Abstract
Original language | English |
---|---|
Pages (from-to) | 267-281 |
Journal | Geoscientific Model Development Discussions |
Volume | 7 |
DOIs | |
Publication status | Published - 2014 |
Fingerprint
Cite this
}
A distributed computing approach to improve the performance of the Parallel Ocean Program (v2.1). / van Werkhoven, B.J.C.; Kliphuis, M.; Dijkstra, H.A.; Brunnabend, S.A.; van Meersbergen, M.A.J.; Seinstra, F.J.; Bal, H.E.
In: Geoscientific Model Development Discussions, Vol. 7, 2014, p. 267-281.Research output: Contribution to Journal › Article › Academic › peer-review
TY - JOUR
T1 - A distributed computing approach to improve the performance of the Parallel Ocean Program (v2.1)
AU - van Werkhoven, B.J.C.
AU - Kliphuis, M.
AU - Dijkstra, H.A.
AU - Brunnabend, S.A.
AU - van Meersbergen, M.A.J.
AU - Seinstra, F.J.
AU - Bal, H.E.
PY - 2014
Y1 - 2014
N2 - The Parallel Ocean Program (POP) is used in many strongly eddying ocean circulation simulations. Ideally it would be desirable to be able to do thousand-yearlong simulations, but the current performance of POP prohibits these types of simulations. In this work, using a new distributed computing approach, two methods to improve the performance of POP are presented. The first is a blockpartitioning scheme for the optimization of the load balancing of POP such that it can be run efficiently in a multiplatform setting. The second is the implementation of part of the POP model code on graphics processing units (GPUs). We show that the combination of both innovations also leads to a substantial performance increase when running POP simultaneously over multiple computational platforms.
AB - The Parallel Ocean Program (POP) is used in many strongly eddying ocean circulation simulations. Ideally it would be desirable to be able to do thousand-yearlong simulations, but the current performance of POP prohibits these types of simulations. In this work, using a new distributed computing approach, two methods to improve the performance of POP are presented. The first is a blockpartitioning scheme for the optimization of the load balancing of POP such that it can be run efficiently in a multiplatform setting. The second is the implementation of part of the POP model code on graphics processing units (GPUs). We show that the combination of both innovations also leads to a substantial performance increase when running POP simultaneously over multiple computational platforms.
U2 - 10.5194/gmd-7-267-2014
DO - 10.5194/gmd-7-267-2014
M3 - Article
VL - 7
SP - 267
EP - 281
JO - Geoscientific Model Development Discussions
JF - Geoscientific Model Development Discussions
SN - 1991-9611
ER -