diff options
| author | Philip Pfaffe <philip.pfaffe@gmail.com> | 2017-05-12 14:37:29 +0000 |
|---|---|---|
| committer | Philip Pfaffe <philip.pfaffe@gmail.com> | 2017-05-12 14:37:29 +0000 |
| commit | 5cc87e3ab3912a601fa33c7019f4284d141cee19 (patch) | |
| tree | 16e10fe8c44adcccf5889990d4b7b9cbc2331270 /polly/lib/Analysis/ScopDetection.cpp | |
| parent | b0fdf57543253fec07a9d315b3cea71e87b513ba (diff) | |
| download | bcm5719-llvm-5cc87e3ab3912a601fa33c7019f4284d141cee19.tar.gz bcm5719-llvm-5cc87e3ab3912a601fa33c7019f4284d141cee19.zip | |
[Polly][NewPM] Port ScopDetection to the new PassManager
Summary: This is a proof of concept of how to port polly-passes to the new PassManager architecture. This approach works ootb for Function-Passes, but might not be directly applicable to Scop/Region-Passes. While we could just run the Analyses/Transforms over functions instead, we'd surrender the nice pipelining behaviour we have now.
Reviewers: Meinersbur, grosser
Reviewed By: grosser
Subscribers: pollydev, sanjoy, nemanjai, llvm-commits
Tags: #polly
Differential Revision: https://reviews.llvm.org/D31459
llvm-svn: 302902
Diffstat (limited to 'polly/lib/Analysis/ScopDetection.cpp')
| -rw-r--r-- | polly/lib/Analysis/ScopDetection.cpp | 297 |
1 files changed, 162 insertions, 135 deletions
diff --git a/polly/lib/Analysis/ScopDetection.cpp b/polly/lib/Analysis/ScopDetection.cpp index 0e8e0efbeaf..b8df3940a24 100644 --- a/polly/lib/Analysis/ScopDetection.cpp +++ b/polly/lib/Analysis/ScopDetection.cpp @@ -225,6 +225,9 @@ STATISTIC(MaxNumLoopsInScop, "Maximal number of loops in scops"); STATISTIC(MaxNumLoopsInProfScop, "Maximal number of loops in scops (profitable scops only)"); +static void updateLoopCountStatistic(ScopDetection::LoopStats Stats, + bool OnlyProfitable); + class DiagnosticScopFound : public DiagnosticInfo { private: static int PluginDiagnosticKind; @@ -266,10 +269,55 @@ void DiagnosticScopFound::print(DiagnosticPrinter &DP) const { //===----------------------------------------------------------------------===// // ScopDetection. -ScopDetection::ScopDetection() : FunctionPass(ID) { - // Disable runtime alias checks if we ignore aliasing all together. - if (IgnoreAliasing) - PollyUseRuntimeAliasChecks = false; +ScopDetection::ScopDetection(Function &F, const DominatorTree &DT, + ScalarEvolution &SE, LoopInfo &LI, RegionInfo &RI, + AliasAnalysis &AA) + : DT(DT), SE(SE), LI(LI), RI(RI), AA(AA) { + + if (!PollyProcessUnprofitable && LI.empty()) + return; + + Region *TopRegion = RI.getTopLevelRegion(); + + if (OnlyFunction != "" && !F.getName().count(OnlyFunction)) + return; + + if (!isValidFunction(F)) + return; + + findScops(*TopRegion); + + NumScopRegions += ValidRegions.size(); + + // Prune non-profitable regions. + for (auto &DIt : DetectionContextMap) { + auto &DC = DIt.getSecond(); + if (DC.Log.hasErrors()) + continue; + if (!ValidRegions.count(&DC.CurRegion)) + continue; + LoopStats Stats = countBeneficialLoops(&DC.CurRegion, SE, LI, 0); + updateLoopCountStatistic(Stats, false /* OnlyProfitable */); + if (isProfitableRegion(DC)) { + updateLoopCountStatistic(Stats, true /* OnlyProfitable */); + continue; + } + + ValidRegions.remove(&DC.CurRegion); + } + + NumProfScopRegions += ValidRegions.size(); + NumLoopsOverall += countBeneficialLoops(TopRegion, SE, LI, 0).NumLoops; + + // Only makes sense when we tracked errors. + if (PollyTrackFailures) + emitMissedRemarks(F); + + if (ReportLevel) + printLocations(F); + + assert(ValidRegions.size() <= DetectionContextMap.size() && + "Cached more results than valid regions"); } template <class RR, typename... Args> @@ -300,7 +348,7 @@ bool ScopDetection::isMaxRegionInScop(const Region &R, bool Verify) const { DetectionContextMap.erase(getBBPairForRegion(&R)); const auto &It = DetectionContextMap.insert(std::make_pair( getBBPairForRegion(&R), - DetectionContext(const_cast<Region &>(R), *AA, false /*verifying*/))); + DetectionContext(const_cast<Region &>(R), AA, false /*verifying*/))); DetectionContext &Context = It.first->second; return isValidRegion(Context); } @@ -333,7 +381,7 @@ bool ScopDetection::addOverApproximatedRegion(Region *AR, // are accesses that depend on the iteration count. for (BasicBlock *BB : AR->blocks()) { - Loop *L = LI->getLoopFor(BB); + Loop *L = LI.getLoopFor(BB); if (AR->contains(L)) Context.BoxedLoopsSet.insert(L); } @@ -358,7 +406,7 @@ bool ScopDetection::onlyValidRequiredInvariantLoads( if (Context.RequiredILS.count(Load)) continue; - if (!isHoistableLoad(Load, CurRegion, *LI, *SE, *DT)) + if (!isHoistableLoad(Load, CurRegion, LI, SE, DT)) return false; for (auto NonAffineRegion : Context.NonAffineSubRegionSet) { @@ -381,9 +429,9 @@ bool ScopDetection::onlyValidRequiredInvariantLoads( bool ScopDetection::involvesMultiplePtrs(const SCEV *S0, const SCEV *S1, Loop *Scope) const { SetVector<Value *> Values; - findValues(S0, *SE, Values); + findValues(S0, SE, Values); if (S1) - findValues(S1, *SE, Values); + findValues(S1, SE, Values); SmallPtrSet<Value *, 8> PtrVals; for (auto *V : Values) { @@ -393,18 +441,18 @@ bool ScopDetection::involvesMultiplePtrs(const SCEV *S0, const SCEV *S1, if (!V->getType()->isPointerTy()) continue; - auto *PtrSCEV = SE->getSCEVAtScope(V, Scope); + auto *PtrSCEV = SE.getSCEVAtScope(V, Scope); if (isa<SCEVConstant>(PtrSCEV)) continue; - auto *BasePtr = dyn_cast<SCEVUnknown>(SE->getPointerBase(PtrSCEV)); + auto *BasePtr = dyn_cast<SCEVUnknown>(SE.getPointerBase(PtrSCEV)); if (!BasePtr) return true; auto *BasePtrVal = BasePtr->getValue(); if (PtrVals.insert(BasePtrVal).second) { for (auto *PtrVal : PtrVals) - if (PtrVal != BasePtrVal && !AA->isNoAlias(PtrVal, BasePtrVal)) + if (PtrVal != BasePtrVal && !AA.isNoAlias(PtrVal, BasePtrVal)) return true; } } @@ -416,7 +464,7 @@ bool ScopDetection::isAffine(const SCEV *S, Loop *Scope, DetectionContext &Context) const { InvariantLoadsSetTy AccessILS; - if (!isAffineExpr(&Context.CurRegion, Scope, S, *SE, &AccessILS)) + if (!isAffineExpr(&Context.CurRegion, Scope, S, SE, &AccessILS)) return false; if (!onlyValidRequiredInvariantLoads(AccessILS, Context)) @@ -428,8 +476,8 @@ bool ScopDetection::isAffine(const SCEV *S, Loop *Scope, bool ScopDetection::isValidSwitch(BasicBlock &BB, SwitchInst *SI, Value *Condition, bool IsLoopBranch, DetectionContext &Context) const { - Loop *L = LI->getLoopFor(&BB); - const SCEV *ConditionSCEV = SE->getSCEVAtScope(Condition, L); + Loop *L = LI.getLoopFor(&BB); + const SCEV *ConditionSCEV = SE.getSCEVAtScope(Condition, L); if (IsLoopBranch && L->isLoopLatch(&BB)) return false; @@ -442,7 +490,7 @@ bool ScopDetection::isValidSwitch(BasicBlock &BB, SwitchInst *SI, return true; if (AllowNonAffineSubRegions && - addOverApproximatedRegion(RI->getRegionFor(&BB), Context)) + addOverApproximatedRegion(RI.getRegionFor(&BB), Context)) return true; return invalid<ReportNonAffBranch>(Context, /*Assert=*/true, &BB, @@ -470,7 +518,7 @@ bool ScopDetection::isValidBranch(BasicBlock &BB, BranchInst *BI, // Non constant conditions of branches need to be ICmpInst. if (!isa<ICmpInst>(Condition)) { if (!IsLoopBranch && AllowNonAffineSubRegions && - addOverApproximatedRegion(RI->getRegionFor(&BB), Context)) + addOverApproximatedRegion(RI.getRegionFor(&BB), Context)) return true; return invalid<ReportInvalidCond>(Context, /*Assert=*/true, BI, &BB); } @@ -482,14 +530,14 @@ bool ScopDetection::isValidBranch(BasicBlock &BB, BranchInst *BI, isa<UndefValue>(ICmp->getOperand(1))) return invalid<ReportUndefOperand>(Context, /*Assert=*/true, &BB, ICmp); - Loop *L = LI->getLoopFor(&BB); - const SCEV *LHS = SE->getSCEVAtScope(ICmp->getOperand(0), L); - const SCEV *RHS = SE->getSCEVAtScope(ICmp->getOperand(1), L); + Loop *L = LI.getLoopFor(&BB); + const SCEV *LHS = SE.getSCEVAtScope(ICmp->getOperand(0), L); + const SCEV *RHS = SE.getSCEVAtScope(ICmp->getOperand(1), L); // If unsigned operations are not allowed try to approximate the region. if (ICmp->isUnsigned() && !PollyAllowUnsignedOperations) return !IsLoopBranch && AllowNonAffineSubRegions && - addOverApproximatedRegion(RI->getRegionFor(&BB), Context); + addOverApproximatedRegion(RI.getRegionFor(&BB), Context); // Check for invalid usage of different pointers in one expression. if (ICmp->isEquality() && involvesMultiplePtrs(LHS, nullptr, L) && @@ -504,7 +552,7 @@ bool ScopDetection::isValidBranch(BasicBlock &BB, BranchInst *BI, return true; if (!IsLoopBranch && AllowNonAffineSubRegions && - addOverApproximatedRegion(RI->getRegionFor(&BB), Context)) + addOverApproximatedRegion(RI.getRegionFor(&BB), Context)) return true; if (IsLoopBranch) @@ -565,7 +613,7 @@ bool ScopDetection::isValidCallInst(CallInst &CI, return false; if (AllowModrefCall) { - switch (AA->getModRefBehavior(CalledFunction)) { + switch (AA.getModRefBehavior(CalledFunction)) { case FMRB_UnknownModRefBehavior: return false; case FMRB_DoesNotAccessMemory: @@ -583,11 +631,11 @@ bool ScopDetection::isValidCallInst(CallInst &CI, // Bail if a pointer argument has a base address not known to // ScalarEvolution. Note that a zero pointer is acceptable. - auto *ArgSCEV = SE->getSCEVAtScope(Arg, LI->getLoopFor(CI.getParent())); + auto *ArgSCEV = SE.getSCEVAtScope(Arg, LI.getLoopFor(CI.getParent())); if (ArgSCEV->isZero()) continue; - auto *BP = dyn_cast<SCEVUnknown>(SE->getPointerBase(ArgSCEV)); + auto *BP = dyn_cast<SCEVUnknown>(SE.getPointerBase(ArgSCEV)); if (!BP) return false; @@ -614,7 +662,7 @@ bool ScopDetection::isValidIntrinsicInst(IntrinsicInst &II, return true; // The closest loop surrounding the call instruction. - Loop *L = LI->getLoopFor(II.getParent()); + Loop *L = LI.getLoopFor(II.getParent()); // The access function and base pointer for memory intrinsics. const SCEV *AF; @@ -624,25 +672,25 @@ bool ScopDetection::isValidIntrinsicInst(IntrinsicInst &II, // Memory intrinsics that can be represented are supported. case llvm::Intrinsic::memmove: case llvm::Intrinsic::memcpy: - AF = SE->getSCEVAtScope(cast<MemTransferInst>(II).getSource(), L); + AF = SE.getSCEVAtScope(cast<MemTransferInst>(II).getSource(), L); if (!AF->isZero()) { - BP = dyn_cast<SCEVUnknown>(SE->getPointerBase(AF)); + BP = dyn_cast<SCEVUnknown>(SE.getPointerBase(AF)); // Bail if the source pointer is not valid. if (!isValidAccess(&II, AF, BP, Context)) return false; } // Fall through case llvm::Intrinsic::memset: - AF = SE->getSCEVAtScope(cast<MemIntrinsic>(II).getDest(), L); + AF = SE.getSCEVAtScope(cast<MemIntrinsic>(II).getDest(), L); if (!AF->isZero()) { - BP = dyn_cast<SCEVUnknown>(SE->getPointerBase(AF)); + BP = dyn_cast<SCEVUnknown>(SE.getPointerBase(AF)); // Bail if the destination pointer is not valid. if (!isValidAccess(&II, AF, BP, Context)) return false; } // Bail if the length is not affine. - if (!isAffine(SE->getSCEVAtScope(cast<MemIntrinsic>(II).getLength(), L), L, + if (!isAffine(SE.getSCEVAtScope(cast<MemIntrinsic>(II).getLength(), L), L, Context)) return false; @@ -722,7 +770,7 @@ ScopDetection::getDelinearizationTerms(DetectionContext &Context, SmallVector<const SCEV *, 4> Terms; for (const auto &Pair : Context.Accesses[BasePointer]) { std::vector<const SCEV *> MaxTerms; - SCEVRemoveMax::rewrite(Pair.second, *SE, &MaxTerms); + SCEVRemoveMax::rewrite(Pair.second, SE, &MaxTerms); if (MaxTerms.size() > 0) { Terms.insert(Terms.begin(), MaxTerms.begin(), MaxTerms.end()); continue; @@ -738,7 +786,7 @@ ScopDetection::getDelinearizationTerms(DetectionContext &Context, if (auto *AF = dyn_cast<SCEVAddExpr>(Pair.second)) { for (auto Op : AF->operands()) { if (auto *AF2 = dyn_cast<SCEVAddRecExpr>(Op)) - SE->collectParametricTerms(AF2, Terms); + SE.collectParametricTerms(AF2, Terms); if (auto *AF2 = dyn_cast<SCEVMulExpr>(Op)) { SmallVector<const SCEV *, 0> Operands; @@ -756,12 +804,12 @@ ScopDetection::getDelinearizationTerms(DetectionContext &Context, } } if (Operands.size()) - Terms.push_back(SE->getMulExpr(Operands)); + Terms.push_back(SE.getMulExpr(Operands)); } } } if (Terms.empty()) - SE->collectParametricTerms(Pair.second, Terms); + SE.collectParametricTerms(Pair.second, Terms); } return Terms; } @@ -781,7 +829,7 @@ bool ScopDetection::hasValidArraySizes(DetectionContext &Context, auto *V = dyn_cast<Value>(Unknown->getValue()); if (auto *Load = dyn_cast<LoadInst>(V)) { if (Context.CurRegion.contains(Load) && - isHoistableLoad(Load, CurRegion, *LI, *SE, *DT)) + isHoistableLoad(Load, CurRegion, LI, SE, DT)) Context.RequiredILS.insert(Load); continue; } @@ -828,11 +876,11 @@ bool ScopDetection::computeAccessFunctions( for (const auto &Pair : Context.Accesses[BasePointer]) { const Instruction *Insn = Pair.first; auto *AF = Pair.second; - AF = SCEVRemoveMax::rewrite(AF, *SE); + AF = SCEVRemoveMax::rewrite(AF, SE); bool IsNonAffine = false; TempMemoryAccesses.insert(std::make_pair(Insn, MemAcc(Insn, Shape))); MemAcc *Acc = &TempMemoryAccesses.find(Insn)->second; - auto *Scope = LI->getLoopFor(Insn->getParent()); + auto *Scope = LI.getLoopFor(Insn->getParent()); if (!AF) { if (isAffine(Pair.second, Scope, Context)) @@ -840,8 +888,8 @@ bool ScopDetection::computeAccessFunctions( else IsNonAffine = true; } else { - SE->computeAccessFunctions(AF, Acc->DelinearizedSubscripts, - Shape->DelinearizedSizes); + SE.computeAccessFunctions(AF, Acc->DelinearizedSubscripts, + Shape->DelinearizedSizes); if (Acc->DelinearizedSubscripts.size() == 0) IsNonAffine = true; for (const SCEV *S : Acc->DelinearizedSubscripts) @@ -874,8 +922,8 @@ bool ScopDetection::hasBaseAffineAccesses(DetectionContext &Context, auto Terms = getDelinearizationTerms(Context, BasePointer); - SE->findArrayDimensions(Terms, Shape->DelinearizedSizes, - Context.ElementSize[BasePointer]); + SE.findArrayDimensions(Terms, Shape->DelinearizedSizes, + Context.ElementSize[BasePointer]); if (!hasValidArraySizes(Context, Shape->DelinearizedSizes, BasePointer, Scope)) @@ -923,15 +971,15 @@ bool ScopDetection::isValidAccess(Instruction *Inst, const SCEV *AF, if (!isInvariant(*BV, Context.CurRegion, Context)) return invalid<ReportVariantBasePtr>(Context, /*Assert=*/true, BV, Inst); - AF = SE->getMinusSCEV(AF, BP); + AF = SE.getMinusSCEV(AF, BP); const SCEV *Size; if (!isa<MemIntrinsic>(Inst)) { - Size = SE->getElementSize(Inst); + Size = SE.getElementSize(Inst); } else { auto *SizeTy = - SE->getEffectiveSCEVType(PointerType::getInt8PtrTy(SE->getContext())); - Size = SE->getConstant(SizeTy, 8); + SE.getEffectiveSCEVType(PointerType::getInt8PtrTy(SE.getContext())); + Size = SE.getConstant(SizeTy, 8); } if (Context.ElementSize[BP]) { @@ -939,7 +987,7 @@ bool ScopDetection::isValidAccess(Instruction *Inst, const SCEV *AF, return invalid<ReportDifferentArrayElementSize>(Context, /*Assert=*/true, Inst, BV); - Context.ElementSize[BP] = SE->getSMinExpr(Size, Context.ElementSize[BP]); + Context.ElementSize[BP] = SE.getSMinExpr(Size, Context.ElementSize[BP]); } else { Context.ElementSize[BP] = Size; } @@ -951,7 +999,7 @@ bool ScopDetection::isValidAccess(Instruction *Inst, const SCEV *AF, if (Context.BoxedLoopsSet.count(L)) IsVariantInNonAffineLoop = true; - auto *Scope = LI->getLoopFor(Inst->getParent()); + auto *Scope = LI.getLoopFor(Inst->getParent()); bool IsAffine = !IsVariantInNonAffineLoop && isAffine(AF, Scope, Context); // Do not try to delinearize memory intrinsics and force them to be affine. if (isa<MemIntrinsic>(Inst) && !IsAffine) { @@ -962,7 +1010,7 @@ bool ScopDetection::isValidAccess(Instruction *Inst, const SCEV *AF, if (!IsAffine) Context.NonAffineAccesses.insert( - std::make_pair(BP, LI->getLoopFor(Inst->getParent()))); + std::make_pair(BP, LI.getLoopFor(Inst->getParent()))); } else if (!AllowNonAffine && !IsAffine) { return invalid<ReportNonAffineAccess>(Context, /*Assert=*/true, AF, Inst, BV); @@ -990,7 +1038,7 @@ bool ScopDetection::isValidAccess(Instruction *Inst, const SCEV *AF, Instruction *Inst = dyn_cast<Instruction>(Ptr.getValue()); if (Inst && Context.CurRegion.contains(Inst)) { auto *Load = dyn_cast<LoadInst>(Inst); - if (Load && isHoistableLoad(Load, Context.CurRegion, *LI, *SE, *DT)) { + if (Load && isHoistableLoad(Load, Context.CurRegion, LI, SE, DT)) { Context.RequiredILS.insert(Load); continue; } @@ -1012,11 +1060,11 @@ bool ScopDetection::isValidAccess(Instruction *Inst, const SCEV *AF, bool ScopDetection::isValidMemoryAccess(MemAccInst Inst, DetectionContext &Context) const { Value *Ptr = Inst.getPointerOperand(); - Loop *L = LI->getLoopFor(Inst->getParent()); - const SCEV *AccessFunction = SE->getSCEVAtScope(Ptr, L); + Loop *L = LI.getLoopFor(Inst->getParent()); + const SCEV *AccessFunction = SE.getSCEVAtScope(Ptr, L); const SCEVUnknown *BasePointer; - BasePointer = dyn_cast<SCEVUnknown>(SE->getPointerBase(AccessFunction)); + BasePointer = dyn_cast<SCEVUnknown>(SE.getPointerBase(AccessFunction)); return isValidAccess(Inst, AccessFunction, BasePointer, Context); } @@ -1029,7 +1077,7 @@ bool ScopDetection::isValidInstruction(Instruction &Inst, if (!OpInst) continue; - if (isErrorBlock(*OpInst->getParent(), Context.CurRegion, *LI, *DT)) + if (isErrorBlock(*OpInst->getParent(), Context.CurRegion, LI, DT)) return false; } @@ -1130,7 +1178,7 @@ bool ScopDetection::isValidLoop(Loop *L, DetectionContext &Context) const { return true; if (AllowNonAffineSubLoops && AllowNonAffineSubRegions) { - Region *R = RI->getRegionFor(L->getHeader()); + Region *R = RI.getRegionFor(L->getHeader()); while (R != &Context.CurRegion && !R->contains(L)) R = R->getParent(); @@ -1138,7 +1186,7 @@ bool ScopDetection::isValidLoop(Loop *L, DetectionContext &Context) const { return true; } - const SCEV *LoopCount = SE->getBackedgeTakenCount(L); + const SCEV *LoopCount = SE.getBackedgeTakenCount(L); return invalid<ReportLoopBound>(Context, /*Assert=*/true, L, LoopCount); } @@ -1199,7 +1247,7 @@ Region *ScopDetection::expandRegion(Region &R) { while (ExpandedRegion) { const auto &It = DetectionContextMap.insert(std::make_pair( getBBPairForRegion(ExpandedRegion.get()), - DetectionContext(*ExpandedRegion, *AA, false /*verifying*/))); + DetectionContext(*ExpandedRegion, AA, false /*verifying*/))); DetectionContext &Context = It.first->second; DEBUG(dbgs() << "\t\tTrying " << ExpandedRegion->getNameStr() << "\n"); // Only expand when we did not collect errors. @@ -1244,9 +1292,9 @@ Region *ScopDetection::expandRegion(Region &R) { return LastValidRegion.release(); } -static bool regionWithoutLoops(Region &R, LoopInfo *LI) { +static bool regionWithoutLoops(Region &R, LoopInfo &LI) { for (const BasicBlock *BB : R.blocks()) - if (R.contains(LI->getLoopFor(BB))) + if (R.contains(LI.getLoopFor(BB))) return false; return true; @@ -1267,7 +1315,7 @@ void ScopDetection::removeCachedResults(const Region &R) { void ScopDetection::findScops(Region &R) { const auto &It = DetectionContextMap.insert(std::make_pair( - getBBPairForRegion(&R), DetectionContext(R, *AA, false /*verifying*/))); + getBBPairForRegion(&R), DetectionContext(R, AA, false /*verifying*/))); DetectionContext &Context = It.first->second; bool RegionIsValid = false; @@ -1326,14 +1374,14 @@ bool ScopDetection::allBlocksValid(DetectionContext &Context) const { Region &CurRegion = Context.CurRegion; for (const BasicBlock *BB : CurRegion.blocks()) { - Loop *L = LI->getLoopFor(BB); + Loop *L = LI.getLoopFor(BB); if (L && L->getHeader() == BB && CurRegion.contains(L) && (!isValidLoop(L, Context) && !KeepGoing)) return false; } for (BasicBlock *BB : CurRegion.blocks()) { - bool IsErrorBlock = isErrorBlock(*BB, CurRegion, *LI, *DT); + bool IsErrorBlock = isErrorBlock(*BB, CurRegion, LI, DT); // Also check exception blocks (and possibly register them as non-affine // regions). Even though exception blocks are not modeled, we use them @@ -1363,7 +1411,7 @@ bool ScopDetection::hasSufficientCompute(DetectionContext &Context, return false; for (auto *BB : Context.CurRegion.blocks()) - if (Context.CurRegion.contains(LI->getLoopFor(BB))) + if (Context.CurRegion.contains(LI.getLoopFor(BB))) InstCount += BB->size(); InstCount = InstCount / NumLoops; @@ -1374,7 +1422,7 @@ bool ScopDetection::hasSufficientCompute(DetectionContext &Context, bool ScopDetection::hasPossiblyDistributableLoop( DetectionContext &Context) const { for (auto *BB : Context.CurRegion.blocks()) { - auto *L = LI->getLoopFor(BB); + auto *L = LI.getLoopFor(BB); if (!Context.CurRegion.contains(L)) continue; if (Context.BoxedLoopsSet.count(L)) @@ -1403,7 +1451,7 @@ bool ScopDetection::isProfitableRegion(DetectionContext &Context) const { return invalid<ReportUnprofitable>(Context, /*Assert=*/true, &CurRegion); int NumLoops = - countBeneficialLoops(&CurRegion, *SE, *LI, MIN_LOOP_TRIP_COUNT).NumLoops; + countBeneficialLoops(&CurRegion, SE, LI, MIN_LOOP_TRIP_COUNT).NumLoops; int NumAffineLoops = NumLoops - Context.BoxedLoopsSet.size(); // Scops with at least two loops may allow either loop fusion or tiling and @@ -1553,7 +1601,7 @@ bool ScopDetection::isReducibleRegion(Region &R, DebugLoc &DbgLoc) const { // GREY indicates a loop in the control flow. // If the destination dominates the source, it is a natural loop // else, an irreducible control flow in the region is detected. - if (!DT->dominates(SuccBB, CurrBB)) { + if (!DT.dominates(SuccBB, CurrBB)) { // Get debug info of instruction which causes irregular control flow. DbgLoc = TInst->getDebugLoc(); return false; @@ -1570,8 +1618,8 @@ bool ScopDetection::isReducibleRegion(Region &R, DebugLoc &DbgLoc) const { return true; } -void updateLoopCountStatistic(ScopDetection::LoopStats Stats, - bool OnlyProfitable) { +static void updateLoopCountStatistic(ScopDetection::LoopStats Stats, + bool OnlyProfitable) { if (!OnlyProfitable) { NumLoopsInScop += Stats.NumLoops; MaxNumLoopsInScop = @@ -1607,61 +1655,6 @@ void updateLoopCountStatistic(ScopDetection::LoopStats Stats, } } -bool ScopDetection::runOnFunction(llvm::Function &F) { - LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo(); - RI = &getAnalysis<RegionInfoPass>().getRegionInfo(); - if (!PollyProcessUnprofitable && LI->empty()) - return false; - - AA = &getAnalysis<AAResultsWrapperPass>().getAAResults(); - SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE(); - DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree(); - Region *TopRegion = RI->getTopLevelRegion(); - - releaseMemory(); - - if (OnlyFunction != "" && !F.getName().count(OnlyFunction)) - return false; - - if (!isValidFunction(F)) - return false; - - findScops(*TopRegion); - - NumScopRegions += ValidRegions.size(); - - // Prune non-profitable regions. - for (auto &DIt : DetectionContextMap) { - auto &DC = DIt.getSecond(); - if (DC.Log.hasErrors()) - continue; - if (!ValidRegions.count(&DC.CurRegion)) - continue; - LoopStats Stats = countBeneficialLoops(&DC.CurRegion, *SE, *LI, 0); - updateLoopCountStatistic(Stats, false /* OnlyProfitable */); - if (isProfitableRegion(DC)) { - updateLoopCountStatistic(Stats, true /* OnlyProfitable */); - continue; - } - - ValidRegions.remove(&DC.CurRegion); - } - - NumProfScopRegions += ValidRegions.size(); - NumLoopsOverall += countBeneficialLoops(TopRegion, *SE, *LI, 0).NumLoops; - - // Only makes sense when we tracked errors. - if (PollyTrackFailures) - emitMissedRemarks(F); - - if (ReportLevel) - printLocations(F); - - assert(ValidRegions.size() <= DetectionContextMap.size() && - "Cached more results than valid regions"); - return false; -} - ScopDetection::DetectionContext * ScopDetection::getDetectionContext(const Region *R) const { auto DCMIt = DetectionContextMap.find(getBBPairForRegion(R)); @@ -1678,7 +1671,7 @@ const RejectLog *ScopDetection::lookupRejectionLog(const Region *R) const { void polly::ScopDetection::verifyRegion(const Region &R) const { assert(isMaxRegionInScop(R) && "Expect R is a valid region."); - DetectionContext Context(const_cast<Region &>(R), *AA, true /*verifying*/); + DetectionContext Context(const_cast<Region &>(R), AA, true /*verifying*/); isValidRegion(Context); } @@ -1690,7 +1683,17 @@ void polly::ScopDetection::verifyAnalysis() const { verifyRegion(*R); } -void ScopDetection::getAnalysisUsage(AnalysisUsage &AU) const { +bool ScopDetectionWrapperPass::runOnFunction(llvm::Function &F) { + auto &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo(); + auto &RI = getAnalysis<RegionInfoPass>().getRegionInfo(); + auto &AA = getAnalysis<AAResultsWrapperPass>().getAAResults(); + auto &SE = getAnalysis<ScalarEvolutionWrapperPass>().getSE(); + auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree(); + Result.reset(new ScopDetection(F, DT, SE, LI, RI, AA)); + return false; +} + +void ScopDetectionWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const { AU.addRequired<LoopInfoWrapperPass>(); AU.addRequiredTransitive<ScalarEvolutionWrapperPass>(); AU.addRequired<DominatorTreeWrapperPass>(); @@ -1700,25 +1703,49 @@ void ScopDetection::getAnalysisUsage(AnalysisUsage &AU) const { AU.setPreservesAll(); } -void ScopDetection::print(raw_ostream &OS, const Module *) const { - for (const Region *R : ValidRegions) +void ScopDetectionWrapperPass::print(raw_ostream &OS, const Module *) const { + for (const Region *R : Result->ValidRegions) OS << "Valid Region for Scop: " << R->getNameStr() << '\n'; OS << "\n"; } -void ScopDetection::releaseMemory() { - ValidRegions.clear(); - DetectionContextMap.clear(); +ScopDetectionWrapperPass::ScopDetectionWrapperPass() : FunctionPass(ID) { + // Disable runtime alias checks if we ignore aliasing all together. + if (IgnoreAliasing) + PollyUseRuntimeAliasChecks = false; +} + +void ScopDetectionWrapperPass::releaseMemory() { Result.reset(); } + +char ScopDetectionWrapperPass::ID; + +AnalysisKey ScopAnalysis::Key; - // Do not clear the invalid function set. +ScopDetection ScopAnalysis::run(Function &F, FunctionAnalysisManager &FAM) { + auto &LI = FAM.getResult<LoopAnalysis>(F); + auto &RI = FAM.getResult<RegionInfoAnalysis>(F); + auto &AA = FAM.getResult<AAManager>(F); + auto &SE = FAM.getResult<ScalarEvolutionAnalysis>(F); + auto &DT = FAM.getResult<DominatorTreeAnalysis>(F); + return {F, DT, SE, LI, RI, AA}; } -char ScopDetection::ID = 0; +PreservedAnalyses ScopAnalysisPrinterPass::run(Function &F, + FunctionAnalysisManager &FAM) { + auto &SD = FAM.getResult<ScopAnalysis>(F); + for (const Region *R : SD.ValidRegions) + Stream << "Valid Region for Scop: " << R->getNameStr() << '\n'; -Pass *polly::createScopDetectionPass() { return new ScopDetection(); } + Stream << "\n"; + return PreservedAnalyses::all(); +} + +Pass *polly::createScopDetectionWrapperPassPass() { + return new ScopDetectionWrapperPass(); +} -INITIALIZE_PASS_BEGIN(ScopDetection, "polly-detect", +INITIALIZE_PASS_BEGIN(ScopDetectionWrapperPass, "polly-detect", "Polly - Detect static control parts (SCoPs)", false, false); INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass); @@ -1726,5 +1753,5 @@ INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass); INITIALIZE_PASS_DEPENDENCY(RegionInfoPass); INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass); INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass); -INITIALIZE_PASS_END(ScopDetection, "polly-detect", +INITIALIZE_PASS_END(ScopDetectionWrapperPass, "polly-detect", "Polly - Detect static control parts (SCoPs)", false, false) |

