Index: llvm/trunk/include/llvm/InitializePasses.h
===================================================================
--- llvm/trunk/include/llvm/InitializePasses.h
+++ llvm/trunk/include/llvm/InitializePasses.h
@@ -314,6 +314,7 @@
 void initializeFuncletLayoutPass(PassRegistry &);
 void initializeLoopLoadEliminationPass(PassRegistry&);
 void initializeFunctionImportPassPass(PassRegistry &);
+void initializeLoopVersioningPassPass(PassRegistry &);
 }
 
 #endif
Index: llvm/trunk/include/llvm/Transforms/Scalar.h
===================================================================
--- llvm/trunk/include/llvm/Transforms/Scalar.h
+++ llvm/trunk/include/llvm/Transforms/Scalar.h
@@ -483,6 +483,12 @@
 //
 Pass *createLoopSimplifyCFGPass();
 
+//===----------------------------------------------------------------------===//
+//
+// LoopVersioning - Perform loop multi-versioning.
+//
+FunctionPass *createLoopVersioningPass();
+
 } // End llvm namespace
 
 #endif
Index: llvm/trunk/lib/Transforms/Scalar/Scalar.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Scalar/Scalar.cpp
+++ llvm/trunk/lib/Transforms/Scalar/Scalar.cpp
@@ -85,6 +85,7 @@
   initializeLoopDistributePass(Registry);
   initializeLoopLoadEliminationPass(Registry);
   initializeLoopSimplifyCFGPass(Registry);
+  initializeLoopVersioningPassPass(Registry);
 }
 
 void LLVMInitializeScalarOpts(LLVMPassRegistryRef R) {
Index: llvm/trunk/lib/Transforms/Utils/LoopVersioning.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Utils/LoopVersioning.cpp
+++ llvm/trunk/lib/Transforms/Utils/LoopVersioning.cpp
@@ -145,3 +145,77 @@
     PN->addIncoming(NonVersionedLoopInst, NonVersionedLoop->getExitingBlock());
   }
 }
+
+namespace {
+/// \brief Also expose this is a pass.  Currently this is only used for
+/// unit-testing.  It adds all memchecks necessary to remove all may-aliasing
+/// array accesses from the loop.
+class LoopVersioningPass : public FunctionPass {
+public:
+  LoopVersioningPass() : FunctionPass(ID) {
+    initializeLoopVersioningPassPass(*PassRegistry::getPassRegistry());
+  }
+
+  bool runOnFunction(Function &F) override {
+    auto *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
+    auto *LAA = &getAnalysis<LoopAccessAnalysis>();
+    auto *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
+    auto *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
+
+    // Build up a worklist of inner-loops to version. This is necessary as the
+    // act of versioning a loop creates new loops and can invalidate iterators
+    // across the loops.
+    SmallVector<Loop *, 8> Worklist;
+
+    for (Loop *TopLevelLoop : *LI)
+      for (Loop *L : depth_first(TopLevelLoop))
+        // We only handle inner-most loops.
+        if (L->empty())
+          Worklist.push_back(L);
+
+    // Now walk the identified inner loops.
+    bool Changed = false;
+    for (Loop *L : Worklist) {
+      const LoopAccessInfo &LAI = LAA->getInfo(L, ValueToValueMap());
+      if (LAI.getNumRuntimePointerChecks() ||
+          !LAI.PSE.getUnionPredicate().isAlwaysTrue()) {
+        LoopVersioning LVer(LAI, L, LI, DT, SE);
+        LVer.versionLoop();
+        Changed = true;
+      }
+    }
+
+    return Changed;
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<LoopInfoWrapperPass>();
+    AU.addPreserved<LoopInfoWrapperPass>();
+    AU.addRequired<LoopAccessAnalysis>();
+    AU.addRequired<DominatorTreeWrapperPass>();
+    AU.addPreserved<DominatorTreeWrapperPass>();
+    AU.addRequired<ScalarEvolutionWrapperPass>();
+  }
+
+  static char ID;
+};
+}
+
+#define LVER_OPTION "loop-versioning"
+#define DEBUG_TYPE LVER_OPTION
+
+char LoopVersioningPass::ID;
+static const char LVer_name[] = "Loop Versioning";
+
+INITIALIZE_PASS_BEGIN(LoopVersioningPass, LVER_OPTION, LVer_name, false, false)
+INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(LoopAccessAnalysis)
+INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
+INITIALIZE_PASS_END(LoopVersioningPass, LVER_OPTION, LVer_name, false, false)
+
+namespace llvm {
+FunctionPass *createLoopVersioningPass() {
+  return new LoopVersioningPass();
+}
+}
Index: llvm/trunk/test/Transforms/LoopVersioning/basic.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopVersioning/basic.ll
+++ llvm/trunk/test/Transforms/LoopVersioning/basic.ll
@@ -0,0 +1,47 @@
+; RUN: opt -basicaa -loop-versioning -S < %s | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; Version this loop with overlap checks between a, c and b, c.
+
+define void @f(i32* %a, i32* %b, i32* %c) {
+entry:
+  br label %for.body
+
+; CHECK: for.body.lver.check:
+; CHECK:   icmp
+; CHECK:   icmp
+; CHECK:   icmp
+; CHECK:   icmp
+; CHECK-NOT: icmp
+; CHECK:   br i1 %memcheck.conflict, label %for.body.ph.lver.orig, label %for.body.ph
+
+; CHECK: for.body.ph.lver.orig:
+; CHECK: for.body.lver.orig:
+; CHECK:   br i1 %exitcond.lver.orig, label %for.end, label %for.body.lver.orig
+; CHECK: for.body.ph:
+; CHECK: for.body:
+; CHECK:   br i1 %exitcond, label %for.end, label %for.body
+; CHECK: for.end:
+
+for.body:                                         ; preds = %for.body, %entry
+  %ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
+
+  %arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
+  %loadA = load i32, i32* %arrayidxA, align 4
+
+  %arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
+  %loadB = load i32, i32* %arrayidxB, align 4
+
+  %mulC = mul i32 %loadA, %loadB
+
+  %arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
+  store i32 %mulC, i32* %arrayidxC, align 4
+
+  %add = add nuw nsw i64 %ind, 1
+  %exitcond = icmp eq i64 %add, 20
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}