Index: llvm/include/llvm/Analysis/TargetTransformInfo.h
===================================================================
--- llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -573,6 +573,8 @@
     /// Don't allow loop unrolling to simulate more than this number of
     /// iterations when checking full unroll profitability
     unsigned MaxIterationsCountToAnalyze;
+    /// Enable runtime unrolling when vectorizing the epilogue loop. 
+    bool unrollLoopEpilogues = false;
   };
 
   /// Get target-customized preferences for the generic loop unrolling
Index: llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -113,6 +113,9 @@
   // manipulations in average.
   UP.BEInsns += 3;
 
+  // We want to run unroll for epilog loops.
+  UP.unrollLoopEpilogues = true;
+
   // TODO: Do we want runtime unrolling?
 
   // Maximum alloca size than can fit registers. Reserve 16 registers.
Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7778,7 +7778,10 @@
     LoopVectorizeHints Hints(L, true, *ORE);
     Hints.setAlreadyVectorized();
   }
-  AddRuntimeUnrollDisableMetaData(L);
+  TargetTransformInfo::UnrollingPreferences UP;
+  TTI->getUnrollingPreferences(L, *PSE.getSE(), UP, ORE);
+  if (!UP.unrollLoopEpilogues)
+    AddRuntimeUnrollDisableMetaData(L);
 
   // 3. Fix the vectorized code: take care of header phi's, live-outs,
   //    predication, updating analyses.