Performance Analysis of a Hybrid Overset Multi-block Application on Multiple Architectures
- 337 Downloads
This paper presents a detailed performance analysis of a multi-block overset grid CFD application on multiple state-of-the-art computer architectures. The application is implemented using a hybrid MPI+OpenMP programming paradigm that exploits both coarse and fine-grain parallelism. The hybrid model also extends the applicability of multi-block programs to large clusters of SMP nodes. Extensive investigations were conducted on Cray SX-6, IBM Power3 and Power4, and SGI Origin3000 platforms. Overall results for complex vortex dynamics simulations demonstrate that the SX-6 achieves the highest performance and outperforms the RISC-based architectures; however, the best scaling performance was achieved on the Power3.
KeywordsProgramming Paradigm NASA Ames Research Master Thread Overset Grid Single Program Multiple Data
Unable to display preview. Download preview PDF.
- 1.Barszcz, E., Fatoohi, R., Venkatakrishnan, V., Weeratunga, S.: Solution of regular, sparse triangular linear systems on vector and distributed-memory multiprocessors, Tech. Rep. RNR-93-007, NASA Ames Research Center (1993)Google Scholar
- 2.Djomehri, M.J., Biswas, R., Lopez-Benitez, N.: Load balancing strategies for multi-block overset grid applications. In: Proc. 18th Intl. Conf. on Computers and Their Applications, Honolulu, HI, pp. 373–378 (2003)Google Scholar
- 3.Djomehri, M.J., Jin, H.: Hybrid MPI+OpenMP programming of an overset CFD solver and performance investigations, Technical Report NAS-02-002, NASA Ames Research Center (2002)Google Scholar
- 4.Earth Simulator Center, See URL, http://www.jamstec.go.jp
- 5.Meakin, R.: On adaptive refinement and overset structured grids. In: Proc. 13th AIAA Computational Fluid Dynamics Conf., Snowmass, CO (1997) Paper 97-1858Google Scholar
- 6.Steger, J.L., Dougherty, F.C., Benek, J.A.: A Chimera grid scheme, Advances in Grid Generation. In: ASME FED-5 (1983)Google Scholar
- 8.Wissink, A.M., Meakin, R.: Computational fluid dynamics with adaptive overset grids on parallel and distributed computer platforms. In: Proc. Intl. Conf. on Parallel and Distributed Processing Techniques and Applications, Las Vegas, NV, pp. 1628–1634 (1998)Google Scholar
- 9.Yarrow, M., Van der Wijngaart, R.: Communication improvement for the LU NAS Parallel Benchmark: A model for efficient parallel relaxation schemes, Technical Report NAS-97-032, NASA Ames Research Center (1997)Google Scholar