[Loads] Use BatchAAResults for available value APIs (NFCI)

This allows caching AA queries both within and across the calls,
and enables us to use a custom AAQI configuration.

Author: nikic

llvm/include/llvm/Analysis/Loads.h

@@ -18,7 +18,7 @@
 
 namespace llvm {
 
-class AAResults;
+class BatchAAResults;
 class AssumptionCache;
 class DataLayout;
 class DominatorTree;
@@ -129,19 +129,19 @@ extern cl::opt<unsigned> DefMaxInstsToScan;
 /// location in memory, as opposed to the value operand of a store.
 ///
 /// \returns The found value, or nullptr if no value is found.
-Value *FindAvailableLoadedValue(LoadInst *Load,
-                                BasicBlock *ScanBB,
+Value *FindAvailableLoadedValue(LoadInst *Load, BasicBlock *ScanBB,
                                 BasicBlock::iterator &ScanFrom,
                                 unsigned MaxInstsToScan = DefMaxInstsToScan,
-                                AAResults *AA = nullptr,
+                                BatchAAResults *AA = nullptr,
                                 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,
+Value *FindAvailableLoadedValue(LoadInst *Load, BatchAAResults &AA,
+                                bool *IsLoadCSE,
                                 unsigned MaxInstsToScan = DefMaxInstsToScan);
 
 /// Scan backwards to see if we have the value of the given pointer available
@@ -170,7 +170,7 @@ Value *FindAvailableLoadedValue(LoadInst *Load, AAResults &AA, bool *IsLoadCSE,
 Value *findAvailablePtrLoadStore(const MemoryLocation &Loc, Type *AccessTy,
                                  bool AtLeastAtomic, BasicBlock *ScanBB,
                                  BasicBlock::iterator &ScanFrom,
-                                 unsigned MaxInstsToScan, AAResults *AA,
+                                 unsigned MaxInstsToScan, BatchAAResults *AA,
                                  bool *IsLoadCSE, unsigned *NumScanedInst);
 
 /// Returns true if a pointer value \p A can be replace with another pointer

llvm/lib/Analysis/Lint.cpp

@@ -657,11 +657,12 @@ Value *Lint::findValueImpl(Value *V, bool OffsetOk,
     BasicBlock::iterator BBI = L->getIterator();
     BasicBlock *BB = L->getParent();
     SmallPtrSet<BasicBlock *, 4> VisitedBlocks;
+    BatchAAResults BatchAA(*AA);
     for (;;) {
       if (!VisitedBlocks.insert(BB).second)
         break;
       if (Value *U =
-              FindAvailableLoadedValue(L, BB, BBI, DefMaxInstsToScan, AA))
+              FindAvailableLoadedValue(L, BB, BBI, DefMaxInstsToScan, &BatchAA))
         return findValueImpl(U, OffsetOk, Visited);
       if (BBI != BB->begin())
         break;

llvm/lib/Analysis/Loads.cpp

@@ -450,11 +450,10 @@ llvm::DefMaxInstsToScan("available-load-scan-limit", cl::init(6), cl::Hidden,
            "to scan backward from a given instruction, when searching for "
            "available loaded value"));
 
-Value *llvm::FindAvailableLoadedValue(LoadInst *Load,
-                                      BasicBlock *ScanBB,
+Value *llvm::FindAvailableLoadedValue(LoadInst *Load, BasicBlock *ScanBB,
                                       BasicBlock::iterator &ScanFrom,
                                       unsigned MaxInstsToScan,
-                                      AAResults *AA, bool *IsLoad,
+                                      BatchAAResults *AA, bool *IsLoad,
                                       unsigned *NumScanedInst) {
   // Don't CSE load that is volatile or anything stronger than unordered.
   if (!Load->isUnordered())
@@ -583,7 +582,7 @@ static Value *getAvailableLoadStore(Instruction *Inst, const Value *Ptr,
 Value *llvm::findAvailablePtrLoadStore(
     const MemoryLocation &Loc, Type *AccessTy, bool AtLeastAtomic,
     BasicBlock *ScanBB, BasicBlock::iterator &ScanFrom, unsigned MaxInstsToScan,
-    AAResults *AA, bool *IsLoadCSE, unsigned *NumScanedInst) {
+    BatchAAResults *AA, bool *IsLoadCSE, unsigned *NumScanedInst) {
   if (MaxInstsToScan == 0)
     MaxInstsToScan = ~0U;
 
@@ -664,7 +663,7 @@ Value *llvm::findAvailablePtrLoadStore(
   return nullptr;
 }
 
-Value *llvm::FindAvailableLoadedValue(LoadInst *Load, AAResults &AA,
+Value *llvm::FindAvailableLoadedValue(LoadInst *Load, BatchAAResults &AA,
                                       bool *IsLoadCSE,
                                       unsigned MaxInstsToScan) {
   const DataLayout &DL = Load->getModule()->getDataLayout();

llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp

@@ -1032,7 +1032,8 @@ Instruction *InstCombinerImpl::visitLoadInst(LoadInst &LI) {
   // where there are several consecutive memory accesses to the same location,
   // separated by a few arithmetic operations.
   bool IsLoadCSE = false;
-  if (Value *AvailableVal = FindAvailableLoadedValue(&LI, *AA, &IsLoadCSE)) {
+  BatchAAResults BatchAA(*AA);
+  if (Value *AvailableVal = FindAvailableLoadedValue(&LI, BatchAA, &IsLoadCSE)) {
     if (IsLoadCSE)
       combineMetadataForCSE(cast<LoadInst>(AvailableVal), &LI, false);
 

llvm/lib/Transforms/Scalar/JumpThreading.cpp

@@ -1260,8 +1260,9 @@ bool JumpThreadingPass::simplifyPartiallyRedundantLoad(LoadInst *LoadI) {
   // the entry to its block.
   BasicBlock::iterator BBIt(LoadI);
   bool IsLoadCSE;
+  BatchAAResults BatchAA(*AA);
   if (Value *AvailableVal = FindAvailableLoadedValue(
-          LoadI, LoadBB, BBIt, DefMaxInstsToScan, AA, &IsLoadCSE)) {
+          LoadI, LoadBB, BBIt, DefMaxInstsToScan, &BatchAA, &IsLoadCSE)) {
     // If the value of the load is locally available within the block, just use
     // it.  This frequently occurs for reg2mem'd allocas.
 
@@ -1322,9 +1323,9 @@ bool JumpThreadingPass::simplifyPartiallyRedundantLoad(LoadInst *LoadI) {
     MemoryLocation Loc(LoadedPtr->DoPHITranslation(LoadBB, PredBB),
                        LocationSize::precise(DL.getTypeStoreSize(AccessTy)),
                        AATags);
-    PredAvailable = findAvailablePtrLoadStore(Loc, AccessTy, LoadI->isAtomic(),
-                                              PredBB, BBIt, DefMaxInstsToScan,
-                                              AA, &IsLoadCSE, &NumScanedInst);
+    PredAvailable = findAvailablePtrLoadStore(
+        Loc, AccessTy, LoadI->isAtomic(), PredBB, BBIt, DefMaxInstsToScan,
+        &BatchAA, &IsLoadCSE, &NumScanedInst);
 
     // If PredBB has a single predecessor, continue scanning through the
     // single predecessor.
@@ -1336,7 +1337,7 @@ bool JumpThreadingPass::simplifyPartiallyRedundantLoad(LoadInst *LoadI) {
         BBIt = SinglePredBB->end();
         PredAvailable = findAvailablePtrLoadStore(
             Loc, AccessTy, LoadI->isAtomic(), SinglePredBB, BBIt,
-            (DefMaxInstsToScan - NumScanedInst), AA, &IsLoadCSE,
+            (DefMaxInstsToScan - NumScanedInst), &BatchAA, &IsLoadCSE,
             &NumScanedInst);
       }
     }