Selecting Directions for Parallel RAMS Performance Optimization

  • Celso L. Mendes INPE / LAC
  • Jairo Panetta INPE / CPTEC

Resumo


This paper presents the results from a preliminary performance evaluation of parallel RAMS, a numerical weather prediction model designed to simulate atmospheric phenomena at a regional level. The main goal in our work was to study in detail the performance of the current RAMS version, and to uncover aspects of its code where opportunities for optimization exist. We present our observations on both computation and communication performance of RAMS executing on a distributed memory parallel platform, and analyze their contributions to total program performance. From the observed data, we present simulations that predict bounds on potential performance gains for possible load balancing strategies.

Palavras-chave: Performance analysis, Numerical weather prediction, Performance measurement

Referências

BAILLIE, C.; MICHALAKES, J.; SKALIN, R. (Eds.) Parallel Computing, vol.23. Special issue: Regional Weather Models. North-Holland, 1997.

BERNAL. W.: KOFUJI, S.: SIPAHI. G.: ANDERSON. A.: NETTO, M. PAD Cluster: An Open, Modular and Low Cost High Performance Computing System. In: 11th Symposium on Computer Architecture and High Performance Computing, 1999. Proceedings... , Natal, Brazil, Sep. 1999.

DEROSE. L.: ZHANG, Y.: REED, D.A. SvPablo: A Multi-Language: Performance Analysis System. In: International Conference on Computer Performance Evaluation - Modelling Techniques and Tools, 10., 1998, Proceedings.... Palma de Mallorca. Sep. 1998, p.352-35S.

DRAKE. J.B.; FOSTER, I. (Eds.) Parallel Computing. vol.21. Special issue on applications: Climate and Weather Modeling. North-Holland, 1995.

HOLLINGSWORTH, J.K.: MILLER, B.P. Dynamic Control of Performance Monitoring on Large Scale Parallel Systems. Lecture Notes in Computer Science, V.1124. p.88-98, New York. Springer-Verlag, 1996.

MICHALAKES, J. MM90: A Scalable Parallel Implementaion of the Penn State/NCAR Mesoscale Model (MM5). Parallel Computing, V.23, p.2173-2186, 1997.

PACHECO, P. Parallel Programming with MPI. Morgan Kaufmann. San Francisco, 1997.

REED. O.A. ; AYDT, R.A.: NOE. R.J.: ROTH. P.C.; SHIELDS. K.A.: SCHWATRZ. B.; TAVERA, L.F. Scalable Performance Analysis: The Pablo Performance Analysis Environment. In: SCALABLE PARALLEL LIBRARIES CONFERENCE, 1993. Proceedings... IEEE Computer Society. Oct. 1993, p.l 04-113.

REED. D.A.: AYDT, R.A.: DeROSE, L.; MENDES, C.L.; RIBLER. R.L.: SHAFFER. E.; SIMITCI. H.: WETTER. J.S.: WELLS. D.R.; WHITMORE, S.; ZHANG. Y.Performance Analysis of Parallel Systems: Approaches and Open Problems. Joint Symposium on Parallel Processing - JSPP, Nagoy. Japan, p.239-256, Jun. 1998.

SATHYE, A.: XUE,M.; BASSETT,G.; DROEGEMEIER.K. Parallel Weather Modeling with the Advanced Regional Prediction System. Parallel Computing. V.23. p.2243-2256. 1997.

SCHATTLER. U.: KRENZIEN. E. The Parallel 'Deutschland Model' - A Message-Passing Version for Distributed Memory Computers. Parallel Computing. V.23, p.2215-2226, 1997.

TREMBACK, C. J.: WALKO, R. L. The Regional Atmospheric Modeling System (RAMS): Development for Parallel Processing Computer Architectures Fort Collins. USA, 1997.

WALLCRAFT, A.; MOORE, D.R. The NRL Layered Ocean Model. Parallel Computing. V.23, p.2227-2242, 1997.
Publicado
29/09/1999
MENDES, Celso L.; PANETTA, Jairo. Selecting Directions for Parallel RAMS Performance Optimization. In: INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING (SBAC-PAD), 11. , 1999, Natal. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 1999 . p. 85-92. DOI: https://doi.org/10.5753/sbac-pad.1999.19775.