//
//===----------------------------------------------------------------------===//
-#include "llvm/Transforms/Scalar.h"
+#include "llvm/Transforms/Scalar/EarlyCSE.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/ScopedHashTable.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Instructions.h"
#include "llvm/Pass.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/RecyclingAllocator.h"
-#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/Local.h"
#include <deque>
using namespace llvm;
STATISTIC(NumCSECall, "Number of call instructions CSE'd");
STATISTIC(NumDSE, "Number of trivial dead stores removed");
-static unsigned getHash(const void *V) {
- return DenseMapInfo<const void*>::getHashValue(V);
-}
-
//===----------------------------------------------------------------------===//
// SimpleValue
//===----------------------------------------------------------------------===//
unsigned DenseMapInfo<CallValue>::getHashValue(CallValue Val) {
Instruction *Inst = Val.Inst;
- // Hash in all of the operands as pointers.
- unsigned Res = 0;
- for (unsigned i = 0, e = Inst->getNumOperands(); i != e; ++i) {
- assert(!Inst->getOperand(i)->getType()->isMetadataTy() &&
- "Cannot value number calls with metadata operands");
- Res ^= getHash(Inst->getOperand(i)) << (i & 0xF);
- }
-
- // Mix in the opcode.
- return (Res << 1) ^ Inst->getOpcode();
+ // Hash all of the operands as pointers and mix in the opcode.
+ return hash_combine(
+ Inst->getOpcode(),
+ hash_combine_range(Inst->value_op_begin(), Inst->value_op_end()));
}
bool DenseMapInfo<CallValue>::isEqual(CallValue LHS, CallValue RHS) {
}
//===----------------------------------------------------------------------===//
-// EarlyCSE pass.
+// EarlyCSE implementation
//===----------------------------------------------------------------------===//
namespace {
-
/// \brief A simple and fast domtree-based CSE pass.
///
/// This pass does a simple depth-first walk over the dominator tree,
/// canonicalize things as it goes. It is intended to be fast and catch obvious
/// cases so that instcombine and other passes are more effective. It is
/// expected that a later pass of GVN will catch the interesting/hard cases.
-class EarlyCSE : public FunctionPass {
+class EarlyCSE {
public:
- const DataLayout *DL;
- const TargetLibraryInfo *TLI;
- DominatorTree *DT;
- AssumptionCache *AC;
+ Function &F;
+ const TargetLibraryInfo &TLI;
+ const TargetTransformInfo &TTI;
+ DominatorTree &DT;
+ AssumptionCache &AC;
typedef RecyclingAllocator<
BumpPtrAllocator, ScopedHashTableVal<SimpleValue, Value *>> AllocatorTy;
typedef ScopedHashTable<SimpleValue, Value *, DenseMapInfo<SimpleValue>,
/// As we walk down the domtree, we look to see if instructions are in this:
/// if so, we replace them with what we find, otherwise we insert them so
/// that dominated values can succeed in their lookup.
- ScopedHTType *AvailableValues;
+ ScopedHTType AvailableValues;
/// \brief A scoped hash table of the current values of loads.
///
LoadMapAllocator;
typedef ScopedHashTable<Value *, std::pair<Value *, unsigned>,
DenseMapInfo<Value *>, LoadMapAllocator> LoadHTType;
- LoadHTType *AvailableLoads;
+ LoadHTType AvailableLoads;
/// \brief A scoped hash table of the current values of read-only call
/// values.
///
/// It uses the same generation count as loads.
typedef ScopedHashTable<CallValue, std::pair<Value *, unsigned>> CallHTType;
- CallHTType *AvailableCalls;
+ CallHTType AvailableCalls;
/// \brief This is the current generation of the memory value.
unsigned CurrentGeneration;
- static char ID;
- explicit EarlyCSE() : FunctionPass(ID) {
- initializeEarlyCSEPass(*PassRegistry::getPassRegistry());
- }
+ /// \brief Set up the EarlyCSE runner for a particular function.
+ EarlyCSE(Function &F, const TargetLibraryInfo &TLI,
+ const TargetTransformInfo &TTI, DominatorTree &DT,
+ AssumptionCache &AC)
+ : F(F), TLI(TLI), TTI(TTI), DT(DT), AC(AC), CurrentGeneration(0) {}
- bool runOnFunction(Function &F) override;
+ bool run();
private:
// Almost a POD, but needs to call the constructors for the scoped hash
// scope gets popped when the NodeScope is destroyed.
class NodeScope {
public:
- NodeScope(ScopedHTType *availableValues, LoadHTType *availableLoads,
- CallHTType *availableCalls)
- : Scope(*availableValues), LoadScope(*availableLoads),
- CallScope(*availableCalls) {}
+ NodeScope(ScopedHTType &AvailableValues, LoadHTType &AvailableLoads,
+ CallHTType &AvailableCalls)
+ : Scope(AvailableValues), LoadScope(AvailableLoads),
+ CallScope(AvailableCalls) {}
private:
- NodeScope(const NodeScope &) LLVM_DELETED_FUNCTION;
- void operator=(const NodeScope &) LLVM_DELETED_FUNCTION;
+ NodeScope(const NodeScope &) = delete;
+ void operator=(const NodeScope &) = delete;
ScopedHTType::ScopeTy Scope;
LoadHTType::ScopeTy LoadScope;
// children do not need to be store spearately.
class StackNode {
public:
- StackNode(ScopedHTType *availableValues, LoadHTType *availableLoads,
- CallHTType *availableCalls, unsigned cg, DomTreeNode *n,
+ StackNode(ScopedHTType &AvailableValues, LoadHTType &AvailableLoads,
+ CallHTType &AvailableCalls, unsigned cg, DomTreeNode *n,
DomTreeNode::iterator child, DomTreeNode::iterator end)
: CurrentGeneration(cg), ChildGeneration(cg), Node(n), ChildIter(child),
- EndIter(end), Scopes(availableValues, availableLoads, availableCalls),
+ EndIter(end), Scopes(AvailableValues, AvailableLoads, AvailableCalls),
Processed(false) {}
// Accessors.
void process() { Processed = true; }
private:
- StackNode(const StackNode &) LLVM_DELETED_FUNCTION;
- void operator=(const StackNode &) LLVM_DELETED_FUNCTION;
+ StackNode(const StackNode &) = delete;
+ void operator=(const StackNode &) = delete;
// Members.
unsigned CurrentGeneration;
bool Processed;
};
+ /// \brief Wrapper class to handle memory instructions, including loads,
+ /// stores and intrinsic loads and stores defined by the target.
+ class ParseMemoryInst {
+ public:
+ ParseMemoryInst(Instruction *Inst, const TargetTransformInfo &TTI)
+ : Load(false), Store(false), Vol(false), MayReadFromMemory(false),
+ MayWriteToMemory(false), MatchingId(-1), Ptr(nullptr) {
+ MayReadFromMemory = Inst->mayReadFromMemory();
+ MayWriteToMemory = Inst->mayWriteToMemory();
+ if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(Inst)) {
+ MemIntrinsicInfo Info;
+ if (!TTI.getTgtMemIntrinsic(II, Info))
+ return;
+ if (Info.NumMemRefs == 1) {
+ Store = Info.WriteMem;
+ Load = Info.ReadMem;
+ MatchingId = Info.MatchingId;
+ MayReadFromMemory = Info.ReadMem;
+ MayWriteToMemory = Info.WriteMem;
+ Vol = Info.Vol;
+ Ptr = Info.PtrVal;
+ }
+ } else if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
+ Load = true;
+ Vol = !LI->isSimple();
+ Ptr = LI->getPointerOperand();
+ } else if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
+ Store = true;
+ Vol = !SI->isSimple();
+ Ptr = SI->getPointerOperand();
+ }
+ }
+ bool isLoad() { return Load; }
+ bool isStore() { return Store; }
+ bool isVolatile() { return Vol; }
+ bool isMatchingMemLoc(const ParseMemoryInst &Inst) {
+ return Ptr == Inst.Ptr && MatchingId == Inst.MatchingId;
+ }
+ bool isValid() { return Ptr != nullptr; }
+ int getMatchingId() { return MatchingId; }
+ Value *getPtr() { return Ptr; }
+ bool mayReadFromMemory() { return MayReadFromMemory; }
+ bool mayWriteToMemory() { return MayWriteToMemory; }
+
+ private:
+ bool Load;
+ bool Store;
+ bool Vol;
+ bool MayReadFromMemory;
+ bool MayWriteToMemory;
+ // For regular (non-intrinsic) loads/stores, this is set to -1. For
+ // intrinsic loads/stores, the id is retrieved from the corresponding
+ // field in the MemIntrinsicInfo structure. That field contains
+ // non-negative values only.
+ int MatchingId;
+ Value *Ptr;
+ };
+
bool processNode(DomTreeNode *Node);
- void getAnalysisUsage(AnalysisUsage &AU) const override {
- AU.addRequired<AssumptionCacheTracker>();
- AU.addRequired<DominatorTreeWrapperPass>();
- AU.addRequired<TargetLibraryInfoWrapperPass>();
- AU.setPreservesCFG();
+ Value *getOrCreateResult(Value *Inst, Type *ExpectedType) const {
+ if (LoadInst *LI = dyn_cast<LoadInst>(Inst))
+ return LI;
+ else if (StoreInst *SI = dyn_cast<StoreInst>(Inst))
+ return SI->getValueOperand();
+ assert(isa<IntrinsicInst>(Inst) && "Instruction not supported");
+ return TTI.getOrCreateResultFromMemIntrinsic(cast<IntrinsicInst>(Inst),
+ ExpectedType);
}
};
}
-char EarlyCSE::ID = 0;
-
-FunctionPass *llvm::createEarlyCSEPass() { return new EarlyCSE(); }
-
-INITIALIZE_PASS_BEGIN(EarlyCSE, "early-cse", "Early CSE", false, false)
-INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
-INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
-INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
-INITIALIZE_PASS_END(EarlyCSE, "early-cse", "Early CSE", false, false)
-
bool EarlyCSE::processNode(DomTreeNode *Node) {
BasicBlock *BB = Node->getBlock();
if (!BB->getSinglePredecessor())
++CurrentGeneration;
+ // If this node has a single predecessor which ends in a conditional branch,
+ // we can infer the value of the branch condition given that we took this
+ // path. We need the single predeccesor to ensure there's not another path
+ // which reaches this block where the condition might hold a different
+ // value. Since we're adding this to the scoped hash table (like any other
+ // def), it will have been popped if we encounter a future merge block.
+ if (BasicBlock *Pred = BB->getSinglePredecessor())
+ if (auto *BI = dyn_cast<BranchInst>(Pred->getTerminator()))
+ if (BI->isConditional())
+ if (auto *CondInst = dyn_cast<Instruction>(BI->getCondition()))
+ if (SimpleValue::canHandle(CondInst)) {
+ assert(BI->getSuccessor(0) == BB || BI->getSuccessor(1) == BB);
+ auto *ConditionalConstant = (BI->getSuccessor(0) == BB) ?
+ ConstantInt::getTrue(BB->getContext()) :
+ ConstantInt::getFalse(BB->getContext());
+ AvailableValues.insert(CondInst, ConditionalConstant);
+ DEBUG(dbgs() << "EarlyCSE CVP: Add conditional value for '"
+ << CondInst->getName() << "' as " << *ConditionalConstant
+ << " in " << BB->getName() << "\n");
+ // Replace all dominated uses with the known value
+ replaceDominatedUsesWith(CondInst, ConditionalConstant, DT,
+ BasicBlockEdge(Pred, BB));
+ }
+
/// LastStore - Keep track of the last non-volatile store that we saw... for
/// as long as there in no instruction that reads memory. If we see a store
/// to the same location, we delete the dead store. This zaps trivial dead
/// stores which can occur in bitfield code among other things.
- StoreInst *LastStore = nullptr;
+ Instruction *LastStore = nullptr;
bool Changed = false;
+ const DataLayout &DL = BB->getModule()->getDataLayout();
// See if any instructions in the block can be eliminated. If so, do it. If
// not, add them to AvailableValues.
Instruction *Inst = I++;
// Dead instructions should just be removed.
- if (isInstructionTriviallyDead(Inst, TLI)) {
+ if (isInstructionTriviallyDead(Inst, &TLI)) {
DEBUG(dbgs() << "EarlyCSE DCE: " << *Inst << '\n');
Inst->eraseFromParent();
Changed = true;
// If the instruction can be simplified (e.g. X+0 = X) then replace it with
// its simpler value.
- if (Value *V = SimplifyInstruction(Inst, DL, TLI, DT, AC)) {
+ if (Value *V = SimplifyInstruction(Inst, DL, &TLI, &DT, &AC)) {
DEBUG(dbgs() << "EarlyCSE Simplify: " << *Inst << " to: " << *V << '\n');
Inst->replaceAllUsesWith(V);
Inst->eraseFromParent();
// If this is a simple instruction that we can value number, process it.
if (SimpleValue::canHandle(Inst)) {
// See if the instruction has an available value. If so, use it.
- if (Value *V = AvailableValues->lookup(Inst)) {
+ if (Value *V = AvailableValues.lookup(Inst)) {
DEBUG(dbgs() << "EarlyCSE CSE: " << *Inst << " to: " << *V << '\n');
Inst->replaceAllUsesWith(V);
Inst->eraseFromParent();
}
// Otherwise, just remember that this value is available.
- AvailableValues->insert(Inst, Inst);
+ AvailableValues.insert(Inst, Inst);
continue;
}
+ ParseMemoryInst MemInst(Inst, TTI);
// If this is a non-volatile load, process it.
- if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
+ if (MemInst.isValid() && MemInst.isLoad()) {
// Ignore volatile loads.
- if (!LI->isSimple()) {
+ if (MemInst.isVolatile()) {
LastStore = nullptr;
+ // Don't CSE across synchronization boundaries.
+ if (Inst->mayWriteToMemory())
+ ++CurrentGeneration;
continue;
}
// If we have an available version of this load, and if it is the right
// generation, replace this instruction.
std::pair<Value *, unsigned> InVal =
- AvailableLoads->lookup(Inst->getOperand(0));
+ AvailableLoads.lookup(MemInst.getPtr());
if (InVal.first != nullptr && InVal.second == CurrentGeneration) {
- DEBUG(dbgs() << "EarlyCSE CSE LOAD: " << *Inst
- << " to: " << *InVal.first << '\n');
- if (!Inst->use_empty())
- Inst->replaceAllUsesWith(InVal.first);
- Inst->eraseFromParent();
- Changed = true;
- ++NumCSELoad;
- continue;
+ Value *Op = getOrCreateResult(InVal.first, Inst->getType());
+ if (Op != nullptr) {
+ DEBUG(dbgs() << "EarlyCSE CSE LOAD: " << *Inst
+ << " to: " << *InVal.first << '\n');
+ if (!Inst->use_empty())
+ Inst->replaceAllUsesWith(Op);
+ Inst->eraseFromParent();
+ Changed = true;
+ ++NumCSELoad;
+ continue;
+ }
}
// Otherwise, remember that we have this instruction.
- AvailableLoads->insert(Inst->getOperand(0), std::pair<Value *, unsigned>(
- Inst, CurrentGeneration));
+ AvailableLoads.insert(MemInst.getPtr(), std::pair<Value *, unsigned>(
+ Inst, CurrentGeneration));
LastStore = nullptr;
continue;
}
// If this instruction may read from memory, forget LastStore.
- if (Inst->mayReadFromMemory())
+ // Load/store intrinsics will indicate both a read and a write to
+ // memory. The target may override this (e.g. so that a store intrinsic
+ // does not read from memory, and thus will be treated the same as a
+ // regular store for commoning purposes).
+ if (Inst->mayReadFromMemory() &&
+ !(MemInst.isValid() && !MemInst.mayReadFromMemory()))
LastStore = nullptr;
// If this is a read-only call, process it.
if (CallValue::canHandle(Inst)) {
// If we have an available version of this call, and if it is the right
// generation, replace this instruction.
- std::pair<Value *, unsigned> InVal = AvailableCalls->lookup(Inst);
+ std::pair<Value *, unsigned> InVal = AvailableCalls.lookup(Inst);
if (InVal.first != nullptr && InVal.second == CurrentGeneration) {
DEBUG(dbgs() << "EarlyCSE CSE CALL: " << *Inst
<< " to: " << *InVal.first << '\n');
}
// Otherwise, remember that we have this instruction.
- AvailableCalls->insert(
+ AvailableCalls.insert(
Inst, std::pair<Value *, unsigned>(Inst, CurrentGeneration));
continue;
}
if (Inst->mayWriteToMemory()) {
++CurrentGeneration;
- if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
+ if (MemInst.isValid() && MemInst.isStore()) {
// We do a trivial form of DSE if there are two stores to the same
// location with no intervening loads. Delete the earlier store.
- if (LastStore &&
- LastStore->getPointerOperand() == SI->getPointerOperand()) {
- DEBUG(dbgs() << "EarlyCSE DEAD STORE: " << *LastStore
- << " due to: " << *Inst << '\n');
- LastStore->eraseFromParent();
- Changed = true;
- ++NumDSE;
- LastStore = nullptr;
+ if (LastStore) {
+ ParseMemoryInst LastStoreMemInst(LastStore, TTI);
+ if (LastStoreMemInst.isMatchingMemLoc(MemInst)) {
+ DEBUG(dbgs() << "EarlyCSE DEAD STORE: " << *LastStore
+ << " due to: " << *Inst << '\n');
+ LastStore->eraseFromParent();
+ Changed = true;
+ ++NumDSE;
+ LastStore = nullptr;
+ }
// fallthrough - we can exploit information about this store
}
// version of the pointer. It is safe to forward from volatile stores
// to non-volatile loads, so we don't have to check for volatility of
// the store.
- AvailableLoads->insert(SI->getPointerOperand(),
- std::pair<Value *, unsigned>(
- SI->getValueOperand(), CurrentGeneration));
+ AvailableLoads.insert(MemInst.getPtr(), std::pair<Value *, unsigned>(
+ Inst, CurrentGeneration));
// Remember that this was the last store we saw for DSE.
- if (SI->isSimple())
- LastStore = SI;
+ if (!MemInst.isVolatile())
+ LastStore = Inst;
}
}
}
return Changed;
}
-bool EarlyCSE::runOnFunction(Function &F) {
- if (skipOptnoneFunction(F))
- return false;
-
+bool EarlyCSE::run() {
// Note, deque is being used here because there is significant performance
// gains over vector when the container becomes very large due to the
// specific access patterns. For more information see the mailing list
// http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20120116/135228.html
std::deque<StackNode *> nodesToProcess;
- DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
- DL = DLP ? &DLP->getDataLayout() : nullptr;
- TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
- DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
- AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
-
- // Tables that the pass uses when walking the domtree.
- ScopedHTType AVTable;
- AvailableValues = &AVTable;
- LoadHTType LoadTable;
- AvailableLoads = &LoadTable;
- CallHTType CallTable;
- AvailableCalls = &CallTable;
-
- CurrentGeneration = 0;
bool Changed = false;
// Process the root node.
nodesToProcess.push_back(new StackNode(
AvailableValues, AvailableLoads, AvailableCalls, CurrentGeneration,
- DT->getRootNode(), DT->getRootNode()->begin(), DT->getRootNode()->end()));
+ DT.getRootNode(), DT.getRootNode()->begin(), DT.getRootNode()->end()));
// Save the current generation.
unsigned LiveOutGeneration = CurrentGeneration;
return Changed;
}
+
+PreservedAnalyses EarlyCSEPass::run(Function &F,
+ AnalysisManager<Function> *AM) {
+ auto &TLI = AM->getResult<TargetLibraryAnalysis>(F);
+ auto &TTI = AM->getResult<TargetIRAnalysis>(F);
+ auto &DT = AM->getResult<DominatorTreeAnalysis>(F);
+ auto &AC = AM->getResult<AssumptionAnalysis>(F);
+
+ EarlyCSE CSE(F, TLI, TTI, DT, AC);
+
+ if (!CSE.run())
+ return PreservedAnalyses::all();
+
+ // CSE preserves the dominator tree because it doesn't mutate the CFG.
+ // FIXME: Bundle this with other CFG-preservation.
+ PreservedAnalyses PA;
+ PA.preserve<DominatorTreeAnalysis>();
+ return PA;
+}
+
+namespace {
+/// \brief A simple and fast domtree-based CSE pass.
+///
+/// This pass does a simple depth-first walk over the dominator tree,
+/// eliminating trivially redundant instructions and using instsimplify to
+/// canonicalize things as it goes. It is intended to be fast and catch obvious
+/// cases so that instcombine and other passes are more effective. It is
+/// expected that a later pass of GVN will catch the interesting/hard cases.
+class EarlyCSELegacyPass : public FunctionPass {
+public:
+ static char ID;
+
+ EarlyCSELegacyPass() : FunctionPass(ID) {
+ initializeEarlyCSELegacyPassPass(*PassRegistry::getPassRegistry());
+ }
+
+ bool runOnFunction(Function &F) override {
+ if (skipOptnoneFunction(F))
+ return false;
+
+ auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
+ auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
+ auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
+ auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
+
+ EarlyCSE CSE(F, TLI, TTI, DT, AC);
+
+ return CSE.run();
+ }
+
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
+ AU.addRequired<AssumptionCacheTracker>();
+ AU.addRequired<DominatorTreeWrapperPass>();
+ AU.addRequired<TargetLibraryInfoWrapperPass>();
+ AU.addRequired<TargetTransformInfoWrapperPass>();
+ AU.setPreservesCFG();
+ }
+};
+}
+
+char EarlyCSELegacyPass::ID = 0;
+
+FunctionPass *llvm::createEarlyCSEPass() { return new EarlyCSELegacyPass(); }
+
+INITIALIZE_PASS_BEGIN(EarlyCSELegacyPass, "early-cse", "Early CSE", false,
+ false)
+INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
+INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
+INITIALIZE_PASS_END(EarlyCSELegacyPass, "early-cse", "Early CSE", false, false)