#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/AssumptionCache.h"
+#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/CallGraph.h"
#include "llvm/Analysis/InlineCost.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
// Threshold to use when optsize is specified (and there is no -inline-limit).
const int OptSizeThreshold = 75;
-Inliner::Inliner(char &ID)
- : CallGraphSCCPass(ID), InlineThreshold(InlineLimit), InsertLifetime(true) {}
+Inliner::Inliner(char &ID)
+ : CallGraphSCCPass(ID), InlineThreshold(InlineLimit), InsertLifetime(true) {
+}
Inliner::Inliner(char &ID, int Threshold, bool InsertLifetime)
- : CallGraphSCCPass(ID), InlineThreshold(InlineLimit.getNumOccurrences() > 0 ?
- InlineLimit : Threshold),
- InsertLifetime(InsertLifetime) {}
+ : CallGraphSCCPass(ID),
+ InlineThreshold(InlineLimit.getNumOccurrences() > 0 ? InlineLimit
+ : Threshold),
+ InsertLifetime(InsertLifetime) {}
/// For this class, we declare that we require and preserve the call graph.
/// If the derived class implements this method, it should
/// always explicitly call the implementation here.
void Inliner::getAnalysisUsage(AnalysisUsage &AU) const {
- AU.addRequired<AliasAnalysis>();
AU.addRequired<AssumptionCacheTracker>();
+ AU.addRequired<TargetLibraryInfoWrapperPass>();
CallGraphSCCPass::getAnalysisUsage(AU);
}
typedef DenseMap<ArrayType*, std::vector<AllocaInst*> >
InlinedArrayAllocasTy;
-/// \brief If the inlined function had a higher stack protection level than the
-/// calling function, then bump up the caller's stack protection level.
-static void AdjustCallerSSPLevel(Function *Caller, Function *Callee) {
- // If upgrading the SSP attribute, clear out the old SSP Attributes first.
- // Having multiple SSP attributes doesn't actually hurt, but it adds useless
- // clutter to the IR.
- AttrBuilder B;
- B.addAttribute(Attribute::StackProtect)
- .addAttribute(Attribute::StackProtectStrong)
- .addAttribute(Attribute::StackProtectReq);
- AttributeSet OldSSPAttr = AttributeSet::get(Caller->getContext(),
- AttributeSet::FunctionIndex,
- B);
-
- if (Callee->hasFnAttribute(Attribute::SafeStack)) {
- Caller->removeAttributes(AttributeSet::FunctionIndex, OldSSPAttr);
- Caller->addFnAttr(Attribute::SafeStack);
- } else if (Callee->hasFnAttribute(Attribute::StackProtectReq) &&
- !Caller->hasFnAttribute(Attribute::SafeStack)) {
- Caller->removeAttributes(AttributeSet::FunctionIndex, OldSSPAttr);
- Caller->addFnAttr(Attribute::StackProtectReq);
- } else if (Callee->hasFnAttribute(Attribute::StackProtectStrong) &&
- !Caller->hasFnAttribute(Attribute::SafeStack) &&
- !Caller->hasFnAttribute(Attribute::StackProtectReq)) {
- Caller->removeAttributes(AttributeSet::FunctionIndex, OldSSPAttr);
- Caller->addFnAttr(Attribute::StackProtectStrong);
- } else if (Callee->hasFnAttribute(Attribute::StackProtect) &&
- !Caller->hasFnAttribute(Attribute::SafeStack) &&
- !Caller->hasFnAttribute(Attribute::StackProtectReq) &&
- !Caller->hasFnAttribute(Attribute::StackProtectStrong))
- Caller->addFnAttr(Attribute::StackProtect);
-}
-
/// If it is possible to inline the specified call site,
/// do so and update the CallGraph for this operation.
///
/// available from other functions inlined into the caller. If we are able to
/// inline this call site we attempt to reuse already available allocas or add
/// any new allocas to the set if not possible.
-static bool InlineCallIfPossible(CallSite CS, InlineFunctionInfo &IFI,
+static bool InlineCallIfPossible(Pass &P, CallSite CS, InlineFunctionInfo &IFI,
InlinedArrayAllocasTy &InlinedArrayAllocas,
int InlineHistory, bool InsertLifetime) {
Function *Callee = CS.getCalledFunction();
Function *Caller = CS.getCaller();
+ // We need to manually construct BasicAA directly in order to disable
+ // its use of other function analyses.
+ BasicAAResult BAR(createLegacyPMBasicAAResult(P, *Callee));
+
+ // Construct our own AA results for this function. We do this manually to
+ // work around the limitations of the legacy pass manager.
+ AAResults AAR(createLegacyPMAAResults(P, *Callee, BAR));
+
// Try to inline the function. Get the list of static allocas that were
// inlined.
- if (!InlineFunction(CS, IFI, InsertLifetime))
+ if (!InlineFunction(CS, IFI, &AAR, InsertLifetime))
return false;
- AdjustCallerSSPLevel(Caller, Callee);
+ AttributeFuncs::mergeAttributesForInlining(*Caller, *Callee);
// Look at all of the allocas that we inlined through this call site. If we
// have already inlined other allocas through other calls into this function,
// set to keep track of which "available" allocas are being used by this
// function. Also, AllocasForType can be empty of course!
bool MergedAwayAlloca = false;
- for (unsigned i = 0, e = AllocasForType.size(); i != e; ++i) {
- AllocaInst *AvailableAlloca = AllocasForType[i];
+ for (AllocaInst *AvailableAlloca : AllocasForType) {
unsigned Align1 = AI->getAlignment(),
Align2 = AvailableAlloca->getAlignment();
DEBUG(dbgs() << " ***MERGED ALLOCA: " << *AI << "\n\t\tINTO: "
<< *AvailableAlloca << '\n');
+ // Move affected dbg.declare calls immediately after the new alloca to
+ // avoid the situation when a dbg.declare preceeds its alloca.
+ if (auto *L = LocalAsMetadata::getIfExists(AI))
+ if (auto *MDV = MetadataAsValue::getIfExists(AI->getContext(), L))
+ for (User *U : MDV->users())
+ if (DbgDeclareInst *DDI = dyn_cast<DbgDeclareInst>(U))
+ DDI->moveBefore(AvailableAlloca->getNextNode());
+
AI->replaceAllUsesWith(AvailableAlloca);
if (Align1 != Align2) {
}
unsigned Inliner::getInlineThreshold(CallSite CS) const {
- int thres = InlineThreshold; // -inline-threshold or else selected by
- // overall opt level
+ int Threshold = InlineThreshold; // -inline-threshold or else selected by
+ // overall opt level
// If -inline-threshold is not given, listen to the optsize attribute when it
// would decrease the threshold.
Function *Caller = CS.getCaller();
bool OptSize = Caller && !Caller->isDeclaration() &&
+ // FIXME: Use Function::optForSize().
Caller->hasFnAttribute(Attribute::OptimizeForSize);
if (!(InlineLimit.getNumOccurrences() > 0) && OptSize &&
- OptSizeThreshold < thres)
- thres = OptSizeThreshold;
+ OptSizeThreshold < Threshold)
+ Threshold = OptSizeThreshold;
- // Listen to the inlinehint attribute when it would increase the threshold
- // and the caller does not need to minimize its size.
Function *Callee = CS.getCalledFunction();
- bool InlineHint = Callee && !Callee->isDeclaration() &&
- Callee->hasFnAttribute(Attribute::InlineHint);
- if (InlineHint && HintThreshold > thres &&
- !Caller->hasFnAttribute(Attribute::MinSize))
- thres = HintThreshold;
+ if (!Callee || Callee->isDeclaration())
+ return Threshold;
+
+ // If profile information is available, use that to adjust threshold of hot
+ // and cold functions.
+ // FIXME: The heuristic used below for determining hotness and coldness are
+ // based on preliminary SPEC tuning and may not be optimal. Replace this with
+ // a well-tuned heuristic based on *callsite* hotness and not callee hotness.
+ uint64_t FunctionCount = 0, MaxFunctionCount = 0;
+ bool HasPGOCounts = false;
+ if (Callee->getEntryCount() &&
+ Callee->getParent()->getMaximumFunctionCount()) {
+ HasPGOCounts = true;
+ FunctionCount = Callee->getEntryCount().getValue();
+ MaxFunctionCount =
+ Callee->getParent()->getMaximumFunctionCount().getValue();
+ }
- // Listen to the cold attribute when it would decrease the threshold.
- bool ColdCallee = Callee && !Callee->isDeclaration() &&
- Callee->hasFnAttribute(Attribute::Cold);
+ // Listen to the inlinehint attribute or profile based hotness information
+ // when it would increase the threshold and the caller does not need to
+ // minimize its size.
+ bool InlineHint =
+ Callee->hasFnAttribute(Attribute::InlineHint) ||
+ (HasPGOCounts &&
+ FunctionCount >= (uint64_t)(0.3 * (double)MaxFunctionCount));
+ if (InlineHint && HintThreshold > Threshold &&
+ !Caller->hasFnAttribute(Attribute::MinSize))
+ Threshold = HintThreshold;
+
+ // Listen to the cold attribute or profile based coldness information
+ // when it would decrease the threshold.
+ bool ColdCallee =
+ Callee->hasFnAttribute(Attribute::Cold) ||
+ (HasPGOCounts &&
+ FunctionCount <= (uint64_t)(0.01 * (double)MaxFunctionCount));
// Command line argument for InlineLimit will override the default
// ColdThreshold. If we have -inline-threshold but no -inlinecold-threshold,
// do not use the default cold threshold even if it is smaller.
if ((InlineLimit.getNumOccurrences() == 0 ||
ColdThreshold.getNumOccurrences() > 0) && ColdCallee &&
- ColdThreshold < thres)
- thres = ColdThreshold;
+ ColdThreshold < Threshold)
+ Threshold = ColdThreshold;
- return thres;
+ return Threshold;
}
static void emitAnalysis(CallSite CS, const Twine &Msg) {
bool Inliner::runOnSCC(CallGraphSCC &SCC) {
CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
- AssumptionCacheTracker *ACT = &getAnalysis<AssumptionCacheTracker>();
- auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
- const TargetLibraryInfo *TLI = TLIP ? &TLIP->getTLI() : nullptr;
- AliasAnalysis *AA = &getAnalysis<AliasAnalysis>();
+ ACT = &getAnalysis<AssumptionCacheTracker>();
+ auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
SmallPtrSet<Function*, 8> SCCFunctions;
DEBUG(dbgs() << "Inliner visiting SCC:");
- for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
- Function *F = (*I)->getFunction();
+ for (CallGraphNode *Node : SCC) {
+ Function *F = Node->getFunction();
if (F) SCCFunctions.insert(F);
DEBUG(dbgs() << " " << (F ? F->getName() : "INDIRECTNODE"));
}
// index into the InlineHistory vector.
SmallVector<std::pair<Function*, int>, 8> InlineHistory;
- for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
- Function *F = (*I)->getFunction();
+ for (CallGraphNode *Node : SCC) {
+ Function *F = Node->getFunction();
if (!F) continue;
- for (Function::iterator BB = F->begin(), E = F->end(); BB != E; ++BB)
- for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
- CallSite CS(cast<Value>(I));
+ for (BasicBlock &BB : *F)
+ for (Instruction &I : BB) {
+ CallSite CS(cast<Value>(&I));
// If this isn't a call, or it is a call to an intrinsic, it can
// never be inlined.
if (!CS || isa<IntrinsicInst>(I))
// If this is a direct call to an external function, we can never inline
// it. If it is an indirect call, inlining may resolve it to be a
// direct call, so we keep it.
- if (CS.getCalledFunction() && CS.getCalledFunction()->isDeclaration())
- continue;
+ if (Function *Callee = CS.getCalledFunction())
+ if (Callee->isDeclaration())
+ continue;
CallSites.push_back(std::make_pair(CS, -1));
}
// If there are no calls in this function, exit early.
if (CallSites.empty())
return false;
-
+
// Now that we have all of the call sites, move the ones to functions in the
// current SCC to the end of the list.
unsigned FirstCallInSCC = CallSites.size();
InlinedArrayAllocasTy InlinedArrayAllocas;
- InlineFunctionInfo InlineInfo(&CG, AA, ACT);
+ InlineFunctionInfo InlineInfo(&CG, ACT);
// Now that we have all of the call sites, loop over them and inline them if
// it looks profitable to do so.
LocalChange = false;
// Iterate over the outer loop because inlining functions can cause indirect
// calls to become direct calls.
+ // CallSites may be modified inside so ranged for loop can not be used.
for (unsigned CSi = 0; CSi != CallSites.size(); ++CSi) {
CallSite CS = CallSites[CSi].first;
// just delete the call instead of trying to inline it, regardless of
// size. This happens because IPSCCP propagates the result out of the
// call and then we're left with the dead call.
- if (isInstructionTriviallyDead(CS.getInstruction(), TLI)) {
+ if (isInstructionTriviallyDead(CS.getInstruction(), &TLI)) {
DEBUG(dbgs() << " -> Deleting dead call: "
<< *CS.getInstruction() << "\n");
// Update the call graph by deleting the edge from Callee to Caller.
}
// Attempt to inline the function.
- if (!InlineCallIfPossible(CS, InlineInfo, InlinedArrayAllocas,
+ if (!InlineCallIfPossible(*this, CS, InlineInfo, InlinedArrayAllocas,
InlineHistoryID, InsertLifetime)) {
emitOptimizationRemarkMissed(CallerCtx, DEBUG_TYPE, *Caller, DLoc,
Twine(Callee->getName() +
int NewHistoryID = InlineHistory.size();
InlineHistory.push_back(std::make_pair(Callee, InlineHistoryID));
- for (unsigned i = 0, e = InlineInfo.InlinedCalls.size();
- i != e; ++i) {
- Value *Ptr = InlineInfo.InlinedCalls[i];
+ for (Value *Ptr : InlineInfo.InlinedCalls)
CallSites.push_back(std::make_pair(CallSite(Ptr), NewHistoryID));
- }
}
}
DEBUG(dbgs() << " -> Deleting dead function: "
<< Callee->getName() << "\n");
CallGraphNode *CalleeNode = CG[Callee];
-
+
// Remove any call graph edges from the callee to its callees.
CalleeNode->removeAllCalledFunctions();
// Scan for all of the functions, looking for ones that should now be removed
// from the program. Insert the dead ones in the FunctionsToRemove set.
- for (CallGraph::iterator I = CG.begin(), E = CG.end(); I != E; ++I) {
- CallGraphNode *CGN = I->second;
+ for (const auto &I : CG) {
+ CallGraphNode *CGN = I.second.get();
Function *F = CGN->getFunction();
if (!F || F->isDeclaration())
continue;
FunctionsToRemove.erase(std::unique(FunctionsToRemove.begin(),
FunctionsToRemove.end()),
FunctionsToRemove.end());
- for (SmallVectorImpl<CallGraphNode *>::iterator I = FunctionsToRemove.begin(),
- E = FunctionsToRemove.end();
- I != E; ++I) {
- delete CG.removeFunctionFromModule(*I);
+ for (CallGraphNode *CGN : FunctionsToRemove) {
+ delete CG.removeFunctionFromModule(CGN);
++NumDeleted;
}
return true;
projects / oota-llvm.git / blobdiff