Abstract
In this paper we present a parallel Atmospheric General Circulation Model currently under development at the NASA Data Assimilation Office. The constituent simulation parameterizations of the AGCM are briefly described, and the parallelization strategy discussed. The key performance obstacles to attaining target benchmarks are treated, as well as our plans for code optimization. We also present the most current benchmarks arising from the this High Performance Computing and Communications Initiative Grand Challenge project.
Preview
Unable to display preview. Download preview PDF.
References
L. L. Takacs, A. Molod, and T. Wang. Documentation of the Goddard Earth Observing System (GEOS) General Circulation Model—Version 1. Technical Memorandum 104606, NASA Code 910.3, 1994.
A. da Silva and J. Guo. Documentation of the Physical-space Statistical Analysis System (PSAS). DAO Office Note 96-02, NASA Code 910.3, 1996.
MPI Forum. MPI: A Message-Passing Interface Standard. International Journal of Supercomputer Applications, 8(3&4):157–416, 1994.
C. H. Q. Ding and R. D. Ferraro. Climate Data Assimilation on a Massively Parallel Supercomputer. In Proceedings Supercomputing ’96. ACM-IEEE, 1996.
DAO staff. Algorithm Theoretical Basis Document. NASA Technical Memorandum, NASA Code 910.3, 1996.
M. J. Suárez and L. L. Takacs. Documentation of the ARIES/GEOS Dynamical Core: Version 2. NASA Technical Memorandum 104606, NASA Code 910.3, 1995.
D. S. Schaffer and M. J. Suárez. Next Stop: Teraflop; The Parallelization of an Atmospheric General Circulation Model. In A. Tentner, editor, Proceedings of High Performance Computing 1998. SCS, 1998.
A. Mirin, W. Dannevik, P. Eltgroth, M. Wehner J. Brown, and B. Chan. Performance of a Portable, Parallel Atmospheric General Circulation Model. In R. Sincovec, editor, Proceedings of the Sixth SIAM Conference on Parallel Processing for Scientific Computing. SIAM, 1992.
W. Sawyer, A. da Silva, P. M. Lyster, and L. L. Takacs. Parallel Grid Manipulations in Earth Science Calculations. In VECPAR 1998 Proceedings. Faculdade de Engenharia da Universidade do Porto, 1998.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sawyer, W. et al. (1998). Parallelization of the DAO atmospheric general circulation model. In: Kågström, B., Dongarra, J., Elmroth, E., Waśniewski, J. (eds) Applied Parallel Computing Large Scale Scientific and Industrial Problems. PARA 1998. Lecture Notes in Computer Science, vol 1541. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0095375
Download citation
DOI: https://doi.org/10.1007/BFb0095375
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65414-8
Online ISBN: 978-3-540-49261-0
eBook Packages: Springer Book Archive