
00042 #include <map>
00043 using namespace llvm;
00044 
00045 STATISTIC(NumNoops, "Number of noops inserted");
00046 STATISTIC(NumStalls, "Number of pipeline stalls");
00047 
00048 static cl::opt<bool>
00049 EnableAntiDepBreaking("break-anti-dependencies",
00050                       cl::desc("Break post-RA scheduling anti-dependencies"),
00051                       cl::init(true), cl::Hidden);
00052 
00053 static cl::opt<bool>
00054 EnablePostRAHazardAvoidance("avoid-hazards",
00055                       cl::desc("Enable exact hazard avoidance"),
00056                       cl::init(false), cl::Hidden);
00057 
00058 namespace {
00059   class VISIBILITY_HIDDEN PostRAScheduler : public MachineFunctionPass {
00060   public:
00061     static char ID;
00062     PostRAScheduler() : MachineFunctionPass(&ID) {}
00063 
00064     void getAnalysisUsage(AnalysisUsage &AU) const {
00065       AU.setPreservesCFG();
00066       AU.addRequired<MachineDominatorTree>();
00067       AU.addPreserved<MachineDominatorTree>();
00068       AU.addRequired<MachineLoopInfo>();
00069       AU.addPreserved<MachineLoopInfo>();
00070       MachineFunctionPass::getAnalysisUsage(AU);
00071     }
00072 
00073     const char *getPassName() const {
00074       return "Post RA top-down list latency scheduler";
00075     }
00076 
00077     bool runOnMachineFunction(MachineFunction &Fn);
00078   };
00079   char PostRAScheduler::ID = 0;
00080 
00081   class VISIBILITY_HIDDEN SchedulePostRATDList : public ScheduleDAGInstrs {
00082     /// AvailableQueue - The priority queue to use for the available SUnits.
00083     ///
00084     LatencyPriorityQueue AvailableQueue;
00085   
00086     /// PendingQueue - This contains all of the instructions whose operands have
00087     /// been issued, but their results are not ready yet (due to the latency of
00088     /// the operation).  Once the operands becomes available, the instruction is
00089     /// added to the AvailableQueue.
00090     std::vector<SUnit*> PendingQueue;
00091 
00092     /// Topo - A topological ordering for SUnits.
00093     ScheduleDAGTopologicalSort Topo;
00094 
00095     /// AllocatableSet - The set of allocatable registers.
00096     /// We'll be ignoring anti-dependencies on non-allocatable registers,
00097     /// because they may not be safe to break.
00098     const BitVector AllocatableSet;
00099 
00100     /// HazardRec - The hazard recognizer to use.
00101     ScheduleHazardRecognizer *HazardRec;
00102 
00103     /// Classes - For live regs that are only used in one register class in a
00104     /// live range, the register class. If the register is not live, the
00105     /// corresponding value is null. If the register is live but used in
00106     /// multiple register classes, the corresponding value is -1 casted to a
00107     /// pointer.
00108     const TargetRegisterClass *
00109       Classes[TargetRegisterInfo::FirstVirtualRegister];
00110 
00111     /// RegRegs - Map registers to all their references within a live range.
00112     std::multimap<unsigned, MachineOperand *> RegRefs;
00113 
00114     /// The index of the most recent kill (proceding bottom-up), or ~0u if
00115     /// the register is not live.
00116     unsigned KillIndices[TargetRegisterInfo::FirstVirtualRegister];
00117 
00118     /// The index of the most recent complete def (proceding bottom up), or ~0u
00119     /// if the register is live.
00120     unsigned DefIndices[TargetRegisterInfo::FirstVirtualRegister];
00121 
00122   public:
00123     SchedulePostRATDList(MachineFunction &MF,
00124                          const MachineLoopInfo &MLI,
00125                          const MachineDominatorTree &MDT,
00126                          ScheduleHazardRecognizer *HR)
00127       : ScheduleDAGInstrs(MF, MLI, MDT), Topo(SUnits),
00128         AllocatableSet(TRI->getAllocatableSet(MF)),
00129         HazardRec(HR) {}
00130 
00131     ~SchedulePostRATDList() {
00132       delete HazardRec;
00133     }
00134 
00135     /// StartBlock - Initialize register live-range state for scheduling in
00136     /// this block.
00137     ///
00138     void StartBlock(MachineBasicBlock *BB);
00139 
00140     /// Schedule - Schedule the instruction range using list scheduling.
00141     ///
00142     void Schedule();
00143 
00144     /// Observe - Update liveness information to account for the current
00145     /// instruction, which will not be scheduled.
00146     ///
00147     void Observe(MachineInstr *MI, unsigned Count);
00148 
00149     /// FinishBlock - Clean up register live-range state.
00150     ///
00151     void FinishBlock();
00152 
00153   private:
00154     void PrescanInstruction(MachineInstr *MI);
00155     void ScanInstruction(MachineInstr *MI, unsigned Count);
00156     void ReleaseSucc(SUnit *SU, SDep *SuccEdge);
00157     void ReleaseSuccessors(SUnit *SU);
00158     void ScheduleNodeTopDown(SUnit *SU, unsigned CurCycle);
00159     void ListScheduleTopDown();
00160     bool BreakAntiDependencies();
00161     unsigned findSuitableFreeRegister(unsigned AntiDepReg,
00162                                       unsigned LastNewReg,
00163                                       const TargetRegisterClass *);
00164   };
00165 }
00166 
00167 /// isSchedulingBoundary - Test if the given instruction should be
00168 /// considered a scheduling boundary. This primarily includes labels
00169 /// and terminators.
00170 ///
00171 static bool isSchedulingBoundary(const MachineInstr *MI,
00172                                  const MachineFunction &MF) {
00173   // Terminators and labels can't be scheduled around.
00174   if (MI->getDesc().isTerminator() || MI->isLabel())
00175     return true;
00176 
00177   // Don't attempt to schedule around any instruction that modifies
00178   // a stack-oriented pointer, as it's unlikely to be profitable. This
00179   // saves compile time, because it doesn't require every single
00180   // stack slot reference to depend on the instruction that does the
00181   // modification.
00182   const TargetLowering &TLI = *MF.getTarget().getTargetLowering();
00183   if (MI->modifiesRegister(TLI.getStackPointerRegisterToSaveRestore()))
00184     return true;
00185 
00186   return false;
00187 }
00188 
00189 bool PostRAScheduler::runOnMachineFunction(MachineFunction &Fn) {
00190   DEBUG(errs() << "PostRAScheduler\n");
00191 
00192   const MachineLoopInfo &MLI = getAnalysis<MachineLoopInfo>();
00193   const MachineDominatorTree &MDT = getAnalysis<MachineDominatorTree>();
00194   const InstrItineraryData &InstrItins = Fn.getTarget().getInstrItineraryData();
00195   ScheduleHazardRecognizer *HR = EnablePostRAHazardAvoidance ?
00196     (ScheduleHazardRecognizer *)new ExactHazardRecognizer(InstrItins) :
00197     (ScheduleHazardRecognizer *)new SimpleHazardRecognizer();
00198 
00199   SchedulePostRATDList Scheduler(Fn, MLI, MDT, HR);
00200 
00201   // Loop over all of the basic blocks
00202   for (MachineFunction::iterator MBB = Fn.begin(), MBBe = Fn.end();
00203        MBB != MBBe; ++MBB) {
00204     // Initialize register live-range state for scheduling in this block.
00205     Scheduler.StartBlock(MBB);
00206 
00207     // Schedule each sequence of instructions not interrupted by a label
00208     // or anything else that effectively needs to shut down scheduling.
00209     MachineBasicBlock::iterator Current = MBB->end();
00210     unsigned Count = MBB->size(), CurrentCount = Count;
00211     for (MachineBasicBlock::iterator I = Current; I != MBB->begin(); ) {
00212       MachineInstr *MI = prior(I);
00213       if (isSchedulingBoundary(MI, Fn)) {
00214         Scheduler.Run(MBB, I, Current, CurrentCount);
00215         Scheduler.EmitSchedule();
00216         Current = MI;
00217         CurrentCount = Count - 1;
00218         Scheduler.Observe(MI, CurrentCount);
00219       }
00220       I = MI;
00221       --Count;
00222     }
00223     assert(Count == 0 && "Instruction count mismatch!");
00224     assert((MBB->begin() == Current || CurrentCount != 0) &&
00225            "Instruction count mismatch!");
00226     Scheduler.Run(MBB, MBB->begin(), Current, CurrentCount);
00227     Scheduler.EmitSchedule();
00228 
00229     // Clean up register live-range state.
00230     Scheduler.FinishBlock();
00231   }
00232 
00233   return true;
00234 }
00235   
00236 /// StartBlock - Initialize register live-range state for scheduling in
00237 /// this block.
00238 ///
00239 void SchedulePostRATDList::StartBlock(MachineBasicBlock *BB) {
00240   // Call the superclass.
00241   ScheduleDAGInstrs::StartBlock(BB);
00242 
00243   // Reset the hazard recognizer.
00244   HazardRec->Reset();
00245 
00246   // Clear out the register class data.
00247   std::fill(Classes, array_endof(Classes),
00248             static_cast<const TargetRegisterClass *>(0));
00249 
00250   // Initialize the indices to indicate that no registers are live.
00251   std::fill(KillIndices, array_endof(KillIndices), ~0u);
00252   std::fill(DefIndices, array_endof(DefIndices), BB->size());
00253 
00254   // Determine the live-out physregs for this block.
00255   if (!BB->empty() && BB->back().getDesc().isReturn())
00256     // In a return block, examine the function live-out regs.
00257     for (MachineRegisterInfo::liveout_iterator I = MRI.liveout_begin(),
00258          E = MRI.liveout_end(); I != E; ++I) {
00259       unsigned Reg = *I;
00260       Classes[Reg] = reinterpret_cast<TargetRegisterClass *>(-1);
00261       KillIndices[Reg] = BB->size();
00262       DefIndices[Reg] = ~0u;
00263       // Repeat, for all aliases.
00264       for (const unsigned *Alias = TRI->getAliasSet(Reg); *Alias; ++Alias) {
00265         unsigned AliasReg = *Alias;
00266         Classes[AliasReg] = reinterpret_cast<TargetRegisterClass *>(-1);
00267         KillIndices[AliasReg] = BB->size();
00268         DefIndices[AliasReg] = ~0u;
00269       }
00270     }
00271   else
00272     // In a non-return block, examine the live-in regs of all successors.
00273     for (MachineBasicBlock::succ_iterator SI = BB->succ_begin(),
00274          SE = BB->succ_end(); SI != SE; ++SI)
00275       for (MachineBasicBlock::livein_iterator I = (*SI)->livein_begin(),
00276            E = (*SI)->livein_end(); I != E; ++I) {
00277         unsigned Reg = *I;
00278         Classes[Reg] = reinterpret_cast<TargetRegisterClass *>(-1);
00279         KillIndices[Reg] = BB->size();
00280         DefIndices[Reg] = ~0u;
00281         // Repeat, for all aliases.
00282         for (const unsigned *Alias = TRI->getAliasSet(Reg); *Alias; ++Alias) {
00283           unsigned AliasReg = *Alias;
00284           Classes[AliasReg] = reinterpret_cast<TargetRegisterClass *>(-1);
00285           KillIndices[AliasReg] = BB->size();
00286           DefIndices[AliasReg] = ~0u;
00287         }
00288       }
00289 
00290   // Consider callee-saved registers as live-out, since we're running after
00291   // prologue/epilogue insertion so there's no way to add additional
00292   // saved registers.
00293   //
00294   // TODO: If the callee saves and restores these, then we can potentially
00295   // use them between the save and the restore. To do that, we could scan
00296   // the exit blocks to see which of these registers are defined.
00297   // Alternatively, callee-saved registers that aren't saved and restored
00298   // could be marked live-in in every block.
00299   for (const unsigned *I = TRI->getCalleeSavedRegs(); *I; ++I) {
00300     unsigned Reg = *I;
00301     Classes[Reg] = reinterpret_cast<TargetRegisterClass *>(-1);
00302     KillIndices[Reg] = BB->size();
00303     DefIndices[Reg] = ~0u;
00304     // Repeat, for all aliases.
00305     for (const unsigned *Alias = TRI->getAliasSet(Reg); *Alias; ++Alias) {
00306       unsigned AliasReg = *Alias;
00307       Classes[AliasReg] = reinterpret_cast<TargetRegisterClass *>(-1);
00308       KillIndices[AliasReg] = BB->size();
00309       DefIndices[AliasReg] = ~0u;
00310     }
00311   }
00312 }
00313 
00314 /// Schedule - Schedule the instruction range using list scheduling.
00315 ///
00316 void SchedulePostRATDList::Schedule() {
00317   DEBUG(errs() << "********** List Scheduling **********\n");
00318   
00319   // Build the scheduling graph.
00320   BuildSchedGraph();
00321 
00322   if (EnableAntiDepBreaking) {
00323     if (BreakAntiDependencies()) {
00324       // We made changes. Update the dependency graph.
00325       // Theoretically we could update the graph in place:
00326       // When a live range is changed to use a different register, remove
00327       // the def's anti-dependence *and* output-dependence edges due to
00328       // that register, and add new anti-dependence and output-dependence
00329       // edges based on the next live range of the register.
00330       SUnits.clear();
00331       EntrySU = SUnit();
00332       ExitSU = SUnit();
00333       BuildSchedGraph();
00334     }
00335   }
00336 
00337   DEBUG(for (unsigned su = 0, e = SUnits.size(); su != e; ++su)
00338           SUnits[su].dumpAll(this));
00339 
00340   AvailableQueue.initNodes(SUnits);
00341 
00342   ListScheduleTopDown();
00343   
00344   AvailableQueue.releaseState();
00345 }
00346 
00347 /// Observe - Update liveness information to account for the current
00348 /// instruction, which will not be scheduled.
00349 ///
00350 void SchedulePostRATDList::Observe(MachineInstr *MI, unsigned Count) {
00351   assert(Count < InsertPosIndex && "Instruction index out of expected range!");
00352 
00353   // Any register which was defined within the previous scheduling region
00354   // may have been rescheduled and its lifetime may overlap with registers
00355   // in ways not reflected in our current liveness state. For each such
00356   // register, adjust the liveness state to be conservatively correct.
00357   for (unsigned Reg = 0; Reg != TargetRegisterInfo::FirstVirtualRegister; ++Reg)
00358     if (DefIndices[Reg] < InsertPosIndex && DefIndices[Reg] >= Count) {
00359       assert(KillIndices[Reg] == ~0u && "Clobbered register is live!");
00360       // Mark this register to be non-renamable.
00361       Classes[Reg] = reinterpret_cast<TargetRegisterClass *>(-1);
00362       // Move the def index to the end of the previous region, to reflect
00363       // that the def could theoretically have been scheduled at the end.
00364       DefIndices[Reg] = InsertPosIndex;
00365     }
00366 
00367   PrescanInstruction(MI);
00368   ScanInstruction(MI, Count);
00369 }
00370 
00371 /// FinishBlock - Clean up register live-range state.
00372 ///
00373 void SchedulePostRATDList::FinishBlock() {
00374   RegRefs.clear();
00375 
00376   // Call the superclass.
00377   ScheduleDAGInstrs::FinishBlock();
00378 }
00379 
00380 /// CriticalPathStep - Return the next SUnit after SU on the bottom-up
00381 /// critical path.
00382 static SDep *CriticalPathStep(SUnit *SU) {
00383   SDep *Next = 0;
00384   unsigned NextDepth = 0;
00385   // Find the predecessor edge with the greatest depth.
00386   for (SUnit::pred_iterator P = SU->Preds.begin(), PE = SU->Preds.end();
00387        P != PE; ++P) {
00388     SUnit *PredSU = P->getSUnit();
00389     unsigned PredLatency = P->getLatency();
00390     unsigned PredTotalLatency = PredSU->getDepth() + PredLatency;
00391     // In the case of a latency tie, prefer an anti-dependency edge over
00392     // other types of edges.
00393     if (NextDepth < PredTotalLatency ||
00394         (NextDepth == PredTotalLatency && P->getKind() == SDep::Anti)) {
00395       NextDepth = PredTotalLatency;
00396       Next = &*P;
00397     }
00398   }
00399   return Next;
00400 }
00401 
00402 void SchedulePostRATDList::PrescanInstruction(MachineInstr *MI) {
00403   // Scan the register operands for this instruction and update
00404   // Classes and RegRefs.
00405   for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
00406     MachineOperand &MO = MI->getOperand(i);
00407     if (!MO.isReg()) continue;
00408     unsigned Reg = MO.getReg();
00409     if (Reg == 0) continue;
00410     const TargetRegisterClass *NewRC = 0;
00411     
00412     if (i < MI->getDesc().getNumOperands())
00413       NewRC = MI->getDesc().OpInfo[i].getRegClass(TRI);
00414 
00415     // For now, only allow the register to be changed if its register
00416     // class is consistent across all uses.
00417     if (!Classes[Reg] && NewRC)
00418       Classes[Reg] = NewRC;
00419     else if (!NewRC || Classes[Reg] != NewRC)
00420       Classes[Reg] = reinterpret_cast<TargetRegisterClass *>(-1);
00421 
00422     // Now check for aliases.
00423     for (const unsigned *Alias = TRI->getAliasSet(Reg); *Alias; ++Alias) {
00424       // If an alias of the reg is used during the live range, give up.
00425       // Note that this allows us to skip checking if AntiDepReg
00426       // overlaps with any of the aliases, among other things.
00427       unsigned AliasReg = *Alias;
00428       if (Classes[AliasReg]) {
00429         Classes[AliasReg] = reinterpret_cast<TargetRegisterClass *>(-1);
00430         Classes[Reg] = reinterpret_cast<TargetRegisterClass *>(-1);
00431       }
00432     }
00433 
00434     // If we're still willing to consider this register, note the reference.
00435     if (Classes[Reg] != reinterpret_cast<TargetRegisterClass *>(-1))
00436       RegRefs.insert(std::make_pair(Reg, &MO));
00437   }
00438 }
00439 
00440 void SchedulePostRATDList::ScanInstruction(MachineInstr *MI,
00441                                            unsigned Count) {
00442   // Update liveness.
00443   // Proceding upwards, registers that are defed but not used in this
00444   // instruction are now dead.
00445   for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
00446     MachineOperand &MO = MI->getOperand(i);
00447     if (!MO.isReg()) continue;
00448     unsigned Reg = MO.getReg();
00449     if (Reg == 0) continue;
00450     if (!MO.isDef()) continue;
00451     // Ignore two-addr defs.
00452     if (MI->isRegTiedToUseOperand(i)) continue;
00453 
00454     DefIndices[Reg] = Count;
00455     KillIndices[Reg] = ~0u;
00456           assert(((KillIndices[Reg] == ~0u) !=
00457                   (DefIndices[Reg] == ~0u)) &&
00458                "Kill and Def maps aren't consistent for Reg!");
00459     Classes[Reg] = 0;
00460     RegRefs.erase(Reg);
00461     // Repeat, for all subregs.
00462     for (const unsigned *Subreg = TRI->getSubRegisters(Reg);
00463          *Subreg; ++Subreg) {
00464       unsigned SubregReg = *Subreg;
00465       DefIndices[SubregReg] = Count;
00466       KillIndices[SubregReg] = ~0u;
00467       Classes[SubregReg] = 0;
00468       RegRefs.erase(SubregReg);
00469     }
00470     // Conservatively mark super-registers as unusable.
00471     for (const unsigned *Super = TRI->getSuperRegisters(Reg);
00472          *Super; ++Super) {
00473       unsigned SuperReg = *Super;
00474       Classes[SuperReg] = reinterpret_cast<TargetRegisterClass *>(-1);
00475     }
00476   }
00477   for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
00478     MachineOperand &MO = MI->getOperand(i);
00479     if (!MO.isReg()) continue;
00480     unsigned Reg = MO.getReg();
00481     if (Reg == 0) continue;
00482     if (!MO.isUse()) continue;
00483 
00484     const TargetRegisterClass *NewRC = 0;
00485     if (i < MI->getDesc().getNumOperands())
00486       NewRC = MI->getDesc().OpInfo[i].getRegClass(TRI);
00487 
00488     // For now, only allow the register to be changed if its register
00489     // class is consistent across all uses.
00490     if (!Classes[Reg] && NewRC)
00491       Classes[Reg] = NewRC;
00492     else if (!NewRC || Classes[Reg] != NewRC)
00493       Classes[Reg] = reinterpret_cast<TargetRegisterClass *>(-1);
00494 
00495     RegRefs.insert(std::make_pair(Reg, &MO));
00496 
00497     // It wasn't previously live but now it is, this is a kill.
00498     if (KillIndices[Reg] == ~0u) {
00499       KillIndices[Reg] = Count;
00500       DefIndices[Reg] = ~0u;
00501           assert(((KillIndices[Reg] == ~0u) !=
00502                   (DefIndices[Reg] == ~0u)) &&
00503                "Kill and Def maps aren't consistent for Reg!");
00504     }
00505     // Repeat, for all aliases.
00506     for (const unsigned *Alias = TRI->getAliasSet(Reg); *Alias; ++Alias) {
00507       unsigned AliasReg = *Alias;
00508       if (KillIndices[AliasReg] == ~0u) {
00509         KillIndices[AliasReg] = Count;
00510         DefIndices[AliasReg] = ~0u;
00511       }
00512     }
00513   }
00514 }
00515 
00516 unsigned
00517 SchedulePostRATDList::findSuitableFreeRegister(unsigned AntiDepReg,
00518                                                unsigned LastNewReg,
00519                                                const TargetRegisterClass *RC) {
00520   for (TargetRegisterClass::iterator R = RC->allocation_order_begin(MF),
00521        RE = RC->allocation_order_end(MF); R != RE; ++R) {
00522     unsigned NewReg = *R;
00523     // Don't replace a register with itself.
00524     if (NewReg == AntiDepReg) continue;
00525     // Don't replace a register with one that was recently used to repair
00526     // an anti-dependence with this AntiDepReg, because that would
00527     // re-introduce that anti-dependence.
00528     if (NewReg == LastNewReg) continue;
00529     // If NewReg is dead and NewReg's most recent def is not before
00530     // AntiDepReg's kill, it's safe to replace AntiDepReg with NewReg.
00531     assert(((KillIndices[AntiDepReg] == ~0u) != (DefIndices[AntiDepReg] == ~0u)) &&
00532            "Kill and Def maps aren't consistent for AntiDepReg!");
00533     assert(((KillIndices[NewReg] == ~0u) != (DefIndices[NewReg] == ~0u)) &&
00534            "Kill and Def maps aren't consistent for NewReg!");
00535     if (KillIndices[NewReg] != ~0u ||
00536         Classes[NewReg] == reinterpret_cast<TargetRegisterClass *>(-1) ||
00537         KillIndices[AntiDepReg] > DefIndices[NewReg])
00538       continue;
00539     return NewReg;
00540   }
00541 
00542   // No registers are free and available!
00543   return 0;
00544 }
00545 
00546 /// BreakAntiDependencies - Identifiy anti-dependencies along the critical path
00547 /// of the ScheduleDAG and break them by renaming registers.
00548 ///
00549 bool SchedulePostRATDList::BreakAntiDependencies() {
00550   // The code below assumes that there is at least one instruction,
00551   // so just duck out immediately if the block is empty.
00552   if (SUnits.empty()) return false;
00553 
00554   // Find the node at the bottom of the critical path.
00555   SUnit *Max = 0;
00556   for (unsigned i = 0, e = SUnits.size(); i != e; ++i) {
00557     SUnit *SU = &SUnits[i];
00558     if (!Max || SU->getDepth() + SU->Latency > Max->getDepth() + Max->Latency)
00559       Max = SU;
00560   }
00561 
00562   DEBUG(errs() << "Critical path has total latency "
00563         << (Max->getDepth() + Max->Latency) << "\n");
00564 
00565   // Track progress along the critical path through the SUnit graph as we walk
00566   // the instructions.
00567   SUnit *CriticalPathSU = Max;
00568   MachineInstr *CriticalPathMI = CriticalPathSU->getInstr();
00569 
00570   // Consider this pattern:
00571   //   A = ...
00572   //   ... = A
00573   //   A = ...
00574   //   ... = A
00575   //   A = ...
00576   //   ... = A
00577   //   A = ...
00578   //   ... = A
00579   // There are three anti-dependencies here, and without special care,
00580   // we'd break all of them using the same register:
00581   //   A = ...
00582   //   ... = A
00583   //   B = ...
00584   //   ... = B
00585   //   B = ...
00586   //   ... = B
00587   //   B = ...
00588   //   ... = B
00589   // because at each anti-dependence, B is the first register that
00590   // isn't A which is free.  This re-introduces anti-dependencies
00591   // at all but one of the original anti-dependencies that we were
00592   // trying to break.  To avoid this, keep track of the most recent
00593   // register that each register was replaced with, avoid
00594   // using it to repair an anti-dependence on the same register.
00595   // This lets us produce this:
00596   //   A = ...
00597   //   ... = A
00598   //   B = ...
00599   //   ... = B
00600   //   C = ...
00601   //   ... = C
00602   //   B = ...
00603   //   ... = B
00604   // This still has an anti-dependence on B, but at least it isn't on the
00605   // original critical path.
00606   //
00607   // TODO: If we tracked more than one register here, we could potentially
00608   // fix that remaining critical edge too. This is a little more involved,
00609   // because unlike the most recent register, less recent registers should
00610   // still be considered, though only if no other registers are available.
00611   unsigned LastNewReg[TargetRegisterInfo::FirstVirtualRegister] = {};
00612 
00613   // Attempt to break anti-dependence edges on the critical path. Walk the
00614   // instructions from the bottom up, tracking information about liveness
00615   // as we go to help determine which registers are available.
00616   bool Changed = false;
00617   unsigned Count = InsertPosIndex - 1;
00618   for (MachineBasicBlock::iterator I = InsertPos, E = Begin;
00619        I != E; --Count) {
00620     MachineInstr *MI = --I;
00621 
00622     // After regalloc, IMPLICIT_DEF instructions aren't safe to treat as
00623     // dependence-breaking. In the case of an INSERT_SUBREG, the IMPLICIT_DEF
00624     // is left behind appearing to clobber the super-register, while the
00625     // subregister needs to remain live. So we just ignore them.
00626     if (MI->getOpcode() == TargetInstrInfo::IMPLICIT_DEF)
00627       continue;
00628 
00629     // Check if this instruction has a dependence on the critical path that
00630     // is an anti-dependence that we may be able to break. If it is, set
00631     // AntiDepReg to the non-zero register associated with the anti-dependence.
00632     //
00633     // We limit our attention to the critical path as a heuristic to avoid
00634     // breaking anti-dependence edges that aren't going to significantly
00635     // impact the overall schedule. There are a limited number of registers
00636     // and we want to save them for the important edges.
00637     // 
00638     // TODO: Instructions with multiple defs could have multiple
00639     // anti-dependencies. The current code here only knows how to break one
00640     // edge per instruction. Note that we'd have to be able to break all of
00641     // the anti-dependencies in an instruction in order to be effective.
00642     unsigned AntiDepReg = 0;
00643     if (MI == CriticalPathMI) {
00644       if (SDep *Edge = CriticalPathStep(CriticalPathSU)) {
00645         SUnit *NextSU = Edge->getSUnit();
00646 
00647         // Only consider anti-dependence edges.
00648         if (Edge->getKind() == SDep::Anti) {
00649           AntiDepReg = Edge->getReg();
00650           assert(AntiDepReg != 0 && "Anti-dependence on reg0?");
00651           // Don't break anti-dependencies on non-allocatable registers.
00652           if (!AllocatableSet.test(AntiDepReg))
00653             AntiDepReg = 0;
00654           else {
00655             // If the SUnit has other dependencies on the SUnit that it
00656             // anti-depends on, don't bother breaking the anti-dependency
00657             // since those edges would prevent such units from being
00658             // scheduled past each other regardless.
00659             //
00660             // Also, if there are dependencies on other SUnits with the
00661             // same register as the anti-dependency, don't attempt to
00662             // break it.
00663             for (SUnit::pred_iterator P = CriticalPathSU->Preds.begin(),
00664                  PE = CriticalPathSU->Preds.end(); P != PE; ++P)
00665               if (P->getSUnit() == NextSU ?
00666                     (P->getKind() != SDep::Anti || P->getReg() != AntiDepReg) :
00667                     (P->getKind() == SDep::Data && P->getReg() == AntiDepReg)) {
00668                 AntiDepReg = 0;
00669                 break;
00670               }
00671           }
00672         }
00673         CriticalPathSU = NextSU;
00674         CriticalPathMI = CriticalPathSU->getInstr();
00675       } else {
00676         // We've reached the end of the critical path.
00677         CriticalPathSU = 0;
00678         CriticalPathMI = 0;
00679       }
00680     }
00681 
00682     PrescanInstruction(MI);
00683 
00684     // If this instruction has a use of AntiDepReg, breaking it
00685     // is invalid.
00686     for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
00687       MachineOperand &MO = MI->getOperand(i);
00688       if (!MO.isReg()) continue;
00689       unsigned Reg = MO.getReg();
00690       if (Reg == 0) continue;
00691       if (MO.isUse() && AntiDepReg == Reg) {
00692         AntiDepReg = 0;
00693         break;
00694       }
00695     }
00696 
00697     // Determine AntiDepReg's register class, if it is live and is
00698     // consistently used within a single class.
00699     const TargetRegisterClass *RC = AntiDepReg != 0 ? Classes[AntiDepReg] : 0;
00700     assert((AntiDepReg == 0 || RC != NULL) &&
00701            "Register should be live if it's causing an anti-dependence!");
00702     if (RC == reinterpret_cast<TargetRegisterClass *>(-1))
00703       AntiDepReg = 0;
00704 
00705     // Look for a suitable register to use to break the anti-depenence.
00706     //
00707     // TODO: Instead of picking the first free register, consider which might
00708     // be the best.
00709     if (AntiDepReg != 0) {
00710       if (unsigned NewReg = findSuitableFreeRegister(AntiDepReg,
00711                                                      LastNewReg[AntiDepReg],
00712                                                      RC)) {
00713         DEBUG(errs() << "Breaking anti-dependence edge on "
00714               << TRI->getName(AntiDepReg)
00715               << " with " << RegRefs.count(AntiDepReg) << " references"
00716               << " using " << TRI->getName(NewReg) << "!\n");
00717 
00718         // Update the references to the old register to refer to the new
00719         // register.
00720         std::pair<std::multimap<unsigned, MachineOperand *>::iterator,
00721                   std::multimap<unsigned, MachineOperand *>::iterator>
00722            Range = RegRefs.equal_range(AntiDepReg);
00723         for (std::multimap<unsigned, MachineOperand *>::iterator
00724              Q = Range.first, QE = Range.second; Q != QE; ++Q)
00725           Q->second->setReg(NewReg);
00726 
00727         // We just went back in time and modified history; the
00728         // liveness information for the anti-depenence reg is now
00729         // inconsistent. Set the state as if it were dead.
00730         Classes[NewReg] = Classes[AntiDepReg];
00731         DefIndices[NewReg] = DefIndices[AntiDepReg];
00732         KillIndices[NewReg] = KillIndices[AntiDepReg];
00733         assert(((KillIndices[NewReg] == ~0u) !=
00734                 (DefIndices[NewReg] == ~0u)) &&
00735              "Kill and Def maps aren't consistent for NewReg!");
00736 
00737         Classes[AntiDepReg] = 0;
00738         DefIndices[AntiDepReg] = KillIndices[AntiDepReg];
00739         KillIndices[AntiDepReg] = ~0u;
00740         assert(((KillIndices[AntiDepReg] == ~0u) !=
00741                 (DefIndices[AntiDepReg] == ~0u)) &&
00742              "Kill and Def maps aren't consistent for AntiDepReg!");
00743 
00744         RegRefs.erase(AntiDepReg);
00745         Changed = true;
00746         LastNewReg[AntiDepReg] = NewReg;
00747       }
00748     }
00749 
00750     ScanInstruction(MI, Count);
00751   }
00752 
00753   return Changed;
00754 }
00755 
00756 //===----------------------------------------------------------------------===//
00757 //  Top-Down Scheduling
00758 //===----------------------------------------------------------------------===//
00759 
00760 /// ReleaseSucc - Decrement the NumPredsLeft count of a successor. Add it to
00761 /// the PendingQueue if the count reaches zero. Also update its cycle bound.
00762 void SchedulePostRATDList::ReleaseSucc(SUnit *SU, SDep *SuccEdge) {
00763   SUnit *SuccSU = SuccEdge->getSUnit();
00764   --SuccSU->NumPredsLeft;
00765   
00766 #ifndef NDEBUG
00767   if (SuccSU->NumPredsLeft < 0) {
00768     cerr << "*** Scheduling failed! ***\n";
00769     SuccSU->dump(this);
00770     cerr << " has been released too many times!\n";
00771     llvm_unreachable(0);
00772   }
00773 #endif
00774   
00775   // Compute how many cycles it will be before this actually becomes
00776   // available.  This is the max of the start time of all predecessors plus
00777   // their latencies.
00778   SuccSU->setDepthToAtLeast(SU->getDepth() + SuccEdge->getLatency());
00779   
00780   // If all the node's predecessors are scheduled, this node is ready
00781   // to be scheduled. Ignore the special ExitSU node.
00782   if (SuccSU->NumPredsLeft == 0 && SuccSU != &ExitSU)
00783     PendingQueue.push_back(SuccSU);
00784 }
00785 
00786 /// ReleaseSuccessors - Call ReleaseSucc on each of SU's successors.
00787 void SchedulePostRATDList::ReleaseSuccessors(SUnit *SU) {
00788   for (SUnit::succ_iterator I = SU->Succs.begin(), E = SU->Succs.end();
00789        I != E; ++I)
00790     ReleaseSucc(SU, &*I);
00791 }
00792 
00793 /// ScheduleNodeTopDown - Add the node to the schedule. Decrement the pending
00794 /// count of its successors. If a successor pending count is zero, add it to
00795 /// the Available queue.
00796 void SchedulePostRATDList::ScheduleNodeTopDown(SUnit *SU, unsigned CurCycle) {
00797   DEBUG(errs() << "*** Scheduling [" << CurCycle << "]: ");
00798   DEBUG(SU->dump(this));
00799   
00800   Sequence.push_back(SU);
00801   assert(CurCycle >= SU->getDepth() && "Node scheduled above its depth!");
00802   SU->setDepthToAtLeast(CurCycle);
00803 
00804   ReleaseSuccessors(SU);
00805   SU->isScheduled = true;
00806   AvailableQueue.ScheduledNode(SU);
00807 }
00808 
00809 /// ListScheduleTopDown - The main loop of list scheduling for top-down
00810 /// schedulers.
00811 void SchedulePostRATDList::ListScheduleTopDown() {
00812   unsigned CurCycle = 0;
00813 
00814   // Release any successors of the special Entry node.
00815   ReleaseSuccessors(&EntrySU);
00816 
00817   // All leaves to Available queue.
00818   for (unsigned i = 0, e = SUnits.size(); i != e; ++i) {
00819     // It is available if it has no predecessors.
00820     if (SUnits[i].Preds.empty()) {
00821       AvailableQueue.push(&SUnits[i]);
00822       SUnits[i].isAvailable = true;
00823     }
00824   }
00825 
00826   // In any cycle where we can't schedule any instructions, we must
00827   // stall or emit a noop, depending on the target.
00828   bool CycleInstCnt = 0;
00829 
00830   // While Available queue is not empty, grab the node with the highest
00831   // priority. If it is not ready put it back.  Schedule the node.
00832   std::vector<SUnit*> NotReady;
00833   Sequence.reserve(SUnits.size());
00834   while (!AvailableQueue.empty() || !PendingQueue.empty()) {
00835     // Check to see if any of the pending instructions are ready to issue.  If
00836     // so, add them to the available queue.
00837     unsigned MinDepth = ~0u;
00838     for (unsigned i = 0, e = PendingQueue.size(); i != e; ++i) {
00839       if (PendingQueue[i]->getDepth() <= CurCycle) {
00840         AvailableQueue.push(PendingQueue[i]);
00841         PendingQueue[i]->isAvailable = true;
00842         PendingQueue[i] = PendingQueue.back();
00843         PendingQueue.pop_back();
00844         --i; --e;
00845       } else if (PendingQueue[i]->getDepth() < MinDepth)
00846         MinDepth = PendingQueue[i]->getDepth();
00847     }
00848 
00849     DEBUG(errs() << "\n*** Examining Available\n";
00850           LatencyPriorityQueue q = AvailableQueue;
00851           while (!q.empty()) {
00852             SUnit *su = q.pop();
00853             errs() << "Height " << su->getHeight() << ": ";
00854             su->dump(this);
00855           });
00856 
00857     SUnit *FoundSUnit = 0;
00858 
00859     bool HasNoopHazards = false;
00860     while (!AvailableQueue.empty()) {
00861       SUnit *CurSUnit = AvailableQueue.pop();
00862 
00863       ScheduleHazardRecognizer::HazardType HT =
00864         HazardRec->getHazardType(CurSUnit);
00865       if (HT == ScheduleHazardRecognizer::NoHazard) {
00866         FoundSUnit = CurSUnit;
00867         break;
00868       }
00869 
00870       // Remember if this is a noop hazard.
00871       HasNoopHazards |= HT == ScheduleHazardRecognizer::NoopHazard;
00872 
00873       NotReady.push_back(CurSUnit);
00874     }
00875 
00876     // Add the nodes that aren't ready back onto the available list.
00877     if (!NotReady.empty()) {
00878       AvailableQueue.push_all(NotReady);
00879       NotReady.clear();
00880     }
00881 
00882     // If we found a node to schedule, do it now.
00883     if (FoundSUnit) {
00884       ScheduleNodeTopDown(FoundSUnit, CurCycle);
00885       HazardRec->EmitInstruction(FoundSUnit);
00886       CycleInstCnt++;
00887 
00888       // If we are using the target-specific hazards, then don't
00889       // advance the cycle time just because we schedule a node. If
00890       // the target allows it we can schedule multiple nodes in the
00891       // same cycle.
00892       if (!EnablePostRAHazardAvoidance) {
00893         if (FoundSUnit->Latency)  // Don't increment CurCycle for pseudo-ops!
00894           ++CurCycle;
00895       }
00896     } else {
00897       if (CycleInstCnt > 0) {
00898         DEBUG(errs() << "*** Finished cycle " << CurCycle << '\n');
00899         HazardRec->AdvanceCycle();
00900       } else if (!HasNoopHazards) {
00901         // Otherwise, we have a pipeline stall, but no other problem,
00902         // just advance the current cycle and try again.
00903         DEBUG(errs() << "*** Stall in cycle " << CurCycle << '\n');
00904         HazardRec->AdvanceCycle();
00905         ++NumStalls;
00906       } else {
00907         // Otherwise, we have no instructions to issue and we have instructions
00908         // that will fault if we don't do this right.  This is the case for
00909         // processors without pipeline interlocks and other cases.
00910         DEBUG(errs() << "*** Emitting noop in cycle " << CurCycle << '\n');
00911         HazardRec->EmitNoop();
00912         Sequence.push_back(0);   // NULL here means noop
00913         ++NumNoops;
00914       }
00915 
00916       ++CurCycle;
00917       CycleInstCnt = 0;
00918     }
00919   }
00920 
00921 #ifndef NDEBUG
00922   VerifySchedule(/*isBottomUp=*/false);
00923 #endif
00924 }
00925 
00926 //===----------------------------------------------------------------------===//
00927 //                         Public Constructor Functions
00928 //===----------------------------------------------------------------------===//
00929 
00930 FunctionPass *llvm::createPostRAScheduler() {
00931   return new PostRAScheduler();
00932 }