#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/CFG.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
+#include "llvm/Analysis/BlockFrequencyInfoImpl.h"
+#include "llvm/Analysis/BranchProbabilityInfo.h"
#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/LazyValueInfo.h"
#include "llvm/Analysis/Loads.h"
+#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/ValueHandle.h"
#include "llvm/Pass.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/SSAUpdater.h"
+#include <algorithm>
+#include <memory>
using namespace llvm;
#define DEBUG_TYPE "jump-threading"
cl::desc("Max block size to duplicate for jump threading"),
cl::init(6), cl::Hidden);
+static cl::opt<unsigned>
+ImplicationSearchThreshold(
+ "jump-threading-implication-search-threshold",
+ cl::desc("The number of predecessors to search for a stronger "
+ "condition to use to thread over a weaker condition"),
+ cl::init(3), cl::Hidden);
+
namespace {
// These are at global scope so static functions can use them too.
typedef SmallVectorImpl<std::pair<Constant*, BasicBlock*> > PredValueInfo;
class JumpThreading : public FunctionPass {
TargetLibraryInfo *TLI;
LazyValueInfo *LVI;
+ std::unique_ptr<BlockFrequencyInfo> BFI;
+ std::unique_ptr<BranchProbabilityInfo> BPI;
+ bool HasProfileData;
#ifdef NDEBUG
SmallPtrSet<BasicBlock*, 16> LoopHeaders;
#else
AU.addRequired<TargetLibraryInfoWrapperPass>();
}
+ void releaseMemory() override {
+ BFI.reset();
+ BPI.reset();
+ }
+
void FindLoopHeaders(Function &F);
bool ProcessBlock(BasicBlock *BB);
bool ThreadEdge(BasicBlock *BB, const SmallVectorImpl<BasicBlock*> &PredBBs,
bool ProcessBranchOnPHI(PHINode *PN);
bool ProcessBranchOnXOR(BinaryOperator *BO);
+ bool ProcessImpliedCondition(BasicBlock *BB);
bool SimplifyPartiallyRedundantLoad(LoadInst *LI);
bool TryToUnfoldSelect(CmpInst *CondCmp, BasicBlock *BB);
+
+ private:
+ BasicBlock *SplitBlockPreds(BasicBlock *BB, ArrayRef<BasicBlock *> Preds,
+ const char *Suffix);
+ void UpdateBlockFreqAndEdgeWeight(BasicBlock *PredBB, BasicBlock *BB,
+ BasicBlock *NewBB, BasicBlock *SuccBB);
};
}
DEBUG(dbgs() << "Jump threading on function '" << F.getName() << "'\n");
TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
LVI = &getAnalysis<LazyValueInfo>();
+ BFI.reset();
+ BPI.reset();
+ // When profile data is available, we need to update edge weights after
+ // successful jump threading, which requires both BPI and BFI being available.
+ HasProfileData = F.getEntryCount().hasValue();
+ if (HasProfileData) {
+ LoopInfo LI{DominatorTree(F)};
+ BPI.reset(new BranchProbabilityInfo(F, LI));
+ BFI.reset(new BlockFrequencyInfo(F, *BPI, LI));
+ }
// Remove unreachable blocks from function as they may result in infinite
// loop. We do threading if we found something profitable. Jump threading a
// FIXME: THREADING will delete values that are just used to compute the
// branch, so they shouldn't count against the duplication cost.
+ unsigned Bonus = 0;
+ const TerminatorInst *BBTerm = BB->getTerminator();
+ // Threading through a switch statement is particularly profitable. If this
+ // block ends in a switch, decrease its cost to make it more likely to happen.
+ if (isa<SwitchInst>(BBTerm))
+ Bonus = 6;
+
+ // The same holds for indirect branches, but slightly more so.
+ if (isa<IndirectBrInst>(BBTerm))
+ Bonus = 8;
+
+ // Bump the threshold up so the early exit from the loop doesn't skip the
+ // terminator-based Size adjustment at the end.
+ Threshold += Bonus;
+
// Sum up the cost of each instruction until we get to the terminator. Don't
// include the terminator because the copy won't include it.
unsigned Size = 0;
}
}
- // Threading through a switch statement is particularly profitable. If this
- // block ends in a switch, decrease its cost to make it more likely to happen.
- if (isa<SwitchInst>(I))
- Size = Size > 6 ? Size-6 : 0;
-
- // The same holds for indirect branches, but slightly more so.
- if (isa<IndirectBrInst>(I))
- Size = Size > 8 ? Size-8 : 0;
-
- return Size;
+ return Size > Bonus ? Size - Bonus : 0;
}
/// FindLoopHeaders - We do not want jump threading to turn proper loop
CondInst->getParent() == BB && isa<BranchInst>(BB->getTerminator()))
return ProcessBranchOnXOR(cast<BinaryOperator>(CondInst));
+ // Search for a stronger dominating condition that can be used to simplify a
+ // conditional branch leaving BB.
+ if (ProcessImpliedCondition(BB))
+ return true;
+
+ return false;
+}
+
+bool JumpThreading::ProcessImpliedCondition(BasicBlock *BB) {
+ auto *BI = dyn_cast<BranchInst>(BB->getTerminator());
+ if (!BI || !BI->isConditional())
+ return false;
+
+ Value *Cond = BI->getCondition();
+ BasicBlock *CurrentBB = BB;
+ BasicBlock *CurrentPred = BB->getSinglePredecessor();
+ unsigned Iter = 0;
+
+ auto &DL = BB->getModule()->getDataLayout();
+
+ while (CurrentPred && Iter++ < ImplicationSearchThreshold) {
+ auto *PBI = dyn_cast<BranchInst>(CurrentPred->getTerminator());
+ if (!PBI || !PBI->isConditional() || PBI->getSuccessor(0) != CurrentBB)
+ return false;
- // TODO: If we have: "br (X > 0)" and we have a predecessor where we know
- // "(X == 4)", thread through this block.
+ if (isImpliedCondition(PBI->getCondition(), Cond, DL)) {
+ BI->getSuccessor(1)->removePredecessor(BB);
+ BranchInst::Create(BI->getSuccessor(0), BI);
+ BI->eraseFromParent();
+ return true;
+ }
+ CurrentBB = CurrentPred;
+ CurrentPred = CurrentBB->getSinglePredecessor();
+ }
return false;
}
}
// Split them out to their own block.
- UnavailablePred =
- SplitBlockPredecessors(LoadBB, PredsToSplit, "thread-pre-split");
+ UnavailablePred = SplitBlockPreds(LoadBB, PredsToSplit, "thread-pre-split");
}
// If the value isn't available in all predecessors, then there will be
else {
DEBUG(dbgs() << " Factoring out " << PredBBs.size()
<< " common predecessors.\n");
- PredBB = SplitBlockPredecessors(BB, PredBBs, ".thr_comm");
+ PredBB = SplitBlockPreds(BB, PredBBs, ".thr_comm");
}
// And finally, do it!
BB->getParent(), BB);
NewBB->moveAfter(PredBB);
+ // Set the block frequency of NewBB.
+ if (HasProfileData) {
+ auto NewBBFreq =
+ BFI->getBlockFreq(PredBB) * BPI->getEdgeProbability(PredBB, BB);
+ BFI->setBlockFreq(NewBB, NewBBFreq.getFrequency());
+ }
+
BasicBlock::iterator BI = BB->begin();
for (; PHINode *PN = dyn_cast<PHINode>(BI); ++BI)
ValueMapping[PN] = PN->getIncomingValueForBlock(PredBB);
// We didn't copy the terminator from BB over to NewBB, because there is now
// an unconditional jump to SuccBB. Insert the unconditional jump.
- BranchInst *NewBI =BranchInst::Create(SuccBB, NewBB);
+ BranchInst *NewBI = BranchInst::Create(SuccBB, NewBB);
NewBI->setDebugLoc(BB->getTerminator()->getDebugLoc());
// Check to see if SuccBB has PHI nodes. If so, we need to add entries to the
// frequently happens because of phi translation.
SimplifyInstructionsInBlock(NewBB, TLI);
+ // Update the edge weight from BB to SuccBB, which should be less than before.
+ UpdateBlockFreqAndEdgeWeight(PredBB, BB, NewBB, SuccBB);
+
// Threaded an edge!
++NumThreads;
return true;
}
+/// Create a new basic block that will be the predecessor of BB and successor of
+/// all blocks in Preds. When profile data is availble, update the frequency of
+/// this new block.
+BasicBlock *JumpThreading::SplitBlockPreds(BasicBlock *BB,
+ ArrayRef<BasicBlock *> Preds,
+ const char *Suffix) {
+ // Collect the frequencies of all predecessors of BB, which will be used to
+ // update the edge weight on BB->SuccBB.
+ BlockFrequency PredBBFreq(0);
+ if (HasProfileData)
+ for (auto Pred : Preds)
+ PredBBFreq += BFI->getBlockFreq(Pred) * BPI->getEdgeProbability(Pred, BB);
+
+ BasicBlock *PredBB = SplitBlockPredecessors(BB, Preds, Suffix);
+
+ // Set the block frequency of the newly created PredBB, which is the sum of
+ // frequencies of Preds.
+ if (HasProfileData)
+ BFI->setBlockFreq(PredBB, PredBBFreq.getFrequency());
+ return PredBB;
+}
+
+/// Update the block frequency of BB and branch weight and the metadata on the
+/// edge BB->SuccBB. This is done by scaling the weight of BB->SuccBB by 1 -
+/// Freq(PredBB->BB) / Freq(BB->SuccBB).
+void JumpThreading::UpdateBlockFreqAndEdgeWeight(BasicBlock *PredBB,
+ BasicBlock *BB,
+ BasicBlock *NewBB,
+ BasicBlock *SuccBB) {
+ if (!HasProfileData)
+ return;
+
+ assert(BFI && BPI && "BFI & BPI should have been created here");
+
+ // As the edge from PredBB to BB is deleted, we have to update the block
+ // frequency of BB.
+ auto BBOrigFreq = BFI->getBlockFreq(BB);
+ auto NewBBFreq = BFI->getBlockFreq(NewBB);
+ auto BB2SuccBBFreq = BBOrigFreq * BPI->getEdgeProbability(BB, SuccBB);
+ auto BBNewFreq = BBOrigFreq - NewBBFreq;
+ BFI->setBlockFreq(BB, BBNewFreq.getFrequency());
+
+ // Collect updated outgoing edges' frequencies from BB and use them to update
+ // edge probabilities.
+ SmallVector<uint64_t, 4> BBSuccFreq;
+ for (auto I = succ_begin(BB), E = succ_end(BB); I != E; ++I) {
+ auto SuccFreq = (*I == SuccBB)
+ ? BB2SuccBBFreq - NewBBFreq
+ : BBOrigFreq * BPI->getEdgeProbability(BB, *I);
+ BBSuccFreq.push_back(SuccFreq.getFrequency());
+ }
+
+ uint64_t MaxBBSuccFreq =
+ *std::max_element(BBSuccFreq.begin(), BBSuccFreq.end());
+
+ SmallVector<BranchProbability, 4> BBSuccProbs;
+ if (MaxBBSuccFreq == 0)
+ BBSuccProbs.assign(BBSuccFreq.size(),
+ {1, static_cast<unsigned>(BBSuccFreq.size())});
+ else {
+ for (uint64_t Freq : BBSuccFreq)
+ BBSuccProbs.push_back(
+ BranchProbability::getBranchProbability(Freq, MaxBBSuccFreq));
+ // Normalize edge probabilities so that they sum up to one.
+ BranchProbability::normalizeProbabilities(BBSuccProbs.begin(),
+ BBSuccProbs.end());
+ }
+
+ // Update edge probabilities in BPI.
+ for (int I = 0, E = BBSuccProbs.size(); I < E; I++)
+ BPI->setEdgeProbability(BB, I, BBSuccProbs[I]);
+
+ if (BBSuccProbs.size() >= 2) {
+ SmallVector<uint32_t, 4> Weights;
+ for (auto Prob : BBSuccProbs)
+ Weights.push_back(Prob.getNumerator());
+
+ auto TI = BB->getTerminator();
+ TI->setMetadata(
+ LLVMContext::MD_prof,
+ MDBuilder(TI->getParent()->getContext()).createBranchWeights(Weights));
+ }
+}
+
/// DuplicateCondBranchOnPHIIntoPred - PredBB contains an unconditional branch
/// to BB which contains an i1 PHI node and a conditional branch on that PHI.
/// If we can duplicate the contents of BB up into PredBB do so now, this
else {
DEBUG(dbgs() << " Factoring out " << PredBBs.size()
<< " common predecessors.\n");
- PredBB = SplitBlockPredecessors(BB, PredBBs, ".thr_comm");
+ PredBB = SplitBlockPreds(BB, PredBBs, ".thr_comm");
}
// Okay, we decided to do this! Clone all the instructions in BB onto the end