/// Return adjusted total frequency of \p BBs.
///
/// * If there is only one BB, sinking instruction will not introduce code
/// size increase. Thus there is no need to adjust the frequency.
/// * If there are more than one BB, sinking would lead to code size increase.
/// In this case, we add some "tax" to the total frequency to make it harder
/// to sink. E.g.
/// Freq(Preheader) = 100
/// Freq(BBs) = sum(50, 49) = 99
/// Even if Freq(BBs) < Freq(Preheader), we will not sink from Preheade to
/// BBs as the difference is too small to justify the code size increase.
/// To model this, The adjusted Freq(BBs) will be:
/// AdjustedFreq(BBs) = 99 / SinkFrequencyPercentThreshold%
static BlockFrequency adjustedSumFreq(SmallPtrSetImpl<BasicBlock *> &BBs,
BlockFrequencyInfo &BFI) {
BlockFrequency T = 0;
for (BasicBlock *B : BBs)
T += BFI.getBlockFreq(B);
if (BBs.size() > 1)
T /= BranchProbability(SinkFrequencyPercentThreshold, 100);
return T;
}
/// Merge an autorelease with a retain into a fused call.
bool ObjCARCContract::contractAutorelease(
Function &F, Instruction *Autorelease, ARCInstKind Class,
SmallPtrSetImpl<Instruction *> &DependingInstructions,
SmallPtrSetImpl<const BasicBlock *> &Visited) {
const Value *Arg = GetArgRCIdentityRoot(Autorelease);
// Check that there are no instructions between the retain and the autorelease
// (such as an autorelease_pop) which may change the count.
CallInst *Retain = nullptr;
if (Class == ARCInstKind::AutoreleaseRV)
FindDependencies(RetainAutoreleaseRVDep, Arg,
Autorelease->getParent(), Autorelease,
DependingInstructions, Visited, PA);
else
FindDependencies(RetainAutoreleaseDep, Arg,
Autorelease->getParent(), Autorelease,
DependingInstructions, Visited, PA);
Visited.clear();
if (DependingInstructions.size() != 1) {
DependingInstructions.clear();
return false;
}
Retain = dyn_cast_or_null<CallInst>(*DependingInstructions.begin());
DependingInstructions.clear();
if (!Retain || GetBasicARCInstKind(Retain) != ARCInstKind::Retain ||
GetArgRCIdentityRoot(Retain) != Arg)
return false;
Changed = true;
++NumPeeps;
LLVM_DEBUG(dbgs() << " Fusing retain/autorelease!\n"
" Autorelease:"
<< *Autorelease
<< "\n"
" Retain: "
<< *Retain << "\n");
Function *Decl = EP.get(Class == ARCInstKind::AutoreleaseRV
? ARCRuntimeEntryPointKind::RetainAutoreleaseRV
: ARCRuntimeEntryPointKind::RetainAutorelease);
Retain->setCalledFunction(Decl);
LLVM_DEBUG(dbgs() << " New RetainAutorelease: " << *Retain << "\n");
EraseInstruction(Autorelease);
return true;
}
/// Return a set of basic blocks to insert sinked instructions.
///
/// The returned set of basic blocks (BBsToSinkInto) should satisfy:
///
/// * Inside the loop \p L
/// * For each UseBB in \p UseBBs, there is at least one BB in BBsToSinkInto
/// that domintates the UseBB
/// * Has minimum total frequency that is no greater than preheader frequency
///
/// The purpose of the function is to find the optimal sinking points to
/// minimize execution cost, which is defined as "sum of frequency of
/// BBsToSinkInto".
/// As a result, the returned BBsToSinkInto needs to have minimum total
/// frequency.
/// Additionally, if the total frequency of BBsToSinkInto exceeds preheader
/// frequency, the optimal solution is not sinking (return empty set).
///
/// \p ColdLoopBBs is used to help find the optimal sinking locations.
/// It stores a list of BBs that is:
///
/// * Inside the loop \p L
/// * Has a frequency no larger than the loop's preheader
/// * Sorted by BB frequency
///
/// The complexity of the function is O(UseBBs.size() * ColdLoopBBs.size()).
/// To avoid expensive computation, we cap the maximum UseBBs.size() in its
/// caller.
static SmallPtrSet<BasicBlock *, 2>
findBBsToSinkInto(const Loop &L, const SmallPtrSetImpl<BasicBlock *> &UseBBs,
const SmallVectorImpl<BasicBlock *> &ColdLoopBBs,
DominatorTree &DT, BlockFrequencyInfo &BFI) {
SmallPtrSet<BasicBlock *, 2> BBsToSinkInto;
if (UseBBs.size() == 0)
return BBsToSinkInto;
BBsToSinkInto.insert(UseBBs.begin(), UseBBs.end());
SmallPtrSet<BasicBlock *, 2> BBsDominatedByColdestBB;
// For every iteration:
// * Pick the ColdestBB from ColdLoopBBs
// * Find the set BBsDominatedByColdestBB that satisfy:
// - BBsDominatedByColdestBB is a subset of BBsToSinkInto
// - Every BB in BBsDominatedByColdestBB is dominated by ColdestBB
// * If Freq(ColdestBB) < Freq(BBsDominatedByColdestBB), remove
// BBsDominatedByColdestBB from BBsToSinkInto, add ColdestBB to
// BBsToSinkInto
for (BasicBlock *ColdestBB : ColdLoopBBs) {
BBsDominatedByColdestBB.clear();
for (BasicBlock *SinkedBB : BBsToSinkInto)
if (DT.dominates(ColdestBB, SinkedBB))
BBsDominatedByColdestBB.insert(SinkedBB);
if (BBsDominatedByColdestBB.size() == 0)
continue;
if (adjustedSumFreq(BBsDominatedByColdestBB, BFI) >
BFI.getBlockFreq(ColdestBB)) {
for (BasicBlock *DominatedBB : BBsDominatedByColdestBB) {
BBsToSinkInto.erase(DominatedBB);
}
BBsToSinkInto.insert(ColdestBB);
}
}
// If the total frequency of BBsToSinkInto is larger than preheader frequency,
// do not sink.
if (adjustedSumFreq(BBsToSinkInto, BFI) >
BFI.getBlockFreq(L.getLoopPreheader()))
BBsToSinkInto.clear();
return BBsToSinkInto;
}
