Investigating solution convergence in a global ocean model using a 2048-processor cluster of distributed shared memory machines

Authors:
Chris Hill;Dimitris Menemenlis;Bob Ciotti;Chris Henze
Affiliations:
(Correspd. Tel.: +1 617 253 6430/ Fax: +1 617 253 4464/ E-mail: cnh@mit.edu) Department of Earth, Atmospheric and Planetary Sciences, Massachusetts Institute of Technology, Room 54-1515, 77 Massac ...;Jet Propulsion Lab, California Institute of Technology, CA, USA;NASA Advanced Supercomputing, Ames Research Center, CA, USA;NASA Advanced Supercomputing, Ames Research Center, CA, USA
Venue:
Scientific Programming - High Performance Computing for Mission-Enabling Space Applications
Year:
2007

Citing 4
Cited 2

Fat-trees: universal networks for hardware-efficient supercomputing

IEEE Transactions on Computers
The Stanford Dash Multiprocessor

Computer
Scaling Linux to new heights: the SGI Altix 3000 system

Linux Journal
Automatic Generation of Efficient Adjoint Code for a Parallel Navier-Stokes Solver

ICCS '02 Proceedings of the International Conference on Computational Science-Part II

"Zen" and the art of petascale ocean modeling: a conceptual analysis of how virtualization could be key to bringing individual science back to petascale ocean modeling

Proceedings of the 2nd workshop on System-level virtualization for high performance computing
A parallel Jacobian-free Newton-Krylov solver for a coupled sea ice-ocean model

Journal of Computational Physics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Up to 1920 processors of a cluster of distributed shared memory machines at the NASA Ames Research Center are being used to simulate ocean circulation globally at horizontal resolutions of 1/4, 1/8, and 1/16-degree with the Massachusetts Institute of Technology General Circulation Model, a finite volume code that can scale to large numbers of processors. The study aims to understand physical processes responsible for skill improvements as resolution is increased and to gain insight into what resolution is sufficient for particular purposes. This paper focuses on the computational aspects of reaching the technical objective of efficiently performing these global eddy-resolving ocean simulations. At 1/16-degree resolution the model grid contains 1.2 billion cells. At this resolution it is possible to simulate approximately one month of ocean dynamics in about 17 hours of wallclock time with a model timestep of two minutes on a cluster of four 512-way NUMA Altix systems. The Altix systems' large main memory and I/O subsystems allow computation and disk storage of rich sets of diagnostics during each integration, supporting the scientific objective to develop a better understanding of global ocean circulation model solution convergence as model resolution is increased.