bool PartialInlinerImpl::shouldPartialInline(
CallSite CS, FunctionCloner &Cloner, BlockFrequency WeightedOutliningRcost,
OptimizationRemarkEmitter &ORE) {
using namespace ore;
if (SkipCostAnalysis)
return true;
Instruction *Call = CS.getInstruction();
Function *Callee = CS.getCalledFunction();
assert(Callee == Cloner.ClonedFunc);
Function *Caller = CS.getCaller();
auto &CalleeTTI = (*GetTTI)(*Callee);
InlineCost IC = getInlineCost(CS, getInlineParams(), CalleeTTI,
*GetAssumptionCache, GetBFI, PSI, &ORE);
if (IC.isAlways()) {
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, "AlwaysInline", Call)
<< NV("Callee", Cloner.OrigFunc)
<< " should always be fully inlined, not partially");
return false;
}
if (IC.isNever()) {
ORE.emit(OptimizationRemarkMissed(DEBUG_TYPE, "NeverInline", Call)
<< NV("Callee", Cloner.OrigFunc) << " not partially inlined into "
<< NV("Caller", Caller)
<< " because it should never be inlined (cost=never)");
return false;
}
if (!IC) {
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, "TooCostly", Call)
<< NV("Callee", Cloner.OrigFunc) << " not partially inlined into "
<< NV("Caller", Caller) << " because too costly to inline (cost="
<< NV("Cost", IC.getCost()) << ", threshold="
<< NV("Threshold", IC.getCostDelta() + IC.getCost()) << ")");
return false;
}
const DataLayout &DL = Caller->getParent()->getDataLayout();
// The savings of eliminating the call:
int NonWeightedSavings = getCallsiteCost(CS, DL);
BlockFrequency NormWeightedSavings(NonWeightedSavings);
// Weighted saving is smaller than weighted cost, return false
if (NormWeightedSavings < WeightedOutliningRcost) {
ORE.emit(
OptimizationRemarkAnalysis(DEBUG_TYPE, "OutliningCallcostTooHigh", Call)
<< NV("Callee", Cloner.OrigFunc) << " not partially inlined into "
<< NV("Caller", Caller) << " runtime overhead (overhead="
<< NV("Overhead", (unsigned)WeightedOutliningRcost.getFrequency())
<< ", savings="
<< NV("Savings", (unsigned)NormWeightedSavings.getFrequency()) << ")"
<< " of making the outlined call is too high");
return false;
}
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, "CanBePartiallyInlined", Call)
<< NV("Callee", Cloner.OrigFunc) << " can be partially inlined into "
<< NV("Caller", Caller) << " with cost=" << NV("Cost", IC.getCost())
<< " (threshold="
<< NV("Threshold", IC.getCostDelta() + IC.getCost()) << ")");
return true;
}
/// 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;
}
Function *Caller = CS.getCaller();
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 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;
// 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 = Caller->hasLocalLinkage();
// This bool tracks what happens if we DO inline C into B.
bool inliningPreventsSomeOuterInline = false;
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
// from being removed.
if (!CS2 || CS2.getCalledFunction() != Caller) {
callerWillBeRemoved = false;
continue;
}
InlineCost IC2 = getInlineCost(CS2);
++NumCallerCallersAnalyzed;
if (!IC2) {
callerWillBeRemoved = false;
continue;
}
if (IC2.isAlways())
continue;
// 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 += 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_empty())
TotalSecondaryCost += InlineConstants::LastCallToStaticBonus;
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=" << 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;
}
/// Return true if the inliner should attempt to inline at the given CallSite.
static bool shouldInline(CallSite CS,
function_ref<InlineCost(CallSite CS)> GetInlineCost,
OptimizationRemarkEmitter &ORE) {
using namespace ore;
InlineCost IC = GetInlineCost(CS);
Instruction *Call = CS.getInstruction();
Function *Callee = CS.getCalledFunction();
if (IC.isAlways()) {
DEBUG(dbgs() << " Inlining: cost=always"
<< ", Call: " << *CS.getInstruction() << "\n");
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, "AlwaysInline", Call)
<< NV("Callee", Callee)
<< " should always be inlined (cost=always)");
return true;
}
if (IC.isNever()) {
DEBUG(dbgs() << " NOT Inlining: cost=never"
<< ", Call: " << *CS.getInstruction() << "\n");
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, "NeverInline", Call)
<< NV("Callee", Callee)
<< " should never be inlined (cost=never)");
return false;
}
Function *Caller = CS.getCaller();
if (!IC) {
DEBUG(dbgs() << " NOT Inlining: cost=" << IC.getCost()
<< ", thres=" << (IC.getCostDelta() + IC.getCost())
<< ", Call: " << *CS.getInstruction() << "\n");
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, "TooCostly", Call)
<< NV("Callee", Callee) << " too costly to inline (cost="
<< NV("Cost", IC.getCost()) << ", threshold="
<< NV("Threshold", IC.getCostDelta() + IC.getCost()) << ")");
return false;
}
int TotalSecondaryCost = 0;
if (shouldBeDeferred(Caller, CS, IC, TotalSecondaryCost, GetInlineCost)) {
DEBUG(dbgs() << " NOT Inlining: " << *CS.getInstruction()
<< " Cost = " << IC.getCost()
<< ", outer Cost = " << TotalSecondaryCost << '\n');
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE,
"IncreaseCostInOtherContexts", Call)
<< "Not inlining. Cost of inlining " << NV("Callee", Callee)
<< " increases the cost of inlining " << NV("Caller", Caller)
<< " in other contexts");
return false;
}
DEBUG(dbgs() << " Inlining: cost=" << IC.getCost()
<< ", thres=" << (IC.getCostDelta() + IC.getCost())
<< ", Call: " << *CS.getInstruction() << '\n');
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, "CanBeInlined", Call)
<< NV("Callee", Callee) << " can be inlined into "
<< NV("Caller", Caller) << " with cost=" << NV("Cost", IC.getCost())
<< " (threshold="
<< NV("Threshold", IC.getCostDelta() + IC.getCost()) << ")");
return true;
}