diff --git a/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear.h b/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear.h
index 1485b1533..4a08ba9e3 100644
--- a/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear.h
+++ b/include/cutlass/transform/threadblock/regular_tile_iterator_pitch_linear.h
@@ -204,7 +204,8 @@ public:
   void store(Fragment const &frag, TensorCoord const & tile_offset) {
     store_with_pointer_offset(
       frag,
-      tile_offset.contiguous() * Shape::kContiguous + tile_offset.strided() * Shape::kStrided * stride_
+      tile_offset.contiguous() * Shape::kContiguous / ThreadMap::kElementsPerAccess +
+        tile_offset.strided() * Shape::kStrided * stride_
     );
   }