2 files changed, 36 insertions, 3 deletions
diff --git a/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp b/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp
index ba90f1cf2fb..d41b6be75f2 100644
--- a/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp
+++ b/llvm/lib/Analysis/MemoryDependenceAnalysis.cpp
@@ -919,6 +919,14 @@ void MemoryDependenceResults::getNonLocalPointerDependency(
     Instruction *QueryInst, SmallVectorImpl<NonLocalDepResult> &Result) {
   const MemoryLocation Loc = MemoryLocation::get(QueryInst);
   bool isLoad = isa<LoadInst>(QueryInst);
+  return getNonLocalPointerDependencyFrom(QueryInst, Loc, isLoad, Result);
+}
+
+void MemoryDependenceResults::getNonLocalPointerDependencyFrom(
+    Instruction *QueryInst,
+    const MemoryLocation &Loc,
+    bool isLoad,
+    SmallVectorImpl<NonLocalDepResult> &Result) {
   BasicBlock *FromBB = QueryInst->getParent();
   assert(FromBB);
 
diff --git a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
index a4b4330bfed..86d7b5e8ddd 100644
--- a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -1031,9 +1031,22 @@ bool MemCpyOptPass::processMemCpyMemCpyDependence(MemCpyInst *M,
   //
   // 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());
+  MemoryLocation SourceLoc = MemoryLocation::getForSource(MDep);
+  MemDepResult SourceDep = MD->getPointerDependencyFrom(SourceLoc, false,
+                                                        M->getIterator(), M->getParent());
+
+  if (SourceDep.isNonLocal()) {
+    SmallVector<NonLocalDepResult, 2> NonLocalDepResults;
+    MD->getNonLocalPointerDependencyFrom(M, SourceLoc, /*isLoad=*/false,
+                                         NonLocalDepResults);
+    if (NonLocalDepResults.size() == 1) {
+      SourceDep = NonLocalDepResults[0].getResult();
+      assert((!SourceDep.getInst() ||
+              LookupDomTree().dominates(SourceDep.getInst(), M)) &&
+             "when memdep returns exactly one result, it should dominate");
+    }
+  }
+
   if (!SourceDep.isClobber() || SourceDep.getInst() != MDep)
     return false;
 
@@ -1235,6 +1248,18 @@ bool MemCpyOptPass::processMemCpy(MemCpyInst *M) {
   MemDepResult SrcDepInfo = MD->getPointerDependencyFrom(
       SrcLoc, true, M->getIterator(), M->getParent());
 
+  if (SrcDepInfo.isNonLocal()) {
+    SmallVector<NonLocalDepResult, 2> NonLocalDepResults;
+    MD->getNonLocalPointerDependencyFrom(M, SrcLoc, /*isLoad=*/true,
+                                         NonLocalDepResults);
+    if (NonLocalDepResults.size() == 1) {
+      SrcDepInfo = NonLocalDepResults[0].getResult();
+      assert((!SrcDepInfo.getInst() ||
+              LookupDomTree().dominates(SrcDepInfo.getInst(), M)) &&
+             "when memdep returns exactly one result, it should dominate");
+    }
+  }
+
   if (SrcDepInfo.isClobber()) {
     if (MemCpyInst *MDep = dyn_cast<MemCpyInst>(SrcDepInfo.getInst()))
       return processMemCpyMemCpyDependence(M, MDep);