Target/AMDGPU/GCNSchedStrategy.cpp

//===-- GCNSchedStrategy.cpp - GCN Scheduler Strategy ---------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
/// \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) { }

static unsigned getMaxWaves(unsigned SGPRs, unsigned VGPRs,
                            const MachineFunction &MF) {

  const SISubtarget &ST = MF.getSubtarget<SISubtarget>();
  const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
  unsigned MinRegOccupancy = std::min(ST.getOccupancyWithNumSGPRs(SGPRs),
                                      ST.getOccupancyWithNumVGPRs(VGPRs));
  return std::min(MinRegOccupancy,
                  ST.getOccupancyWithLocalMemSize(MFI->getLDSSize(),
                                                  MF.getFunction()));
}

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

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

  MF = &DAG->MF;

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

  // 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<SISubtarget>()),
  MFI(*MF.getInfo<SIMachineFunctionInfo>()),
  StartingOccupancy(std::min(ST.getOccupancyWithLocalMemSize(MFI.getLDSSize(),
                                                             MF.getFunction()),
                             MFI.getMaxWavesPerEU())),
  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 WavesAfter = getMaxWaves(PressureAfter.getSGPRNum(),
                                    PressureAfter.getVGPRNum(), MF);
  unsigned WavesBefore = getMaxWaves(PressureBefore.getSGPRNum(),
                                     PressureBefore.getVGPRNum(), MF);
  WavesAfter = std::min(WavesAfter, MFI.getMaxWavesPerEU());
  WavesBefore = std::min(WavesBefore, MFI.getMaxWavesPerEU());
  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);
  if (NewOccupancy < MinOccupancy) {
    MinOccupancy = NewOccupancy;
    LLVM_DEBUG(dbgs() << "Occupancy lowered for the function to "
                      << MinOccupancy << ".\n");
  }

  if (WavesAfter >= WavesBefore) {
    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 {
    I = Regions[CurRegion].first;
    RPTracker.reset(*I);
  }

  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();
  }
}

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());

  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);
}