D-STHARk: Avaliando Escalonadores Dinâmicos de Tarefas em Arquiteturas Híbridas Simuladas
Resumo
Para melhor explorar novas arquiteturas computacionais, composta por diversas Unidades de Processamento (UPs), tais como CPUs, GPUs e Intel Xeon Phi, estudos recentes focam em propor ambientes de execução que oferecem métodos de escalonamento dinâmico para diferentes UPs. A principal limitação dessas propostas são as restrições de configuração de sistema para avaliá-las. Nesse trabalho apresentamos o D-STHARk, (Dynamic Scheduling of Tasks in Hybrid Simulated ARchitectures), uma ferramenta que provê um ambiente completo de simulação de arquiteturas híbridas para avaliação de estratégias de escalonamento dinâmico. Simulamos com o D-STHARk experimentos apresentados em trabalhos recentes alcançando as mesmas conclusões.
Referências
Andrade, G., Ferreira, R., Teodoro, G., da Rocha, L. C., Saltz, J. H., and Kurc¸, T. M. (2014a). Efficient execution of microscopy image analysis on cpu, gpu, and MIC equipped cluster systems. In 26th IEEE SBAC-PAD Paris, France.
Andrade, G., Ramos, G., Madeira, D., Sachetto, R., Clua, E., Ferreira, R., and Rocha, L. (2014b). Efficient dynamic scheduling of heterogeneous applications in hybrid architectures. In Proceedings of ACM SAC, pages 866–871.
Augonnet, C., Thibault, S., and Namyst, R. (2010). StarPU: a Runtime System for Scheduling Tasks over Accelerator-Based Multicore Machines. Rapport de recherche RR-7240, INRIA.
Bradski, G. (2000). The OpenCV Library. Dr. Dobb’s Journal of Software Tools.
Bueno, J., Planas, J., Duran, A., Badia, R., Martorell, X., Ayguade, E., and Labarta, J. (2012). Productive Programming of GPU Clusters with OmpSs. In 26th IEEE IPDPS.
Fatica, M. and Luebke, D. (2007). High performance computing with CUDA. Supercomputing 2007 tutorial. In Supercomputing 2007 tutorial notes.
Jeffers, J. and Reinders, J. (2013). Intel Xeon Phi Coprocessor High Performance Programming. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1st edition.
Lima, J. V. F., Broquedis, F., Gautier, T., and Raffin, B. (2013). Preliminary experiments with xkaapi on intel xeon phi coprocessor. In 25th IEEE SBAC-PAD, pages 105–112.
Ravi, V., Ma, W., Chiu, D., and Agrawal, G. (2014). Compiler and runtime support for enabling generalized reduction computations on heterogeneous parallel configurations. In ACM Supercomputing.
Rossbach, C. J., Currey, J., Silberstein, M., Ray, B., and Witchel, E. (2011). PTask: operating system abstractions to manage GPUs as compute devices. In ACM SOSP.
Teodoro, G., Kurc, T., Kong, J., Cooper, L., and Saltz, J. (2014). Comparative Performance Analysis of Intel Xeon Phi, GPU, and CPU: A Case Study from Microscopy Image Analysis. In IPDPS.
Andrade, G., Ramos, G., Madeira, D., Sachetto, R., Clua, E., Ferreira, R., and Rocha, L. (2014b). Efficient dynamic scheduling of heterogeneous applications in hybrid architectures. In Proceedings of ACM SAC, pages 866–871.
Augonnet, C., Thibault, S., and Namyst, R. (2010). StarPU: a Runtime System for Scheduling Tasks over Accelerator-Based Multicore Machines. Rapport de recherche RR-7240, INRIA.
Bradski, G. (2000). The OpenCV Library. Dr. Dobb’s Journal of Software Tools.
Bueno, J., Planas, J., Duran, A., Badia, R., Martorell, X., Ayguade, E., and Labarta, J. (2012). Productive Programming of GPU Clusters with OmpSs. In 26th IEEE IPDPS.
Fatica, M. and Luebke, D. (2007). High performance computing with CUDA. Supercomputing 2007 tutorial. In Supercomputing 2007 tutorial notes.
Jeffers, J. and Reinders, J. (2013). Intel Xeon Phi Coprocessor High Performance Programming. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1st edition.
Lima, J. V. F., Broquedis, F., Gautier, T., and Raffin, B. (2013). Preliminary experiments with xkaapi on intel xeon phi coprocessor. In 25th IEEE SBAC-PAD, pages 105–112.
Ravi, V., Ma, W., Chiu, D., and Agrawal, G. (2014). Compiler and runtime support for enabling generalized reduction computations on heterogeneous parallel configurations. In ACM Supercomputing.
Rossbach, C. J., Currey, J., Silberstein, M., Ray, B., and Witchel, E. (2011). PTask: operating system abstractions to manage GPUs as compute devices. In ACM SOSP.
Teodoro, G., Kurc, T., Kong, J., Cooper, L., and Saltz, J. (2014). Comparative Performance Analysis of Intel Xeon Phi, GPU, and CPU: A Case Study from Microscopy Image Analysis. In IPDPS.
Publicado
04/07/2016
Como Citar
TOLEDO, Sávyo; MELO, Danilo; ANDRADE, Guilherme; MOURÃO, Fernando; ROCHA, Leonardo.
D-STHARk: Avaliando Escalonadores Dinâmicos de Tarefas em Arquiteturas Híbridas Simuladas. In: CONCURSO DE TRABALHOS DE INICIAÇÃO CIENTÍFICA DA SBC (CTIC-SBC), 35. , 2016, Porto Alegre.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2016
.
p. 81-90.
