Articles | Volume 14, issue 2
Geosci. Model Dev., 14, 843–857, 2021
https://doi.org/10.5194/gmd-14-843-2021
Geosci. Model Dev., 14, 843–857, 2021
https://doi.org/10.5194/gmd-14-843-2021

Development and technical paper 05 Feb 2021

Development and technical paper | 05 Feb 2021

Advanced parallel implementation of the coupled ocean–ice model FEMAO (version 2.0) with load balancing

Pavel Perezhogin et al.

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 Pavel Perezhogin on behalf of the Authors (17 Nov 2020)  Author's response    Manuscript
ED: Publish subject to minor revisions (review by editor) (20 Nov 2020) by Richard Mills
AR by Pavel Perezhogin on behalf of the Authors (20 Nov 2020)  Author's response    Manuscript
ED: Publish subject to minor revisions (review by editor) (08 Dec 2020) by Richard Mills
AR by Pavel Perezhogin on behalf of the Authors (13 Dec 2020)  Author's response    Author's tracked changes    Manuscript
ED: Publish as is (23 Dec 2020) by Richard Mills
AR by Pavel Perezhogin on behalf of the Authors (23 Dec 2020)  Author's response    Manuscript
Download
Short summary
We describe the parallel implementation of the FEMAO model for an ice-covered sea with 2D Hilbert-curve domain decomposition. Load balancing is crucial because performance depends on the local depth. We propose, compare, and discuss four approaches to load balancing. The parallel library allowed us to modify the original sequential algorithm as little as possible. The performance increases almost linearly (tested with up to 996 CPU cores) for the model of the shallow White Sea.