//
//===----------------------------------------------------------------------===//
-#define DEBUG_TYPE "inline"
-#include "llvm/Module.h"
-#include "llvm/Instructions.h"
-#include "llvm/IntrinsicInst.h"
+#include "llvm/Transforms/IPO/InlinerPass.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#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/Target/TargetData.h"
-#include "llvm/Transforms/IPO/InlinerPass.h"
-#include "llvm/Transforms/Utils/Cloning.h"
-#include "llvm/Transforms/Utils/Local.h"
-#include "llvm/Support/CallSite.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/IR/CallSite.h"
+#include "llvm/IR/DataLayout.h"
+#include "llvm/IR/DiagnosticInfo.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/Module.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
-#include "llvm/ADT/SmallPtrSet.h"
-#include "llvm/ADT/Statistic.h"
+#include "llvm/Transforms/Utils/Cloning.h"
+#include "llvm/Transforms/Utils/Local.h"
using namespace llvm;
+#define DEBUG_TYPE "inline"
+
STATISTIC(NumInlined, "Number of functions inlined");
STATISTIC(NumCallsDeleted, "Number of call sites deleted, not inlined");
STATISTIC(NumDeleted, "Number of functions deleted because all callers found");
STATISTIC(NumMergedAllocas, "Number of allocas merged together");
+// This weirdly named statistic tracks the number of times that, when attempting
+// to inline a function A into B, we analyze the callers of B in order to see
+// if those would be more profitable and blocked inline steps.
+STATISTIC(NumCallerCallersAnalyzed, "Number of caller-callers analyzed");
+
static cl::opt<int>
InlineLimit("inline-threshold", cl::Hidden, cl::init(225), cl::ZeroOrMore,
cl::desc("Control the amount of inlining to perform (default = 225)"));
HintThreshold("inlinehint-threshold", cl::Hidden, cl::init(325),
cl::desc("Threshold for inlining functions with inline hint"));
+// We instroduce this threshold to help performance of instrumentation based
+// PGO before we actually hook up inliner with analysis passes such as BPI and
+// BFI.
+static cl::opt<int>
+ColdThreshold("inlinecold-threshold", cl::Hidden, cl::init(225),
+ cl::desc("Threshold for inlining functions with cold attribute"));
+
// Threshold to use when optsize is specified (and there is no -inline-limit).
const int OptSizeThreshold = 75;
InlineLimit : Threshold),
InsertLifetime(InsertLifetime) {}
-/// getAnalysisUsage - For this class, we declare that we require and preserve
-/// the call graph. If the derived class implements this method, it should
+/// 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 &Info) const {
- CallGraphSCCPass::getAnalysisUsage(Info);
+void Inliner::getAnalysisUsage(AnalysisUsage &AU) const {
+ AU.addRequired<AssumptionCacheTracker>();
+ AU.addRequired<TargetLibraryInfoWrapperPass>();
+ CallGraphSCCPass::getAnalysisUsage(AU);
}
typedef DenseMap<ArrayType*, std::vector<AllocaInst*> >
InlinedArrayAllocasTy;
-/// InlineCallIfPossible - If it is possible to inline the specified call site,
+/// \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.
///
/// This function also does some basic book-keeping to update the IR. The
/// InlinedArrayAllocas map keeps track of any allocas that are already
-/// available from other functions inlined into the caller. If we are able to
+/// 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;
- // If the inlined function had a higher stack protection level than the
- // calling function, then bump up the caller's stack protection level.
- if (Callee->hasFnAttr(Attribute::StackProtectReq))
- Caller->addFnAttr(Attribute::StackProtectReq);
- else if (Callee->hasFnAttr(Attribute::StackProtect) &&
- !Caller->hasFnAttr(Attribute::StackProtectReq))
- Caller->addFnAttr(Attribute::StackProtect);
+ AdjustCallerSSPLevel(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,
// canonicalized to be an allocation *of* an array), or allocations whose
// type is not itself an array (because we're afraid of pessimizing SRoA).
ArrayType *ATy = dyn_cast<ArrayType>(AI->getAllocatedType());
- if (ATy == 0 || AI->isArrayAllocation())
+ if (!ATy || AI->isArrayAllocation())
continue;
// Get the list of all available allocas for this array type.
// 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();
// The available alloca has to be in the right function, not in some other
// function in this SCC.
// If the inlined function already uses this alloca then we can't reuse
// it.
- if (!UsedAllocas.insert(AvailableAlloca))
+ if (!UsedAllocas.insert(AvailableAlloca).second)
continue;
// Otherwise, we *can* reuse it, RAUW AI into AvailableAlloca and declare
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) {
+ if (!Align1 || !Align2) {
+ const DataLayout &DL = Caller->getParent()->getDataLayout();
+ unsigned TypeAlign = DL.getABITypeAlignment(AI->getAllocatedType());
+
+ Align1 = Align1 ? Align1 : TypeAlign;
+ Align2 = Align2 ? Align2 : TypeAlign;
+ }
+
+ if (Align1 > Align2)
+ AvailableAlloca->setAlignment(AI->getAlignment());
+ }
+
AI->eraseFromParent();
MergedAwayAlloca = true;
++NumMergedAllocas;
- IFI.StaticAllocas[AllocaNo] = 0;
+ IFI.StaticAllocas[AllocaNo] = nullptr;
break;
}
}
unsigned Inliner::getInlineThreshold(CallSite CS) const {
- int thres = InlineThreshold;
+ int Threshold = InlineThreshold; // -inline-threshold or else selected by
+ // overall opt level
- // Listen to optsize when -inline-limit is not given.
+ // If -inline-threshold is not given, listen to the optsize attribute when it
+ // would decrease the threshold.
Function *Caller = CS.getCaller();
- if (Caller && !Caller->isDeclaration() &&
- Caller->hasFnAttr(Attribute::OptimizeForSize) &&
- InlineLimit.getNumOccurrences() == 0)
- thres = OptSizeThreshold;
+ bool OptSize = Caller && !Caller->isDeclaration() &&
+ // FIXME: Use Function::optForSize().
+ Caller->hasFnAttribute(Attribute::OptimizeForSize);
+ if (!(InlineLimit.getNumOccurrences() > 0) && OptSize &&
+ OptSizeThreshold < Threshold)
+ Threshold = OptSizeThreshold;
- // Listen to inlinehint when it would increase the threshold.
Function *Callee = CS.getCalledFunction();
- if (HintThreshold > thres && Callee && !Callee->isDeclaration() &&
- Callee->hasFnAttr(Attribute::InlineHint))
- 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 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 < Threshold)
+ Threshold = ColdThreshold;
+
+ return Threshold;
+}
- return thres;
+static void emitAnalysis(CallSite CS, const Twine &Msg) {
+ Function *Caller = CS.getCaller();
+ LLVMContext &Ctx = Caller->getContext();
+ DebugLoc DLoc = CS.getInstruction()->getDebugLoc();
+ emitOptimizationRemarkAnalysis(Ctx, DEBUG_TYPE, *Caller, DLoc, Msg);
}
-/// shouldInline - Return true if the inliner should attempt to inline
-/// at the given CallSite.
+/// Return true if the inliner should attempt to inline at the given CallSite.
bool Inliner::shouldInline(CallSite CS) {
InlineCost IC = getInlineCost(CS);
if (IC.isAlways()) {
DEBUG(dbgs() << " Inlining: cost=always"
<< ", Call: " << *CS.getInstruction() << "\n");
+ emitAnalysis(CS, Twine(CS.getCalledFunction()->getName()) +
+ " should always be inlined (cost=always)");
return true;
}
if (IC.isNever()) {
DEBUG(dbgs() << " NOT Inlining: cost=never"
<< ", Call: " << *CS.getInstruction() << "\n");
+ emitAnalysis(CS, Twine(CS.getCalledFunction()->getName() +
+ " should never be inlined (cost=never)"));
return false;
}
- int Cost = IC.getValue();
Function *Caller = CS.getCaller();
- int CurrentThreshold = getInlineThreshold(CS);
- float FudgeFactor = getInlineFudgeFactor(CS);
- int AdjThreshold = (int)(CurrentThreshold * FudgeFactor);
- if (Cost >= AdjThreshold) {
- DEBUG(dbgs() << " NOT Inlining: cost=" << Cost
- << ", thres=" << AdjThreshold
+ if (!IC) {
+ DEBUG(dbgs() << " NOT Inlining: cost=" << IC.getCost()
+ << ", thres=" << (IC.getCostDelta() + IC.getCost())
<< ", Call: " << *CS.getInstruction() << "\n");
+ emitAnalysis(CS, Twine(CS.getCalledFunction()->getName() +
+ " too costly to inline (cost=") +
+ Twine(IC.getCost()) + ", threshold=" +
+ Twine(IC.getCostDelta() + IC.getCost()) + ")");
return false;
}
- // Try to detect the case where the current inlining candidate caller
- // (call it B) is a static function and is an inlining candidate elsewhere,
- // and the current candidate callee (call it C) is large enough that
- // inlining it into B would make B too big to inline later. In these
- // circumstances it may be best not to inline C into B, but to inline B
- // into its callers.
- if (Caller->hasLocalLinkage()) {
+ // Try to detect the case where the current inlining candidate caller (call
+ // it B) is a static or linkonce-ODR function and is an inlining candidate
+ // elsewhere, and the current candidate callee (call it C) is large enough
+ // that inlining it into B would make B too big to inline later. In these
+ // circumstances it may be best not to inline C into B, but to inline B into
+ // its callers.
+ //
+ // This only applies to static and linkonce-ODR functions because those are
+ // expected to be available for inlining in the translation units where they
+ // are used. Thus we will always have the opportunity to make local inlining
+ // decisions. Importantly the linkonce-ODR linkage covers inline functions
+ // and templates in C++.
+ //
+ // FIXME: All of this logic should be sunk into getInlineCost. It relies on
+ // the internal implementation of the inline cost metrics rather than
+ // treating them as truly abstract units etc.
+ if (Caller->hasLocalLinkage() || Caller->hasLinkOnceODRLinkage()) {
int TotalSecondaryCost = 0;
- bool outerCallsFound = false;
+ // The candidate cost to be imposed upon the current function.
+ int CandidateCost = IC.getCost() - (InlineConstants::CallPenalty + 1);
// This bool tracks what happens if we do NOT inline C into B.
- bool callerWillBeRemoved = true;
+ bool callerWillBeRemoved = Caller->hasLocalLinkage();
// This bool tracks what happens if we DO inline C into B.
bool inliningPreventsSomeOuterInline = false;
- for (Value::use_iterator I = Caller->use_begin(), E =Caller->use_end();
- I != E; ++I) {
- CallSite CS2(*I);
+ for (User *U : Caller->users()) {
+ CallSite CS2(U);
// If this isn't a call to Caller (it could be some other sort
// of reference) skip it. Such references will prevent the caller
}
InlineCost IC2 = getInlineCost(CS2);
- if (IC2.isNever())
+ ++NumCallerCallersAnalyzed;
+ if (!IC2) {
callerWillBeRemoved = false;
- if (IC2.isAlways() || IC2.isNever())
+ continue;
+ }
+ if (IC2.isAlways())
continue;
- outerCallsFound = true;
- int Cost2 = IC2.getValue();
- int CurrentThreshold2 = getInlineThreshold(CS2);
- float FudgeFactor2 = getInlineFudgeFactor(CS2);
-
- if (Cost2 >= (int)(CurrentThreshold2 * FudgeFactor2))
- callerWillBeRemoved = false;
-
- // See if we have this case. We subtract off the penalty
- // for the call instruction, which we would be deleting.
- if (Cost2 < (int)(CurrentThreshold2 * FudgeFactor2) &&
- Cost2 + Cost - (InlineConstants::CallPenalty + 1) >=
- (int)(CurrentThreshold2 * FudgeFactor2)) {
+ // See if inlining or original callsite would erase the cost delta of
+ // this callsite. We subtract off the penalty for the call instruction,
+ // which we would be deleting.
+ if (IC2.getCostDelta() <= CandidateCost) {
inliningPreventsSomeOuterInline = true;
- TotalSecondaryCost += Cost2;
+ TotalSecondaryCost += IC2.getCost();
}
}
// If all outer calls to Caller would get inlined, the cost for the last
// one is set very low by getInlineCost, in anticipation that Caller will
// be removed entirely. We did not account for this above unless there
// is only one caller of Caller.
- if (callerWillBeRemoved && Caller->use_begin() != Caller->use_end())
+ if (callerWillBeRemoved && !Caller->use_empty())
TotalSecondaryCost += InlineConstants::LastCallToStaticBonus;
- if (outerCallsFound && inliningPreventsSomeOuterInline &&
- TotalSecondaryCost < Cost) {
- DEBUG(dbgs() << " NOT Inlining: " << *CS.getInstruction() <<
- " Cost = " << Cost <<
+ if (inliningPreventsSomeOuterInline && TotalSecondaryCost < IC.getCost()) {
+ DEBUG(dbgs() << " NOT Inlining: " << *CS.getInstruction() <<
+ " Cost = " << IC.getCost() <<
", outer Cost = " << TotalSecondaryCost << '\n');
+ emitAnalysis(
+ CS, Twine("Not inlining. Cost of inlining " +
+ CS.getCalledFunction()->getName() +
+ " increases the cost of inlining " +
+ CS.getCaller()->getName() + " in other contexts"));
return false;
}
}
- DEBUG(dbgs() << " Inlining: cost=" << Cost
- << ", thres=" << AdjThreshold
+ DEBUG(dbgs() << " Inlining: cost=" << IC.getCost()
+ << ", thres=" << (IC.getCostDelta() + IC.getCost())
<< ", Call: " << *CS.getInstruction() << '\n');
+ emitAnalysis(
+ CS, CS.getCalledFunction()->getName() + Twine(" can be inlined into ") +
+ CS.getCaller()->getName() + " with cost=" + Twine(IC.getCost()) +
+ " (threshold=" + Twine(IC.getCostDelta() + IC.getCost()) + ")");
return true;
}
-/// InlineHistoryIncludes - Return true if the specified inline history ID
+/// Return true if the specified inline history ID
/// indicates an inline history that includes the specified function.
static bool InlineHistoryIncludes(Function *F, int InlineHistoryID,
const SmallVectorImpl<std::pair<Function*, int> > &InlineHistory) {
return false;
}
-
bool Inliner::runOnSCC(CallGraphSCC &SCC) {
- CallGraph &CG = getAnalysis<CallGraph>();
- const TargetData *TD = getAnalysisIfAvailable<TargetData>();
+ CallGraph &CG = getAnalysis<CallGraphWrapperPass>().getCallGraph();
+ AssumptionCacheTracker *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, TD);
-
+ 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.
bool Changed = false;
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())) {
+ 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.
CG[Caller]->removeCallEdgeFor(CS);
CS.getInstruction()->eraseFromParent();
++NumCallsDeleted;
- // Update the cached cost info with the missing call
- growCachedCostInfo(Caller, NULL);
} else {
// We can only inline direct calls to non-declarations.
- if (Callee == 0 || Callee->isDeclaration()) continue;
+ if (!Callee || Callee->isDeclaration()) continue;
// If this call site was obtained by inlining another function, verify
// that the include path for the function did not include the callee
InlineHistoryIncludes(Callee, InlineHistoryID, InlineHistory))
continue;
-
+ LLVMContext &CallerCtx = Caller->getContext();
+
+ // Get DebugLoc to report. CS will be invalid after Inliner.
+ DebugLoc DLoc = CS.getInstruction()->getDebugLoc();
+
// If the policy determines that we should inline this function,
// try to do so.
- if (!shouldInline(CS))
+ if (!shouldInline(CS)) {
+ emitOptimizationRemarkMissed(CallerCtx, DEBUG_TYPE, *Caller, DLoc,
+ Twine(Callee->getName() +
+ " will not be inlined into " +
+ Caller->getName()));
continue;
+ }
// Attempt to inline the function.
- if (!InlineCallIfPossible(CS, InlineInfo, InlinedArrayAllocas,
- InlineHistoryID, InsertLifetime))
+ if (!InlineCallIfPossible(*this, CS, InlineInfo, InlinedArrayAllocas,
+ InlineHistoryID, InsertLifetime)) {
+ emitOptimizationRemarkMissed(CallerCtx, DEBUG_TYPE, *Caller, DLoc,
+ Twine(Callee->getName() +
+ " will not be inlined into " +
+ Caller->getName()));
continue;
+ }
++NumInlined;
-
+
+ // Report the inline decision.
+ emitOptimizationRemark(
+ CallerCtx, DEBUG_TYPE, *Caller, DLoc,
+ Twine(Callee->getName() + " inlined into " + Caller->getName()));
+
// If inlining this function gave us any new call sites, throw them
// onto our worklist to process. They are useful inline candidates.
if (!InlineInfo.InlinedCalls.empty()) {
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));
- }
}
-
- // Update the cached cost info with the inlined call.
- growCachedCostInfo(Caller, Callee);
}
// If we inlined or deleted the last possible call site to the function,
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();
- resetCachedCostInfo(Callee);
-
// Removing the node for callee from the call graph and delete it.
delete CG.removeFunctionFromModule(CalleeNode);
++NumDeleted;
return Changed;
}
-// doFinalization - Remove now-dead linkonce functions at the end of
-// processing to avoid breaking the SCC traversal.
+/// Remove now-dead linkonce functions at the end of
+/// processing to avoid breaking the SCC traversal.
bool Inliner::doFinalization(CallGraph &CG) {
return removeDeadFunctions(CG);
}
-/// removeDeadFunctions - Remove dead functions that are not included in
-/// DNR (Do Not Remove) list.
-bool Inliner::removeDeadFunctions(CallGraph &CG,
- SmallPtrSet<const Function *, 16> *DNR) {
- SmallPtrSet<CallGraphNode*, 16> FunctionsToRemove;
+/// Remove dead functions that are not included in DNR (Do Not Remove) list.
+bool Inliner::removeDeadFunctions(CallGraph &CG, bool AlwaysInlineOnly) {
+ SmallVector<CallGraphNode*, 16> FunctionsToRemove;
+ SmallVector<CallGraphNode *, 16> DeadFunctionsInComdats;
+ SmallDenseMap<const Comdat *, int, 16> ComdatEntriesAlive;
+
+ auto RemoveCGN = [&](CallGraphNode *CGN) {
+ // Remove any call graph edges from the function to its callees.
+ CGN->removeAllCalledFunctions();
+
+ // Remove any edges from the external node to the function's call graph
+ // node. These edges might have been made irrelegant due to
+ // optimization of the program.
+ CG.getExternalCallingNode()->removeAnyCallEdgeTo(CGN);
+
+ // Removing the node for callee from the call graph and delete it.
+ FunctionsToRemove.push_back(CGN);
+ };
// 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;
- if (CGN->getFunction() == 0)
- continue;
-
+ for (const auto &I : CG) {
+ CallGraphNode *CGN = I.second.get();
Function *F = CGN->getFunction();
-
+ if (!F || F->isDeclaration())
+ continue;
+
+ // Handle the case when this function is called and we only want to care
+ // about always-inline functions. This is a bit of a hack to share code
+ // between here and the InlineAlways pass.
+ if (AlwaysInlineOnly && !F->hasFnAttribute(Attribute::AlwaysInline))
+ continue;
+
// If the only remaining users of the function are dead constants, remove
// them.
F->removeDeadConstantUsers();
- if (DNR && DNR->count(F))
- continue;
if (!F->isDefTriviallyDead())
continue;
-
- // Remove any call graph edges from the function to its callees.
- CGN->removeAllCalledFunctions();
- // Remove any edges from the external node to the function's call graph
- // node. These edges might have been made irrelegant due to
- // optimization of the program.
- CG.getExternalCallingNode()->removeAnyCallEdgeTo(CGN);
+ // It is unsafe to drop a function with discardable linkage from a COMDAT
+ // without also dropping the other members of the COMDAT.
+ // The inliner doesn't visit non-function entities which are in COMDAT
+ // groups so it is unsafe to do so *unless* the linkage is local.
+ if (!F->hasLocalLinkage()) {
+ if (const Comdat *C = F->getComdat()) {
+ --ComdatEntriesAlive[C];
+ DeadFunctionsInComdats.push_back(CGN);
+ continue;
+ }
+ }
- // Removing the node for callee from the call graph and delete it.
- FunctionsToRemove.insert(CGN);
+ RemoveCGN(CGN);
+ }
+ if (!DeadFunctionsInComdats.empty()) {
+ // Count up all the entities in COMDAT groups
+ auto ComdatGroupReferenced = [&](const Comdat *C) {
+ auto I = ComdatEntriesAlive.find(C);
+ if (I != ComdatEntriesAlive.end())
+ ++(I->getSecond());
+ };
+ for (const Function &F : CG.getModule())
+ if (const Comdat *C = F.getComdat())
+ ComdatGroupReferenced(C);
+ for (const GlobalVariable &GV : CG.getModule().globals())
+ if (const Comdat *C = GV.getComdat())
+ ComdatGroupReferenced(C);
+ for (const GlobalAlias &GA : CG.getModule().aliases())
+ if (const Comdat *C = GA.getComdat())
+ ComdatGroupReferenced(C);
+ for (CallGraphNode *CGN : DeadFunctionsInComdats) {
+ Function *F = CGN->getFunction();
+ const Comdat *C = F->getComdat();
+ int NumAlive = ComdatEntriesAlive[C];
+ // We can remove functions in a COMDAT group if the entire group is dead.
+ assert(NumAlive >= 0);
+ if (NumAlive > 0)
+ continue;
+
+ RemoveCGN(CGN);
+ }
}
+ if (FunctionsToRemove.empty())
+ return false;
+
// Now that we know which functions to delete, do so. We didn't want to do
// this inline, because that would invalidate our CallGraph::iterator
// objects. :(
//
- // Note that it doesn't matter that we are iterating over a non-stable set
+ // Note that it doesn't matter that we are iterating over a non-stable order
// here to do this, it doesn't matter which order the functions are deleted
// in.
- bool Changed = false;
- for (SmallPtrSet<CallGraphNode*, 16>::iterator I = FunctionsToRemove.begin(),
- E = FunctionsToRemove.end(); I != E; ++I) {
- resetCachedCostInfo((*I)->getFunction());
- delete CG.removeFunctionFromModule(*I);
+ array_pod_sort(FunctionsToRemove.begin(), FunctionsToRemove.end());
+ FunctionsToRemove.erase(std::unique(FunctionsToRemove.begin(),
+ FunctionsToRemove.end()),
+ FunctionsToRemove.end());
+ for (CallGraphNode *CGN : FunctionsToRemove) {
+ delete CG.removeFunctionFromModule(CGN);
++NumDeleted;
- Changed = true;
}
-
- return Changed;
+ return true;
}
projects / oota-llvm.git / blobdiff