\item In Page 2, Section 2, we have added a paragraph describing the contributions of our work.
\item In Section 4, we have reduced the theory part of the GMRES method as suggested by Reviewer 2.
\item In Section 5.2, we have clarified that the same optimizations are used on the CPU version of the parallel GMRES algorithm too.
-\item We have added some results obtained from other experiments to show the influence of the communications on a GPU cluster. We computed the ratios between the computation time over the communication time and we have showed the weak scaling of the different versions of the parallel GMRES algorithm. In this revised version, there are many modifications from the end of page 13 to the middle of page 16. In particular Tables 10, 11, 12 and Figure 9 show new results that should help the reader to understand the impact of communications with linear systems on GPU clusters.
+\item We have added some results obtained from other experiments to show the influence of the communications on a GPU cluster. We computed the ratios between the computation time over the communication time and we have showed the weak scaling of the different versions of the parallel GMRES algorithm. In this revised version, there are many modifications from the end of page 13 to the middle of page 16. In particular Tables 9, 10, 11, 12 and Figure 9 show new results that should help the reader to understand the impact of communications with linear systems on GPU clusters.
\end{enumerate}
\end{document}
