Implementação MPIC++ e HPX dos Kernels NPB
Resumo
Este artigo apresenta a implementação paralela dos cinco kernels pertencentes ao NAS Parallel Benchmarks (NPB) com MPIC++ e HPX para execução em arquiteturas de cluster. Os resultados demonstraram que o modelo de programação HPX pode ser mais eficiente do que MPIC++ em algoritmos tais como transformada rápida de Fourier, ordenação e Gradiente Conjugado.Referências
Bailey, D. H., Barszcz, E., Barton, J. T., Browning, D. S., Carter, R. L., Dagum, L., Fatoohi, R. A., Frederickson, P. O., Lasinski, T. A., Schreiber, R. S., et al. (1991). The NAS parallel benchmarks. The International Journal of Supercomputing Applications, 5(3):63–73.
Fürlinger, K., Fuchs, T., and Kowalewski, R. (2016). Dash: A c++ pgas library for distributed data structures and parallel algorithms. In IEEE 18th Intern. Conf. on High Performance Computing and Communications, pages 983–990. IEEE.
Griebler, D., Loff, J., Mencagli, G., Danelutto, M., and Fernandes, L. G. (2018). Efcient NAS benchmark kernels with C++ parallel programming. In 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP), pages 733–740. IEEE.
Kaiser, H., Heller, T., Adelstein-Lelbach, B., Serio, A., and Fey, D. (2014). Hpx: A task based programming model in a global address space. In Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, page 6. ACM.
Leonarczyk, R. and Griebler, D. (2020). Implementação MPIC++ dos kernels NPB EP, IS e CG. In 20th Escola Regional de Alto Desempenho da Região Sul (ERAD-RS), pages 101–104, Santa Maria, RS, Brazil. Sociedade Brasileira de Computação.
Sakae, Y. and Matsuoka, S. (2001). MPC++ Performance for Commodity Clustering. In International Conference on High-Performance Computing and Networking, pages 503–512. Springer.
Fürlinger, K., Fuchs, T., and Kowalewski, R. (2016). Dash: A c++ pgas library for distributed data structures and parallel algorithms. In IEEE 18th Intern. Conf. on High Performance Computing and Communications, pages 983–990. IEEE.
Griebler, D., Loff, J., Mencagli, G., Danelutto, M., and Fernandes, L. G. (2018). Efcient NAS benchmark kernels with C++ parallel programming. In 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP), pages 733–740. IEEE.
Kaiser, H., Heller, T., Adelstein-Lelbach, B., Serio, A., and Fey, D. (2014). Hpx: A task based programming model in a global address space. In Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, page 6. ACM.
Leonarczyk, R. and Griebler, D. (2020). Implementação MPIC++ dos kernels NPB EP, IS e CG. In 20th Escola Regional de Alto Desempenho da Região Sul (ERAD-RS), pages 101–104, Santa Maria, RS, Brazil. Sociedade Brasileira de Computação.
Sakae, Y. and Matsuoka, S. (2001). MPC++ Performance for Commodity Clustering. In International Conference on High-Performance Computing and Networking, pages 503–512. Springer.
Publicado
14/04/2021
Como Citar
LEONARCZYK, Ricardo; GRIEBLER, Dalvan.
Implementação MPIC++ e HPX dos Kernels NPB. In: ESCOLA REGIONAL DE ALTO DESEMPENHO DA REGIÃO SUL (ERAD-RS), 21. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 81-84.
ISSN 2595-4164.
DOI: https://doi.org/10.5753/eradrs.2021.14780.
