ComprehensiveBench: Um Benchmark Flexível para Avaliação de Balanceadores de Carga no Ambiente de Programação Charm++
Resumo
Em aplicações paralelas que possuem tarefas com cargas desbalanceadas, os recursos de hardware não são utilizados eficientemente. Técnicas de balanceamento de carga visam amenizar esse problema e, consequentemente, podem melhorar o desempenho da aplicação paralela. Entretanto, identificar qual algoritmo de balanceamento de carga seria o mais indicado em um dado contexto é um problema não trivial. Nesse contexto, este artigo apresenta um benchmark para a avaliação de balanceadores de carga periódicos no ambiente paralelo Charm++. O benchmark tem os objetivos de auxiliar no desenvolvimento de novas técnicas de balanceamento e de auxiliar na escolha de um balanceador de carga específico para uma aplicação paralela qualquer. Por fim, o artigo apresenta avaliações de diferentes balanceadores de carga periódicos do Charm++ realizadas com o benchmark desenvolvido.Referências
Kale, L. V. and Krishnan, S. (1993). Charm++: A portable concurrent object oriented system based on C++. In Proceedings of the Eighth Annual Conference on ObjectOriented Programming Systems, Languages, and Applications (OOPSLA 1993), pages 91–108. ACM.
Leung, J. Y. T. (2004). Handbook of scheduling: algorithms, models, and performance analysis. Chapman & Hall/CRC computer and information science series. Chapman & Hall/CRC.
Menon, H., Jain, N., Zheng, G., and Kalé, L. V. (2012). Automated Load Balancing Invocation based on Application Characteristics. In IEEE Cluster 12, Beijing, China.
Pilla, L. L., Ribeiro, C. P., Cordeiro, D., Mei, C., Bhatele, A., Navaux, Broquedis, F., Mehaut, J., and Kale, L. V. (2012). A Hierarchical Approach for Load Balancing on Parallel Multi-core Systems. In Parallel Processing (ICPP), 2012 41st International Conference on, pages 118–127.
Pilla, L. L., Ribeiro, C. P., Coucheney, P., Broquedis, F., Gaujal, B., Navaux, P. O. A., and Méaut, J.-F. (2014). A Topology-Aware Load Balancing Algorithm for Clustered Hierarchical Multi-Core Machines. Future Generation Computer Systems, 30(0):191– 201.
Rodrigues, E. R., Navaux, P. O. A., Panetta, J., Fazenda, A., Mendes, C. L., and Kale, L. V. (2010). A Comparative Analysis of Load Balancing Algorithms Applied to a Weather Forecast Model. Computer Architecture and High Performance Computing, Symposium on, 0:71–78.
Tesser, R., Pilla, L. L., Navaux, P. O. A., Dupros, F., Mehaut, J. F., and Mendes, C. (2014). Using Dynamic Load Balancing to Improve the Performance of Seismic Wave Simulations. In Parallel, Distributed and Network-Based Processing (PDP), 2014 22st Euromicro International Conference on, pages 196–203.
Zheng, G. (2005). Achieving high performance on extremely large parallel machines: performance prediction and load balancing. PhD thesis, Department of Computer Science, University of Illinois at Urbana-Champaign.
Zheng, G., Bhatele, A., Meneses, E., and Kale, L. V. (2011). Periodic Hierarchical Load International Journal of High Performance Balancing for Large Supercomputers. Computing Applications (IJHPCA).
Leung, J. Y. T. (2004). Handbook of scheduling: algorithms, models, and performance analysis. Chapman & Hall/CRC computer and information science series. Chapman & Hall/CRC.
Menon, H., Jain, N., Zheng, G., and Kalé, L. V. (2012). Automated Load Balancing Invocation based on Application Characteristics. In IEEE Cluster 12, Beijing, China.
Pilla, L. L., Ribeiro, C. P., Cordeiro, D., Mei, C., Bhatele, A., Navaux, Broquedis, F., Mehaut, J., and Kale, L. V. (2012). A Hierarchical Approach for Load Balancing on Parallel Multi-core Systems. In Parallel Processing (ICPP), 2012 41st International Conference on, pages 118–127.
Pilla, L. L., Ribeiro, C. P., Coucheney, P., Broquedis, F., Gaujal, B., Navaux, P. O. A., and Méaut, J.-F. (2014). A Topology-Aware Load Balancing Algorithm for Clustered Hierarchical Multi-Core Machines. Future Generation Computer Systems, 30(0):191– 201.
Rodrigues, E. R., Navaux, P. O. A., Panetta, J., Fazenda, A., Mendes, C. L., and Kale, L. V. (2010). A Comparative Analysis of Load Balancing Algorithms Applied to a Weather Forecast Model. Computer Architecture and High Performance Computing, Symposium on, 0:71–78.
Tesser, R., Pilla, L. L., Navaux, P. O. A., Dupros, F., Mehaut, J. F., and Mendes, C. (2014). Using Dynamic Load Balancing to Improve the Performance of Seismic Wave Simulations. In Parallel, Distributed and Network-Based Processing (PDP), 2014 22st Euromicro International Conference on, pages 196–203.
Zheng, G. (2005). Achieving high performance on extremely large parallel machines: performance prediction and load balancing. PhD thesis, Department of Computer Science, University of Illinois at Urbana-Champaign.
Zheng, G., Bhatele, A., Meneses, E., and Kale, L. V. (2011). Periodic Hierarchical Load International Journal of High Performance Balancing for Large Supercomputers. Computing Applications (IJHPCA).
Publicado
08/10/2014
Como Citar
BOZZETTI, Tiago; PILLA, Laércio; CASTRO, Márcio; NAVAUX, Philippe.
ComprehensiveBench: Um Benchmark Flexível para Avaliação de Balanceadores de Carga no Ambiente de Programação Charm++. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 15. , 2014, São José dos Campos.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2014
.
p. 180-191.
DOI: https://doi.org/10.5753/wscad.2014.15010.
