3 files changed, 28 insertions, 8 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
index 8dcc6351ac7..19145768e5e 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -819,11 +819,10 @@ Instruction *InstCombiner::visitLoadInst(LoadInst &LI) {
   // where there are several consecutive memory accesses to the same location,
   // separated by a few arithmetic operations.
   BasicBlock::iterator BBI(LI);
-  AAMDNodes AATags;
   bool IsLoadCSE = false;
   if (Value *AvailableVal =
       FindAvailableLoadedValue(&LI, LI.getParent(), BBI,
-                               DefMaxInstsToScan, AA, &AATags, &IsLoadCSE)) {
+                               DefMaxInstsToScan, AA, &IsLoadCSE)) {
     if (IsLoadCSE) {
       LoadInst *NLI = cast<LoadInst>(AvailableVal);
       unsigned KnownIDs[] = {
diff --git a/llvm/lib/Transforms/Scalar/JumpThreading.cpp b/llvm/lib/Transforms/Scalar/JumpThreading.cpp
index d1769fc3ebb..4093cc57dfc 100644
--- a/llvm/lib/Transforms/Scalar/JumpThreading.cpp
+++ b/llvm/lib/Transforms/Scalar/JumpThreading.cpp
@@ -951,12 +951,17 @@ bool JumpThreadingPass::SimplifyPartiallyRedundantLoad(LoadInst *LI) {
   // Scan a few instructions up from the load, to see if it is obviously live at
   // the entry to its block.
   BasicBlock::iterator BBIt(LI);
-
+  bool IsLoadCSE;
   if (Value *AvailableVal =
-        FindAvailableLoadedValue(LI, LoadBB, BBIt, DefMaxInstsToScan)) {
+        FindAvailableLoadedValue(LI, LoadBB, BBIt, DefMaxInstsToScan, nullptr, &IsLoadCSE)) {
     // If the value of the load is locally available within the block, just use
     // it.  This frequently occurs for reg2mem'd allocas.
 
+    if (IsLoadCSE) {
+      LoadInst *NLI = cast<LoadInst>(AvailableVal);
+      combineMetadataForCSE(NLI, LI);
+    };
+
     // If the returned value is the load itself, replace with an undef. This can
     // only happen in dead loops.
     if (AvailableVal == LI) AvailableVal = UndefValue::get(LI->getType());
@@ -983,6 +988,7 @@ bool JumpThreadingPass::SimplifyPartiallyRedundantLoad(LoadInst *LI) {
   typedef SmallVector<std::pair<BasicBlock*, Value*>, 8> AvailablePredsTy;
   AvailablePredsTy AvailablePreds;
   BasicBlock *OneUnavailablePred = nullptr;
+  SmallVector<LoadInst*, 8> CSELoads;
 
   // If we got here, the loaded value is transparent through to the start of the
   // block.  Check to see if it is available in any of the predecessor blocks.
@@ -993,17 +999,17 @@ bool JumpThreadingPass::SimplifyPartiallyRedundantLoad(LoadInst *LI) {
 
     // Scan the predecessor to see if the value is available in the pred.
     BBIt = PredBB->end();
-    AAMDNodes ThisAATags;
     Value *PredAvailable = FindAvailableLoadedValue(LI, PredBB, BBIt,
                                                     DefMaxInstsToScan,
-                                                    nullptr, &ThisAATags);
+                                                    nullptr,
+                                                    &IsLoadCSE);
     if (!PredAvailable) {
       OneUnavailablePred = PredBB;
       continue;
     }
 
-    // If AA tags disagree or are not present, forget about them.
-    if (AATags != ThisAATags) AATags = AAMDNodes();
+    if (IsLoadCSE)
+      CSELoads.push_back(cast<LoadInst>(PredAvailable));
 
     // If so, this load is partially redundant.  Remember this info so that we
     // can create a PHI node.
@@ -1101,6 +1107,10 @@ bool JumpThreadingPass::SimplifyPartiallyRedundantLoad(LoadInst *LI) {
     PN->addIncoming(PredV, I->first);
   }
 
+  for (LoadInst *PredLI : CSELoads) {
+    combineMetadataForCSE(PredLI, LI);
+  }
+
   LI->replaceAllUsesWith(PN);
   LI->eraseFromParent();
 
diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
index 987460bef9d..87524e660f0 100644
--- a/llvm/lib/Transforms/Utils/Local.cpp
+++ b/llvm/lib/Transforms/Utils/Local.cpp
@@ -1646,6 +1646,17 @@ void llvm::combineMetadata(Instruction *K, const Instruction *J,
       K->setMetadata(LLVMContext::MD_invariant_group, JMD);
 }
 
+void llvm::combineMetadataForCSE(Instruction *K, const Instruction *J) {
+  unsigned KnownIDs[] = {
+      LLVMContext::MD_tbaa,            LLVMContext::MD_alias_scope,
+      LLVMContext::MD_noalias,         LLVMContext::MD_range,
+      LLVMContext::MD_invariant_load,  LLVMContext::MD_nonnull,
+      LLVMContext::MD_invariant_group, LLVMContext::MD_align,
+      LLVMContext::MD_dereferenceable,
+      LLVMContext::MD_dereferenceable_or_null};
+  combineMetadata(K, J, KnownIDs);
+}
+
 unsigned llvm::replaceDominatedUsesWith(Value *From, Value *To,
                                         DominatorTree &DT,
                                         const BasicBlockEdge &Root) {