addressed adequately below and that our work will be appropriately re-evaluated

We thank the reviewers for their insightful comments and encouraging feedback. Reviewer 1 raises two concerns about speedups which we believe to be based on a misunderstanding. A 2 reduction in this metric seems significant. We will clarify this in the paper. Secondly, the reviewer suspects that Tables 6 and 7 show timings for the slower GLOO backend.