[Loads] Add optimized FindAvailableLoadedValue() overload (NFCI)

FindAvailableLoadedValue() accepts an iterator by reference. If no
available value is found, then the iterator will either be left
at a clobbering instruction or the beginning of the basic block.
This allows using FindAvailableLoadedValue() across multiple blocks.

If this functionality is not needed, as is the case in InstCombine,
then we can use a much more efficient implementation: First try
to find an available value, and only perform clobber checks if
we actually found one. As this function only looks at a very small
number of instructions (6 by default) and usually doesn't find an
available value, this saves many expensive alias analysis queries.

llvm/include/llvm/Analysis/Loads.h

@@ -133,6 +133,13 @@ Value *FindAvailableLoadedValue(LoadInst *Load,
                                 bool *IsLoadCSE = nullptr,
                                 unsigned *NumScanedInst = nullptr);
 
+/// This overload provides a more efficient implementation of
+/// FindAvailableLoadedValue() for the case where we are not interested in
+/// finding the closest clobbering instruction if no available load is found.
+/// This overload cannot be used to scan across multiple blocks.
+Value *FindAvailableLoadedValue(LoadInst *Load, AAResults &AA, bool *IsLoadCSE,
+                                unsigned MaxInstsToScan = DefMaxInstsToScan);
+
 /// Scan backwards to see if we have the value of the given pointer available
 /// locally within a small number of instructions.
 ///

llvm/lib/Analysis/Loads.cpp

@@ -593,6 +593,51 @@ Value *llvm::FindAvailablePtrLoadStore(Value *Ptr, Type *AccessTy,
   return nullptr;
 }
 
+Value *llvm::FindAvailableLoadedValue(LoadInst *Load, AAResults &AA,
+                                      bool *IsLoadCSE,
+                                      unsigned MaxInstsToScan) {
+  const DataLayout &DL = Load->getModule()->getDataLayout();
+  Value *StrippedPtr = Load->getPointerOperand()->stripPointerCasts();
+  BasicBlock *ScanBB = Load->getParent();
+  Type *AccessTy = Load->getType();
+  bool AtLeastAtomic = Load->isAtomic();
+
+  if (!Load->isUnordered())
+    return nullptr;
+
+  // Try to find an available value first, and delay expensive alias analysis
+  // queries until later.
+  Value *Available = nullptr;;
+  SmallVector<Instruction *> MustNotAliasInsts;
+  for (Instruction &Inst : make_range(++Load->getReverseIterator(),
+                                      ScanBB->rend())) {
+    if (isa<DbgInfoIntrinsic>(&Inst))
+      continue;
+
+    if (MaxInstsToScan-- == 0)
+      return nullptr;
+
+    Available = getAvailableLoadStore(&Inst, StrippedPtr, AccessTy,
+                                      AtLeastAtomic, DL, IsLoadCSE);
+    if (Available)
+      break;
+
+    if (Inst.mayWriteToMemory())
+      MustNotAliasInsts.push_back(&Inst);
+  }
+
+  // If we found an available value, ensure that the instructions in between
+  // did not modify the memory location.
+  if (Available) {
+    auto AccessSize = LocationSize::precise(DL.getTypeStoreSize(AccessTy));
+    for (Instruction *Inst : MustNotAliasInsts)
+      if (isModSet(AA.getModRefInfo(Inst, StrippedPtr, AccessSize)))
+        return nullptr;
+  }
+
+  return Available;
+}
+
 bool llvm::canReplacePointersIfEqual(Value *A, Value *B, const DataLayout &DL,
                                      Instruction *CtxI) {
   Type *Ty = A->getType();

llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp

@@ -956,10 +956,8 @@ Instruction *InstCombinerImpl::visitLoadInst(LoadInst &LI) {
   // Do really simple store-to-load forwarding and load CSE, to catch cases
   // where there are several consecutive memory accesses to the same location,
   // separated by a few arithmetic operations.
-  BasicBlock::iterator BBI(LI);
   bool IsLoadCSE = false;
-  if (Value *AvailableVal = FindAvailableLoadedValue(
-          &LI, LI.getParent(), BBI, DefMaxInstsToScan, AA, &IsLoadCSE)) {
+  if (Value *AvailableVal = FindAvailableLoadedValue(&LI, *AA, &IsLoadCSE)) {
     if (IsLoadCSE)
       combineMetadataForCSE(cast<LoadInst>(AvailableVal), &LI, false);