diff options
Diffstat (limited to 'llvm/lib/Transforms/Scalar/DFAJumpThreading.cpp')
| -rw-r--r-- | llvm/lib/Transforms/Scalar/DFAJumpThreading.cpp | 38 |
1 files changed, 33 insertions, 5 deletions
diff --git a/llvm/lib/Transforms/Scalar/DFAJumpThreading.cpp b/llvm/lib/Transforms/Scalar/DFAJumpThreading.cpp index 66e45ec..e84ca81 100644 --- a/llvm/lib/Transforms/Scalar/DFAJumpThreading.cpp +++ b/llvm/lib/Transforms/Scalar/DFAJumpThreading.cpp @@ -122,16 +122,22 @@ static cl::opt<unsigned> cl::desc("Maximum cost accepted for the transformation"), cl::Hidden, cl::init(50)); -extern cl::opt<bool> ProfcheckDisableMetadataFixes; - -} // namespace llvm - static cl::opt<double> MaxClonedRate( "dfa-max-cloned-rate", cl::desc( "Maximum cloned instructions rate accepted for the transformation"), cl::Hidden, cl::init(7.5)); +static cl::opt<unsigned> + MaxOuterUseBlocks("dfa-max-out-use-blocks", + cl::desc("Maximum unduplicated blocks with outer uses " + "accepted for the transformation"), + cl::Hidden, cl::init(40)); + +extern cl::opt<bool> ProfcheckDisableMetadataFixes; + +} // namespace llvm + namespace { class SelectInstToUnfold { SelectInst *SI; @@ -965,8 +971,16 @@ private: // SLPVectorizer. // TODO: Thread the switch partially before reaching the threshold. uint64_t NumOrigInst = 0; - for (auto *BB : DuplicateMap.keys()) + uint64_t NumOuterUseBlock = 0; + for (auto *BB : DuplicateMap.keys()) { NumOrigInst += BB->sizeWithoutDebug(); + // Only unduplicated blocks with single predecessor require new phi + // nodes. + for (auto *Succ : successors(BB)) + if (!DuplicateMap.count(Succ) && Succ->getSinglePredecessor()) + NumOuterUseBlock++; + } + if (double(NumClonedInst) / double(NumOrigInst) > MaxClonedRate) { LLVM_DEBUG(dbgs() << "DFA Jump Threading: Not jump threading, too much " "instructions wll be cloned\n"); @@ -977,6 +991,20 @@ private: return false; } + // Too much unduplicated blocks with outer uses may cause too much + // insertions of phi nodes for duplicated definitions. TODO: Drop this + // threshold if we come up with another way to reduce the number of inserted + // phi nodes. + if (NumOuterUseBlock > MaxOuterUseBlocks) { + LLVM_DEBUG(dbgs() << "DFA Jump Threading: Not jump threading, too much " + "blocks with outer uses\n"); + ORE->emit([&]() { + return OptimizationRemarkMissed(DEBUG_TYPE, "NotProfitable", Switch) + << "Too much blocks with outer uses."; + }); + return false; + } + InstructionCost DuplicationCost = 0; unsigned JumpTableSize = 0; |
