[MemCpyOptimizer] Preserve analyses and replace use of lambdas to get them.

[asbirlea]

Summary

Analyses are preserved in MemCpyOptimizer.
Get analyses before running the pass and store the pointers, instead of
using lambdas and getting them every time on demand.

[efriedma]

LGTM

llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp

298

These changes make sense.

[asbirlea]

Rebase, update tests.

llvm/include/llvm/Transforms/Scalar/MemCpyOptimizer.h

 class MemSetInst;
 class StoreInst;
 class TargetLibraryInfo;
 class Value;
 
 class MemCpyOptPass : public PassInfoMixin<MemCpyOptPass> {
   MemoryDependenceResults *MD = nullptr;
   TargetLibraryInfo *TLI = nullptr;
-  std::function<AliasAnalysis &()> LookupAliasAnalysis;
-  std::function<AssumptionCache &()> LookupAssumptionCache;
-  std::function<DominatorTree &()> LookupDomTree;
+  AliasAnalysis *AA = nullptr;
+  AssumptionCache *AC = nullptr;
+  DominatorTree *DT = nullptr;
 
 public:
   MemCpyOptPass() = default;
 
   PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
 
   // Glue for the old PM.
   bool runImpl(Function &F, MemoryDependenceResults *MD_,
-               TargetLibraryInfo *TLI_,
-               std::function<AliasAnalysis &()> LookupAliasAnalysis_,
-               std::function<AssumptionCache &()> LookupAssumptionCache_,
-               std::function<DominatorTree &()> LookupDomTree_);
+               TargetLibraryInfo *TLI_, AliasAnalysis *AA_,
+               AssumptionCache *AC_, DominatorTree *DT_);
 
 private:
   // Helper functions
   bool processStore(StoreInst *SI, BasicBlock::iterator &BBI);
   bool processMemSet(MemSetInst *SI, BasicBlock::iterator &BBI);
   bool processMemCpy(MemCpyInst *M);
   bool processMemMove(MemMoveInst *M);
   bool performCallSlotOptzn(Instruction *cpy, Value *cpyDst, Value *cpySrc,

llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp

public:
   bool runOnFunction(Function &F) override;
 
 private:
   // This transformation requires dominator postdominator info
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.setPreservesCFG();
     AU.addRequired<AssumptionCacheTracker>();
     AU.addRequired<DominatorTreeWrapperPass>();
-    AU.addRequired<MemoryDependenceWrapperPass>();
+    AU.addPreserved<DominatorTreeWrapperPass>();
     AU.addRequired<AAResultsWrapperPass>();
-    AU.addRequired<TargetLibraryInfoWrapperPass>();
+    AU.addPreserved<AAResultsWrapperPass>();
     AU.addPreserved<GlobalsAAWrapperPass>();
+    AU.addRequired<TargetLibraryInfoWrapperPass>();
+    AU.addRequired<MemoryDependenceWrapperPass>();
     AU.addPreserved<MemoryDependenceWrapperPass>();
   }
 };
 
 } // end anonymous namespace
 
 char MemCpyOptLegacyPass::ID = 0;
 
 /// The public interface to this file...
bool MemCpyOptPass::processStore(StoreInst *SI, BasicBlock::iterator &BBI) {
 
   // Load to store forwarding can be interpreted as memcpy.
   if (LoadInst *LI = dyn_cast<LoadInst>(SI->getOperand(0))) {
     if (LI->isSimple() && LI->hasOneUse() &&
         LI->getParent() == SI->getParent()) {
 
       auto *T = LI->getType();
       if (T->isAggregateType()) {
-        AliasAnalysis &AA = LookupAliasAnalysis();
         MemoryLocation LoadLoc = MemoryLocation::get(LI);
 
         // We use alias analysis to check if an instruction may store to
         // the memory we load from in between the load and the store. If
         // such an instruction is found, we try to promote there instead
         // of at the store position.
         Instruction *P = SI;
         for (auto &I : make_range(++LI->getIterator(), SI->getIterator())) {
-          if (isModSet(AA.getModRefInfo(&I, LoadLoc))) {
+          if (isModSet(AA->getModRefInfo(&I, LoadLoc))) {
             P = &I;
             break;
           }
         }
 
         // We found an instruction that may write to the loaded memory.
         // We can try to promote at this position instead of the store
         // position if nothing alias the store memory after this and the store
         // destination is not in the range.
         if (P && P != SI) {
-          if (!moveUp(AA, SI, P, LI))
+          if (!moveUp(*AA, SI, P, LI))
             P = nullptr;
         }
 
         // If a valid insertion position is found, then we can promote
         // the load/store pair to a memcpy.
         if (P) {
           // If we load from memory that may alias the memory we store to,
           // memmove must be used to preserve semantic. If not, memcpy can
           // be used.
           bool UseMemMove = false;
-          if (!AA.isNoAlias(MemoryLocation::get(SI), LoadLoc))
+          if (!AA->isNoAlias(MemoryLocation::get(SI), LoadLoc))
             UseMemMove = true;
 
           uint64_t Size = DL.getTypeStoreSize(T);
 
           IRBuilder<> Builder(P);
           Instruction *M;
           if (UseMemMove)
             M = Builder.CreateMemMove(
if (LI->isSimple() && LI->hasOneUse() &&
       if (ldep.isClobber() && !isa<MemCpyInst>(ldep.getInst()))
         C = dyn_cast<CallInst>(ldep.getInst());
 
       if (C) {
         // Check that nothing touches the dest of the "copy" between
         // the call and the store.
         Value *CpyDest = SI->getPointerOperand()->stripPointerCasts();
         bool CpyDestIsLocal = isa<AllocaInst>(CpyDest);
-        AliasAnalysis &AA = LookupAliasAnalysis();
         MemoryLocation StoreLoc = MemoryLocation::get(SI);
         for (BasicBlock::iterator I = --SI->getIterator(), E = C->getIterator();
              I != E; --I) {
-          if (isModOrRefSet(AA.getModRefInfo(&*I, StoreLoc))) {
+          if (isModOrRefSet(AA->getModRefInfo(&*I, StoreLoc))) {
             C = nullptr;
             break;
           }
           // The store to dest may never happen if an exception can be thrown
           // between the load and the store.
           if (I->mayThrow() && !CpyDestIsLocal) {
             C = nullptr;
             break;
bool MemCpyOptPass::performCallSlotOptzn(Instruction *cpy, Value *cpyDest,
   // Check that src isn't captured by the called function since the
   // transformation can cause aliasing issues in that case.
   for (unsigned i = 0, e = CS.arg_size(); i != e; ++i)
     if (CS.getArgument(i) == cpySrc && !CS.doesNotCapture(i))
       return false;
 
   // Since we're changing the parameter to the callsite, we need to make sure
   // that what would be the new parameter dominates the callsite.
-  DominatorTree &DT = LookupDomTree();
   if (Instruction *cpyDestInst = dyn_cast<Instruction>(cpyDest))
-    if (!DT.dominates(cpyDestInst, C))
+    if (!DT->dominates(cpyDestInst, C))
       return false;
 
   // In addition to knowing that the call does not access src in some
   // unexpected manner, for example via a global, which we deduce from
   // the use analysis, we also need to know that it does not sneakily
   // access dest.  We rely on AA to figure this out for us.
-  AliasAnalysis &AA = LookupAliasAnalysis();
-  ModRefInfo MR = AA.getModRefInfo(C, cpyDest, LocationSize::precise(srcSize));
+  ModRefInfo MR = AA->getModRefInfo(C, cpyDest, LocationSize::precise(srcSize));
   // If necessary, perform additional analysis.
   if (isModOrRefSet(MR))
-    MR = AA.callCapturesBefore(C, cpyDest, LocationSize::precise(srcSize), &DT);
+    MR = AA->callCapturesBefore(C, cpyDest, LocationSize::precise(srcSize), DT);
   if (isModOrRefSet(MR))
     return false;
 
   // We can't create address space casts here because we don't know if they're
   // safe for the target.
   if (cpySrc->getType()->getPointerAddressSpace() !=
       cpyDest->getType()->getPointerAddressSpace())
     return false;
bool MemCpyOptPass::processMemCpyMemCpyDependence(MemCpyInst *M,
 
   // Second, the length of the memcpy's must be the same, or the preceding one
   // must be larger than the following one.
   ConstantInt *MDepLen = dyn_cast<ConstantInt>(MDep->getLength());
   ConstantInt *MLen = dyn_cast<ConstantInt>(M->getLength());
   if (!MDepLen || !MLen || MDepLen->getZExtValue() < MLen->getZExtValue())
     return false;
 
-  AliasAnalysis &AA = LookupAliasAnalysis();
-
   // Verify that the copied-from memory doesn't change in between the two
   // transfers.  For example, in:
   //    memcpy(a <- b)
   //    *b = 42;
   //    memcpy(c <- a)
   // It would be invalid to transform the second memcpy into memcpy(c <- b).
   //
   // TODO: If the code between M and MDep is transparent to the destination "c",
   // then we could still perform the xform by moving M up to the first memcpy.
   //
   // NOTE: This is conservative, it will stop on any read from the source loc,
   // not just the defining memcpy.
   MemDepResult SourceDep =
       MD->getPointerDependencyFrom(MemoryLocation::getForSource(MDep), false,
                                    M->getIterator(), M->getParent());
   if (!SourceDep.isClobber() || SourceDep.getInst() != MDep)
     return false;
 
   // If the dest of the second might alias the source of the first, then the
   // source and dest might overlap.  We still want to eliminate the intermediate
   // value, but we have to generate a memmove instead of memcpy.
   bool UseMemMove = false;
-  if (!AA.isNoAlias(MemoryLocation::getForDest(M),
+  if (!AA->isNoAlias(MemoryLocation::getForDest(M),
                      MemoryLocation::getForSource(MDep)))
     UseMemMove = true;
 
   // If all checks passed, then we can transform M.
   LLVM_DEBUG(dbgs() << "MemCpyOptPass: Forwarding memcpy->memcpy src:\n"
                     << *MDep << '\n' << *M << '\n');
 
   // TODO: Is this worth it if we're creating a less aligned memcpy? For
   // example we could be moving from movaps -> movq on x86.

 ///   memset(dst1, c, dst1_size);
 ///   memset(dst2, c, dst2_size);
 /// \endcode
 /// When dst2_size <= dst1_size.
 ///
 /// The \p MemCpy must have a Constant length.
 bool MemCpyOptPass::performMemCpyToMemSetOptzn(MemCpyInst *MemCpy,
                                                MemSetInst *MemSet) {
-  AliasAnalysis &AA = LookupAliasAnalysis();
-
   // Make sure that memcpy(..., memset(...), ...), that is we are memsetting and
   // memcpying from the same address. Otherwise it is hard to reason about.
-  if (!AA.isMustAlias(MemSet->getRawDest(), MemCpy->getRawSource()))
+  if (!AA->isMustAlias(MemSet->getRawDest(), MemCpy->getRawSource()))
     return false;
 
   // A known memset size is required.
   ConstantInt *MemSetSize = dyn_cast<ConstantInt>(MemSet->getLength());
   if (!MemSetSize)
     return false;
 
   // Make sure the memcpy doesn't read any more than what the memset wrote.
if (MemSetInst *MDep = dyn_cast<MemSetInst>(SrcDepInfo.getInst()))
       }
 
   return false;
 }
 
 /// Transforms memmove calls to memcpy calls when the src/dst are guaranteed
 /// not to alias.
 bool MemCpyOptPass::processMemMove(MemMoveInst *M) {
-  AliasAnalysis &AA = LookupAliasAnalysis();
-
   if (!TLI->has(LibFunc_memmove))
     return false;
 
   // See if the pointers alias.
-  if (!AA.isNoAlias(MemoryLocation::getForDest(M),
+  if (!AA->isNoAlias(MemoryLocation::getForDest(M),
                      MemoryLocation::getForSource(M)))
     return false;
 
   LLVM_DEBUG(dbgs() << "MemCpyOptPass: Optimizing memmove -> memcpy: " << *M
                     << "\n");
 
   // If not, then we know we can transform this.
   Type *ArgTys[3] = { M->getRawDest()->getType(),
                       M->getRawSource()->getType(),
bool MemCpyOptPass::processByValArgument(CallSite CS, unsigned ArgNo) {
 
   // Get the alignment of the byval.  If the call doesn't specify the alignment,
   // then it is some target specific value that we can't know.
   unsigned ByValAlign = CS.getParamAlignment(ArgNo);
   if (ByValAlign == 0) return false;
 
   // If it is greater than the memcpy, then we check to see if we can force the
   // source of the memcpy to the alignment we need.  If we fail, we bail out.
-  AssumptionCache &AC = LookupAssumptionCache();
-  DominatorTree &DT = LookupDomTree();
   if (MDep->getSourceAlignment() < ByValAlign &&
       getOrEnforceKnownAlignment(MDep->getSource(), ByValAlign, DL,
-                                 CS.getInstruction(), &AC, &DT) < ByValAlign)
+                                 CS.getInstruction(), AC, DT) < ByValAlign)
     return false;
 
   // The address space of the memcpy source must match the byval argument
   if (MDep->getSource()->getType()->getPointerAddressSpace() !=
       ByValArg->getType()->getPointerAddressSpace())
     return false;
 
   // Verify that the copied-from memory doesn't change in between the memcpy and
bool MemCpyOptPass::processByValArgument(CallSite CS, unsigned ArgNo) {
   ++NumMemCpyInstr;
   return true;
 }
 
 /// Executes one iteration of MemCpyOptPass.
 bool MemCpyOptPass::iterateOnFunction(Function &F) {
   bool MadeChange = false;
 
-  DominatorTree &DT = LookupDomTree();
-
   // Walk all instruction in the function.
   for (BasicBlock &BB : F) {
     // Skip unreachable blocks. For example processStore assumes that an
     // instruction in a BB can't be dominated by a later instruction in the
     // same BB (which is a scenario that can happen for an unreachable BB that
     // has itself as a predecessor).
-    if (!DT.isReachableFromEntry(&BB))
+    if (!DT->isReachableFromEntry(&BB))
       continue;
 
     for (BasicBlock::iterator BI = BB.begin(), BE = BB.end(); BI != BE;) {
         // Avoid invalidating the iterator.
       Instruction *I = &*BI++;
 
       bool RepeatInstruction = false;
 
bool MemCpyOptPass::iterateOnFunction(Function &F) {
   }
 
   return MadeChange;
 }
 
 PreservedAnalyses MemCpyOptPass::run(Function &F, FunctionAnalysisManager &AM) {
   auto &MD = AM.getResult<MemoryDependenceAnalysis>(F);
   auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
+  auto *AA = &AM.getResult<AAManager>(F);
+  auto *AC = &AM.getResult<AssumptionAnalysis>(F);
+  auto *DT = &AM.getResult<DominatorTreeAnalysis>(F);
 
-  auto LookupAliasAnalysis = [&]() -> AliasAnalysis & {
-    return AM.getResult<AAManager>(F);
-  };
-  auto LookupAssumptionCache = [&]() -> AssumptionCache & {
-    return AM.getResult<AssumptionAnalysis>(F);
-  };
-  auto LookupDomTree = [&]() -> DominatorTree & {
-    return AM.getResult<DominatorTreeAnalysis>(F);
-  };
-
-  bool MadeChange = runImpl(F, &MD, &TLI, LookupAliasAnalysis,
-                            LookupAssumptionCache, LookupDomTree);
+  bool MadeChange = runImpl(F, &MD, &TLI, AA, AC, DT);
   if (!MadeChange)
     return PreservedAnalyses::all();
 
   PreservedAnalyses PA;
   PA.preserveSet<CFGAnalyses>();
   PA.preserve<GlobalsAA>();
   PA.preserve<MemoryDependenceAnalysis>();
   return PA;
 }
 
-bool MemCpyOptPass::runImpl(
-    Function &F, MemoryDependenceResults *MD_, TargetLibraryInfo *TLI_,
-    std::function<AliasAnalysis &()> LookupAliasAnalysis_,
-    std::function<AssumptionCache &()> LookupAssumptionCache_,
-    std::function<DominatorTree &()> LookupDomTree_) {
+bool MemCpyOptPass::runImpl(Function &F, MemoryDependenceResults *MD_,
+                            TargetLibraryInfo *TLI_, AliasAnalysis *AA_,
+                            AssumptionCache *AC_, DominatorTree *DT_) {
   bool MadeChange = false;
   MD = MD_;
   TLI = TLI_;
-  LookupAliasAnalysis = std::move(LookupAliasAnalysis_);
-  LookupAssumptionCache = std::move(LookupAssumptionCache_);
-  LookupDomTree = std::move(LookupDomTree_);
-
+  AA = AA_;
+  AC = AC_;
+  DT = DT_;
   // If we don't have at least memset and memcpy, there is little point of doing
   // anything here.  These are required by a freestanding implementation, so if
   // even they are disabled, there is no point in trying hard.
   if (!TLI->has(LibFunc_memset) || !TLI->has(LibFunc_memcpy))
     return false;
 
   while (true) {
     if (!iterateOnFunction(F))
       break;
     MadeChange = true;
   }
 
   MD = nullptr;
   return MadeChange;
 }
 
 /// This is the main transformation entry point for a function.
 bool MemCpyOptLegacyPass::runOnFunction(Function &F) {
   if (skipFunction(F))
     return false;
 
   auto *MD = &getAnalysis<MemoryDependenceWrapperPass>().getMemDep();
   auto *TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
+  auto *AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
+  auto *AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
+  auto *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
 
-  auto LookupAliasAnalysis = [this]() -> AliasAnalysis & {
-    return getAnalysis<AAResultsWrapperPass>().getAAResults();
-  };
-  auto LookupAssumptionCache = [this, &F]() -> AssumptionCache & {
-    return getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
-  };
-  auto LookupDomTree = [this]() -> DominatorTree & {
-    return getAnalysis<DominatorTreeWrapperPass>().getDomTree();
-  };
-
-  return Impl.runImpl(F, MD, TLI, LookupAliasAnalysis, LookupAssumptionCache,
-                      LookupDomTree);
+  return Impl.runImpl(F, MD, TLI, AA, AC, DT);
 }

llvm/test/Other/opt-O2-pipeline.ll

 ; CHECK-NEXT:         MergedLoadStoreMotion
 ; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Global Value Numbering
-; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         MemCpy Optimization
 ; CHECK-NEXT:         Sparse Conditional Constant Propagation
 ; CHECK-NEXT:         Demanded bits analysis
 ; CHECK-NEXT:         Bit-Tracking Dead Code Elimination
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis

llvm/test/Other/opt-O3-pipeline.ll

 ; CHECK-NEXT:         MergedLoadStoreMotion
 ; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Global Value Numbering
-; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         MemCpy Optimization
 ; CHECK-NEXT:         Sparse Conditional Constant Propagation
 ; CHECK-NEXT:         Demanded bits analysis
 ; CHECK-NEXT:         Bit-Tracking Dead Code Elimination
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis

llvm/test/Other/opt-Os-pipeline.ll

 ; CHECK-NEXT:         MergedLoadStoreMotion
 ; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis
 ; CHECK-NEXT:         Optimization Remark Emitter
 ; CHECK-NEXT:         Global Value Numbering
-; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
+; CHECK-NEXT:         Phi Values Analysis
 ; CHECK-NEXT:         Memory Dependence Analysis
 ; CHECK-NEXT:         MemCpy Optimization
 ; CHECK-NEXT:         Sparse Conditional Constant Propagation
 ; CHECK-NEXT:         Demanded bits analysis
 ; CHECK-NEXT:         Bit-Tracking Dead Code Elimination
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:         Lazy Branch Probability Analysis
 ; CHECK-NEXT:         Lazy Block Frequency Analysis