Update cuda pinned memory note to include tensor.to (pytorch#20977)

Summary:
separate bits of changes from pytorch#19228
Pull Request resolved: pytorch#20977

Differential Revision: D15511919

Pulled By: soumith

fbshipit-source-id: 5015a29cdac6d6e160388c493182c330f0da63ec

docs/source/notes/cuda.rst

@@ -277,8 +277,9 @@ memory. CPU tensors and storages expose a :meth:`~torch.Tensor.pin_memory`
 method, that returns a copy of the object, with data put in a pinned region.
 
 Also, once you pin a tensor or storage, you can use asynchronous GPU copies.
-Just pass an additional ``non_blocking=True`` argument to a :meth:`~torch.Tensor.cuda`
-call. This can be used to overlap data transfers with computation.
+Just pass an additional ``non_blocking=True`` argument to a
+:meth:`~torch.Tensor.to` or a :meth:`~torch.Tensor.cuda` call. This can be used
+to overlap data transfers with computation.
 
 You can make the :class:`~torch.utils.data.DataLoader` return batches placed in
 pinned memory by passing ``pin_memory=True`` to its constructor.