Articles | Volume 11, issue 8
Geosci. Model Dev., 11, 3409–3426, 2018
https://doi.org/10.5194/gmd-11-3409-2018
Geosci. Model Dev., 11, 3409–3426, 2018
https://doi.org/10.5194/gmd-11-3409-2018

Methods for assessment of models 22 Aug 2018

Methods for assessment of models | 22 Aug 2018

Simulation of the performance and scalability of message passing interface (MPI) communications of atmospheric models running on exascale supercomputers

Yongjun Zheng and Philippe Marguinaud

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Yongjun ZHENG on behalf of the Authors (11 May 2018)  Author's response    Manuscript
ED: Publish subject to minor revisions (review by editor) (26 Jun 2018) by David Ham
AR by Yongjun ZHENG on behalf of the Authors (02 Jul 2018)  Author's response    Manuscript
ED: Publish as is (17 Jul 2018) by David Ham
Download
Short summary
The impacts of collective algorithms, interconnect topologies, and routing algorithms on the performance and scalability of transpositions, halo exchanges, and allreduce operations are significant. The performance of communications can be improved when the congestion is mitigated by a proper configuration of the topology and a congestion-balanced routing algorithm. The scalability of the spectral models could be acceptable for exascale supercomputers.