C++ SmallSetVector::clear方法代码示例

PreservedAnalyses AlwaysInlinerPass::run(Module &M, ModuleAnalysisManager &) {
  InlineFunctionInfo IFI;
  SmallSetVector<CallSite, 16> Calls;
  bool Changed = false;
  SmallVector<Function *, 16> InlinedFunctions;
  for (Function &F : M)
    if (!F.isDeclaration() && F.hasFnAttribute(Attribute::AlwaysInline) &&
        isInlineViable(F)) {
      Calls.clear();

      for (User *U : F.users())
        if (auto CS = CallSite(U))
          if (CS.getCalledFunction() == &F)
            Calls.insert(CS);

      for (CallSite CS : Calls)
        // FIXME: We really shouldn't be able to fail to inline at this point!
        // We should do something to log or check the inline failures here.
        Changed |= InlineFunction(CS, IFI);

      // Remember to try and delete this function afterward. This both avoids
      // re-walking the rest of the module and avoids dealing with any iterator
      // invalidation issues while deleting functions.
      InlinedFunctions.push_back(&F);
    }

  // Remove any live functions.
  erase_if(InlinedFunctions, [&](Function *F) {
    F->removeDeadConstantUsers();
    return !F->isDefTriviallyDead();
  });

  // Delete the non-comdat ones from the module and also from our vector.
  auto NonComdatBegin = partition(
      InlinedFunctions, [&](Function *F) { return F->hasComdat(); });
  for (Function *F : make_range(NonComdatBegin, InlinedFunctions.end()))
    M.getFunctionList().erase(F);
  InlinedFunctions.erase(NonComdatBegin, InlinedFunctions.end());

  if (!InlinedFunctions.empty()) {
    // Now we just have the comdat functions. Filter out the ones whose comdats
    // are not actually dead.
    filterDeadComdatFunctions(M, InlinedFunctions);
    // The remaining functions are actually dead.
    for (Function *F : InlinedFunctions)
      M.getFunctionList().erase(F);
  }

  return Changed ? PreservedAnalyses::none() : PreservedAnalyses::all();
}

PreservedAnalyses AlwaysInlinerPass::run(Module &M, ModuleAnalysisManager &) {
  InlineFunctionInfo IFI;
  SmallSetVector<CallSite, 16> Calls;
  bool Changed = false;
  SmallVector<Function *, 16> InlinedFunctions;
  for (Function &F : M)
    if (!F.isDeclaration() && F.hasFnAttribute(Attribute::AlwaysInline) &&
        isInlineViable(F)) {
      Calls.clear();

      for (User *U : F.users())
        if (auto CS = CallSite(U))
          if (CS.getCalledFunction() == &F)
            Calls.insert(CS);

      for (CallSite CS : Calls)
        // FIXME: We really shouldn't be able to fail to inline at this point!
        // We should do something to log or check the inline failures here.
        Changed |= InlineFunction(CS, IFI);

      // Remember to try and delete this function afterward. This both avoids
      // re-walking the rest of the module and avoids dealing with any iterator
      // invalidation issues while deleting functions.
      InlinedFunctions.push_back(&F);
    }

  // Now try to delete all the functions we inlined.
  for (Function *InlinedF : InlinedFunctions) {
    InlinedF->removeDeadConstantUsers();
    // FIXME: We should use some utility to handle cases where we can
    // completely remove the comdat.
    if (InlinedF->isDefTriviallyDead() && !InlinedF->hasComdat())
      M.getFunctionList().erase(InlinedF);
  }

  return Changed ? PreservedAnalyses::none() : PreservedAnalyses::all();
}

/// \brief Figure out if the loop is worth full unrolling.
///
/// Complete loop unrolling can make some loads constant, and we need to know
/// if that would expose any further optimization opportunities.  This routine
/// estimates this optimization.  It computes cost of unrolled loop
/// (UnrolledCost) and dynamic cost of the original loop (RolledDynamicCost). By
/// dynamic cost we mean that we won't count costs of blocks that are known not
/// to be executed (i.e. if we have a branch in the loop and we know that at the
/// given iteration its condition would be resolved to true, we won't add up the
/// cost of the 'false'-block).
/// \returns Optional value, holding the RolledDynamicCost and UnrolledCost. If
/// the analysis failed (no benefits expected from the unrolling, or the loop is
/// too big to analyze), the returned value is None.
Optional<EstimatedUnrollCost>
analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, ScalarEvolution &SE,
                      const TargetTransformInfo &TTI,
                      unsigned MaxUnrolledLoopSize) {
  // We want to be able to scale offsets by the trip count and add more offsets
  // to them without checking for overflows, and we already don't want to
  // analyze *massive* trip counts, so we force the max to be reasonably small.
  assert(UnrollMaxIterationsCountToAnalyze < (INT_MAX / 2) &&
         "The unroll iterations max is too large!");

  // Don't simulate loops with a big or unknown tripcount
  if (!UnrollMaxIterationsCountToAnalyze || !TripCount ||
      TripCount > UnrollMaxIterationsCountToAnalyze)
    return None;

  SmallSetVector<BasicBlock *, 16> BBWorklist;
  DenseMap<Value *, Constant *> SimplifiedValues;

  // The estimated cost of the unrolled form of the loop. We try to estimate
  // this by simplifying as much as we can while computing the estimate.
  unsigned UnrolledCost = 0;
  // We also track the estimated dynamic (that is, actually executed) cost in
  // the rolled form. This helps identify cases when the savings from unrolling
  // aren't just exposing dead control flows, but actual reduced dynamic
  // instructions due to the simplifications which we expect to occur after
  // unrolling.
  unsigned RolledDynamicCost = 0;

  // Simulate execution of each iteration of the loop counting instructions,
  // which would be simplified.
  // Since the same load will take different values on different iterations,
  // we literally have to go through all loop's iterations.
  for (unsigned Iteration = 0; Iteration < TripCount; ++Iteration) {
    SimplifiedValues.clear();
    UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, L, SE);

    BBWorklist.clear();
    BBWorklist.insert(L->getHeader());
    // Note that we *must not* cache the size, this loop grows the worklist.
    for (unsigned Idx = 0; Idx != BBWorklist.size(); ++Idx) {
      BasicBlock *BB = BBWorklist[Idx];

      // Visit all instructions in the given basic block and try to simplify
      // it.  We don't change the actual IR, just count optimization
      // opportunities.
      for (Instruction &I : *BB) {
        unsigned InstCost = TTI.getUserCost(&I);

        // Visit the instruction to analyze its loop cost after unrolling,
        // and if the visitor returns false, include this instruction in the
        // unrolled cost.
        if (!Analyzer.visit(I))
          UnrolledCost += InstCost;

        // Also track this instructions expected cost when executing the rolled
        // loop form.
        RolledDynamicCost += InstCost;

        // If unrolled body turns out to be too big, bail out.
        if (UnrolledCost > MaxUnrolledLoopSize)
          return None;
      }

      // Add BB's successors to the worklist.
      for (BasicBlock *Succ : successors(BB))
        if (L->contains(Succ))
          BBWorklist.insert(Succ);
    }

    // If we found no optimization opportunities on the first iteration, we
    // won't find them on later ones too.
    if (UnrolledCost == RolledDynamicCost)
      return None;
  }
  return {{UnrolledCost, RolledDynamicCost}};
}

//.........这里部分代码省略.........
            continue;
          }

        // First accumulate the cost of this instruction.
        if (!Cost.IsFree) {
          UnrolledCost += TTI.getUserCost(I);
          DEBUG(dbgs() << "Adding cost of instruction (iteration " << Iteration
                       << "): ");
          DEBUG(I->dump());
        }

        // We must count the cost of every operand which is not free,
        // recursively. If we reach a loop PHI node, simply add it to the set
        // to be considered on the next iteration (backwards!).
        for (Value *Op : I->operands()) {
          // Check whether this operand is free due to being a constant or
          // outside the loop.
          auto *OpI = dyn_cast<Instruction>(Op);
          if (!OpI || !L->contains(OpI))
            continue;

          // Otherwise accumulate its cost.
          CostWorklist.push_back(OpI);
        }
      } while (!CostWorklist.empty());

      if (PHIUsedList.empty())
        // We've exhausted the search.
        break;

      assert(Iteration > 0 &&
             "Cannot track PHI-used values past the first iteration!");
      CostWorklist.append(PHIUsedList.begin(), PHIUsedList.end());
      PHIUsedList.clear();
    }
  };

  // Ensure that we don't violate the loop structure invariants relied on by
  // this analysis.
  assert(L->isLoopSimplifyForm() && "Must put loop into normal form first.");
  assert(L->isLCSSAForm(DT) &&
         "Must have loops in LCSSA form to track live-out values.");

  DEBUG(dbgs() << "Starting LoopUnroll profitability analysis...\n");

  // Simulate execution of each iteration of the loop counting instructions,
  // which would be simplified.
  // Since the same load will take different values on different iterations,
  // we literally have to go through all loop's iterations.
  for (unsigned Iteration = 0; Iteration < TripCount; ++Iteration) {
    DEBUG(dbgs() << " Analyzing iteration " << Iteration << "\n");

    // Prepare for the iteration by collecting any simplified entry or backedge
    // inputs.
    for (Instruction &I : *L->getHeader()) {
      auto *PHI = dyn_cast<PHINode>(&I);
      if (!PHI)
        break;

      // The loop header PHI nodes must have exactly two input: one from the
      // loop preheader and one from the loop latch.
      assert(
          PHI->getNumIncomingValues() == 2 &&
          "Must have an incoming value only for the preheader and the latch.");

      Value *V = PHI->getIncomingValueForBlock(

bool MachineCopyPropagation::CopyPropagateBlock(MachineBasicBlock &MBB) {
  SmallSetVector<MachineInstr*, 8> MaybeDeadCopies;  // Candidates for deletion
  DenseMap<unsigned, MachineInstr*> AvailCopyMap;    // Def -> available copies map
  DenseMap<unsigned, MachineInstr*> CopyMap;         // Def -> copies map
  SourceMap SrcMap; // Src -> Def map

  bool Changed = false;
  for (MachineBasicBlock::iterator I = MBB.begin(), E = MBB.end(); I != E; ) {
    MachineInstr *MI = &*I;
    ++I;

    if (MI->isCopy()) {
      unsigned Def = MI->getOperand(0).getReg();
      unsigned Src = MI->getOperand(1).getReg();

      if (TargetRegisterInfo::isVirtualRegister(Def) ||
          TargetRegisterInfo::isVirtualRegister(Src))
        report_fatal_error("MachineCopyPropagation should be run after"
                           " register allocation!");

      DenseMap<unsigned, MachineInstr*>::iterator CI = AvailCopyMap.find(Src);
      if (CI != AvailCopyMap.end()) {
        MachineInstr *CopyMI = CI->second;
        if (!MRI->isReserved(Def) &&
            (!MRI->isReserved(Src) || NoInterveningSideEffect(CopyMI, MI)) &&
            isNopCopy(CopyMI, Def, Src, TRI)) {
          // The two copies cancel out and the source of the first copy
          // hasn't been overridden, eliminate the second one. e.g.
          //  %ECX<def> = COPY %EAX<kill>
          //  ... nothing clobbered EAX.
          //  %EAX<def> = COPY %ECX
          // =>
          //  %ECX<def> = COPY %EAX
          //
          // Also avoid eliminating a copy from reserved registers unless the
          // definition is proven not clobbered. e.g.
          // %RSP<def> = COPY %RAX
          // CALL
          // %RAX<def> = COPY %RSP

          // Clear any kills of Def between CopyMI and MI. This extends the
          // live range.
          for (MachineBasicBlock::iterator I = CopyMI, E = MI; I != E; ++I)
            I->clearRegisterKills(Def, TRI);

          removeCopy(MI);
          Changed = true;
          ++NumDeletes;
          continue;
        }
      }

      // If Src is defined by a previous copy, it cannot be eliminated.
      for (MCRegAliasIterator AI(Src, TRI, true); AI.isValid(); ++AI) {
        CI = CopyMap.find(*AI);
        if (CI != CopyMap.end())
          MaybeDeadCopies.remove(CI->second);
      }

      // Copy is now a candidate for deletion.
      MaybeDeadCopies.insert(MI);

      // If 'Src' is previously source of another copy, then this earlier copy's
      // source is no longer available. e.g.
      // %xmm9<def> = copy %xmm2
      // ...
      // %xmm2<def> = copy %xmm0
      // ...
      // %xmm2<def> = copy %xmm9
      SourceNoLongerAvailable(Def, SrcMap, AvailCopyMap);

      // Remember Def is defined by the copy.
      // ... Make sure to clear the def maps of aliases first.
      for (MCRegAliasIterator AI(Def, TRI, false); AI.isValid(); ++AI) {
        CopyMap.erase(*AI);
        AvailCopyMap.erase(*AI);
      }
      CopyMap[Def] = MI;
      AvailCopyMap[Def] = MI;
      for (MCSubRegIterator SR(Def, TRI); SR.isValid(); ++SR) {
        CopyMap[*SR] = MI;
        AvailCopyMap[*SR] = MI;
      }

      // Remember source that's copied to Def. Once it's clobbered, then
      // it's no longer available for copy propagation.
      if (std::find(SrcMap[Src].begin(), SrcMap[Src].end(), Def) ==
          SrcMap[Src].end()) {
        SrcMap[Src].push_back(Def);
      }

      continue;
    }

    // Not a copy.
    SmallVector<unsigned, 2> Defs;
    int RegMaskOpNum = -1;
    for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
      MachineOperand &MO = MI->getOperand(i);
      if (MO.isRegMask())
//.........这里部分代码省略.........

//.........这里部分代码省略.........
          Callee.dropAllReferences();
          assert(find(DeadFunctions, &Callee) == DeadFunctions.end() &&
                 "Cannot put cause a function to become dead twice!");
          DeadFunctions.push_back(&Callee);
        }
      }
    }

    // Back the call index up by one to put us in a good position to go around
    // the outer loop.
    --i;

    if (!DidInline)
      continue;
    Changed = true;

    // Add all the inlined callees' edges as ref edges to the caller. These are
    // by definition trivial edges as we always have *some* transitive ref edge
    // chain. While in some cases these edges are direct calls inside the
    // callee, they have to be modeled in the inliner as reference edges as
    // there may be a reference edge anywhere along the chain from the current
    // caller to the callee that causes the whole thing to appear like
    // a (transitive) reference edge that will require promotion to a call edge
    // below.
    for (Function *InlinedCallee : InlinedCallees) {
      LazyCallGraph::Node &CalleeN = *CG.lookup(*InlinedCallee);
      for (LazyCallGraph::Edge &E : *CalleeN)
        RC->insertTrivialRefEdge(N, E.getNode());
    }

    // At this point, since we have made changes we have at least removed
    // a call instruction. However, in the process we do some incremental
    // simplification of the surrounding code. This simplification can
    // essentially do all of the same things as a function pass and we can
    // re-use the exact same logic for updating the call graph to reflect the
    // change.
    LazyCallGraph::SCC *OldC = C;
    C = &updateCGAndAnalysisManagerForFunctionPass(CG, *C, N, AM, UR);
    LLVM_DEBUG(dbgs() << "Updated inlining SCC: " << *C << "\n");
    RC = &C->getOuterRefSCC();

    // If this causes an SCC to split apart into multiple smaller SCCs, there
    // is a subtle risk we need to prepare for. Other transformations may
    // expose an "infinite inlining" opportunity later, and because of the SCC
    // mutation, we will revisit this function and potentially re-inline. If we
    // do, and that re-inlining also has the potentially to mutate the SCC
    // structure, the infinite inlining problem can manifest through infinite
    // SCC splits and merges. To avoid this, we capture the originating caller
    // node and the SCC containing the call edge. This is a slight over
    // approximation of the possible inlining decisions that must be avoided,
    // but is relatively efficient to store.
    // FIXME: This seems like a very heavyweight way of retaining the inline
    // history, we should look for a more efficient way of tracking it.
    if (C != OldC && llvm::any_of(InlinedCallees, [&](Function *Callee) {
          return CG.lookupSCC(*CG.lookup(*Callee)) == OldC;
        })) {
      LLVM_DEBUG(dbgs() << "Inlined an internal call edge and split an SCC, "
                           "retaining this to avoid infinite inlining.\n");
      UR.InlinedInternalEdges.insert({&N, OldC});
    }
    InlinedCallees.clear();
  }

  // Now that we've finished inlining all of the calls across this SCC, delete
  // all of the trivially dead functions, updating the call graph and the CGSCC
  // pass manager in the process.
  //
  // Note that this walks a pointer set which has non-deterministic order but
  // that is OK as all we do is delete things and add pointers to unordered
  // sets.
  for (Function *DeadF : DeadFunctions) {
    // Get the necessary information out of the call graph and nuke the
    // function there. Also, cclear out any cached analyses.
    auto &DeadC = *CG.lookupSCC(*CG.lookup(*DeadF));
    FunctionAnalysisManager &FAM =
        AM.getResult<FunctionAnalysisManagerCGSCCProxy>(DeadC, CG)
            .getManager();
    FAM.clear(*DeadF, DeadF->getName());
    AM.clear(DeadC, DeadC.getName());
    auto &DeadRC = DeadC.getOuterRefSCC();
    CG.removeDeadFunction(*DeadF);

    // Mark the relevant parts of the call graph as invalid so we don't visit
    // them.
    UR.InvalidatedSCCs.insert(&DeadC);
    UR.InvalidatedRefSCCs.insert(&DeadRC);

    // And delete the actual function from the module.
    M.getFunctionList().erase(DeadF);
  }

  if (!Changed)
    return PreservedAnalyses::all();

  // Even if we change the IR, we update the core CGSCC data structures and so
  // can preserve the proxy to the function analysis manager.
  PreservedAnalyses PA;
  PA.preserve<FunctionAnalysisManagerCGSCCProxy>();
  return PA;
}

/// \brief Figure out if the loop is worth full unrolling.
///
/// Complete loop unrolling can make some loads constant, and we need to know
/// if that would expose any further optimization opportunities.  This routine
/// estimates this optimization.  It computes cost of unrolled loop
/// (UnrolledCost) and dynamic cost of the original loop (RolledDynamicCost). By
/// dynamic cost we mean that we won't count costs of blocks that are known not
/// to be executed (i.e. if we have a branch in the loop and we know that at the
/// given iteration its condition would be resolved to true, we won't add up the
/// cost of the 'false'-block).
/// \returns Optional value, holding the RolledDynamicCost and UnrolledCost. If
/// the analysis failed (no benefits expected from the unrolling, or the loop is
/// too big to analyze), the returned value is None.
static Optional<EstimatedUnrollCost>
analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, DominatorTree &DT,
                      ScalarEvolution &SE, const TargetTransformInfo &TTI,
                      int MaxUnrolledLoopSize) {
  // We want to be able to scale offsets by the trip count and add more offsets
  // to them without checking for overflows, and we already don't want to
  // analyze *massive* trip counts, so we force the max to be reasonably small.
  assert(UnrollMaxIterationsCountToAnalyze < (INT_MAX / 2) &&
         "The unroll iterations max is too large!");

  // Don't simulate loops with a big or unknown tripcount
  if (!UnrollMaxIterationsCountToAnalyze || !TripCount ||
      TripCount > UnrollMaxIterationsCountToAnalyze)
    return None;

  SmallSetVector<BasicBlock *, 16> BBWorklist;
  DenseMap<Value *, Constant *> SimplifiedValues;
  SmallVector<std::pair<Value *, Constant *>, 4> SimplifiedInputValues;

  // The estimated cost of the unrolled form of the loop. We try to estimate
  // this by simplifying as much as we can while computing the estimate.
  int UnrolledCost = 0;
  // We also track the estimated dynamic (that is, actually executed) cost in
  // the rolled form. This helps identify cases when the savings from unrolling
  // aren't just exposing dead control flows, but actual reduced dynamic
  // instructions due to the simplifications which we expect to occur after
  // unrolling.
  int RolledDynamicCost = 0;

  // Ensure that we don't violate the loop structure invariants relied on by
  // this analysis.
  assert(L->isLoopSimplifyForm() && "Must put loop into normal form first.");
  assert(L->isLCSSAForm(DT) &&
         "Must have loops in LCSSA form to track live-out values.");

  DEBUG(dbgs() << "Starting LoopUnroll profitability analysis...\n");

  // Simulate execution of each iteration of the loop counting instructions,
  // which would be simplified.
  // Since the same load will take different values on different iterations,
  // we literally have to go through all loop's iterations.
  for (unsigned Iteration = 0; Iteration < TripCount; ++Iteration) {
    DEBUG(dbgs() << " Analyzing iteration " << Iteration << "\n");

    // Prepare for the iteration by collecting any simplified entry or backedge
    // inputs.
    for (Instruction &I : *L->getHeader()) {
      auto *PHI = dyn_cast<PHINode>(&I);
      if (!PHI)
        break;

      // The loop header PHI nodes must have exactly two input: one from the
      // loop preheader and one from the loop latch.
      assert(
          PHI->getNumIncomingValues() == 2 &&
          "Must have an incoming value only for the preheader and the latch.");

      Value *V = PHI->getIncomingValueForBlock(
          Iteration == 0 ? L->getLoopPreheader() : L->getLoopLatch());
      Constant *C = dyn_cast<Constant>(V);
      if (Iteration != 0 && !C)
        C = SimplifiedValues.lookup(V);
      if (C)
        SimplifiedInputValues.push_back({PHI, C});
    }

    // Now clear and re-populate the map for the next iteration.
    SimplifiedValues.clear();
    while (!SimplifiedInputValues.empty())
      SimplifiedValues.insert(SimplifiedInputValues.pop_back_val());

    UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, SE);

    BBWorklist.clear();
    BBWorklist.insert(L->getHeader());
    // Note that we *must not* cache the size, this loop grows the worklist.
    for (unsigned Idx = 0; Idx != BBWorklist.size(); ++Idx) {
      BasicBlock *BB = BBWorklist[Idx];

      // Visit all instructions in the given basic block and try to simplify
      // it.  We don't change the actual IR, just count optimization
      // opportunities.
      for (Instruction &I : *BB) {
        int InstCost = TTI.getUserCost(&I);

        // Visit the instruction to analyze its loop cost after unrolling,
        // and if the visitor returns false, include this instruction in the
//.........这里部分代码省略.........