Eficiência Energética e Desempenho de E/S com Arquiteturas de Baixa Potência
Resumo
Este artigo apresenta uma análise de desempenho e eficiência energética de operações de E/S em processadores de baixo consumo quando comparados a arquiteturas convencionais. O objetivo é analisar a viabilidade da utilização destes dispositivos na implementação de sistemas de arquivos para HPC. Os resultados mostraram que o uso do MPSoC levou a uma eficiência energética até 136 vezes maior do que o observado com o PC. Essa vantagem é causada por uma demanda de potência até 6,7 vezes menor. Concluiu-se que um servidor de armazenamento PC com HDD pode ser substituído por múltiplos MPSoC com SSD para manter um desempenho semelhante com uma demanda de potência até 85% menor.
Referências
Amur, H., Cipar, J., e Gupta, V. (2010). Robust and Flexible Power-Proportional Storage. Proceedings of the 1st ACM symposium on Cloud computing, páginas 217–228.
Blake, G., Dreslinski, R., e Mudge, T. (2009). A Survey of Multicore Processors. IEEE Signal Proc. Magazine, 26(6):26–37.
Cardosa, M., Singh, A., Pucha, H., e Chandra, A. (2012). Exploiting spatio-temporal traIEEE Transactions on Computers, deoffs for energy-aware MapReduce in the cloud. 61(12):1737–1751.
Carrera, E. V., Pinheiro, E., e Bianchini, R. (2003). Conserving disk energy in network servers. Proceedings of the 17th annual international conference on Supercomputing ICS '03, página 86.
Dunn, O. J. (1961). Multiple comparisons among means. Journal of the American Statistical Association, 56(293):52–64.
Ge, R., Feng, X., e Sun, X. H. (2012). SERA-IO: Integrating energy consciousness into parallel I/O middleware. Em Proceedings 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGrid 2012, páginas 204–211.
Gurumurthi, S., Sivasubramaniam, A., Kandemir, M., e Franke, H. (2003). DRPM: dynamic speed control for power management in server class disks. 30th Annual International Symposium on Computer Architecture, 2003. Proceedings.
Hosseinimotlagh, S., Khunjush, F., e Hosseinimotlagh, S. (2014). A cooperative twotier energy-aware scheduling for real-time tasks in computing clouds. Em Proceedings..., páginas 178–182. Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), IEEE.
Ibrahim, S., Phan, T.-D., Carpen-Amarie, A., Chihoub, H.-E., Moise, D., e Antoniu, G. (2016). Governing energy consumption in hadoop through cpu frequency scaling: An analysis. Future Generation Computer Systems, 54:219–232.
Kim, J., Chou, J., e Rotem, D. (2011). Energy proportionality and performance in data parallel computing clusters. Lecture Notes in Computer Science (including subseries Lecture Notes in Articial Intelligence and Lecture Notes in Bioinformatics), 6809 LNCS:414– 431.
Kogge, P., Bergman, K., Borkar, S., Campbell, D., Carson, W., Dally, W., Denneau, M., Franzon, P., Harrod, W., Hill, K., et al. (2008). Exascale computing study: Technology challenges in achieving exascale systems. páginas 1–297.
Lee, W. Y. (2009). Energy-saving dvfs scheduling of multiple periodic real-time tasks on multi-core processors. Em Proceedings..., páginas 216–223. International Symposium on Distributed Simulation and Real Time Applications, IEEE Computer Society.
Lilliefors, H. W. (1967). On the kolmogorov-smirnov test for normality with mean and variance unknown. Journal of the American Statistical Association, 62(318):399–402.
Lim, M. Y., Freeh, V. W., e Lowenthal, D. K. (2006). Adaptive, transparent frequency and voltage scaling of communication phases in MPI programs. Em Proceedings..., páginas 14–14. Supercomputers Conference (SC), ACM/IEEE.
Nijim, M., Manzanares, A., Ruan, X., e Qin, X. (2009). Hybud: An energy-efcient architecture for hybrid parallel disk systems. Proceedings International Conference on Computer Communications and Networks, ICCCN, 0845257(2005).
Padoin, E. L., Pilla, L. L., Boito, F. Z., Kassick, R. V., Velho, P., e Navaux, P. O. A. (2013). Evaluating application performance and energy consumption on hybrid CPU+GPU architecture. Cluster Computing, 16(3):511–525.
Padoin, E. L., Pilla, L. L., Castro, M., Boito, F. Z., Navaux, P. O. A., e Mehaut, J.-F. (2014). Performance/energy trade-off in scientic computing: The case of ARM big.LITTLE and Intel Sandy Bridge. IET Computers & Digital Techniques, 2(3):1–14.
Peraza, J., Tiwari, A., Laurenzano, M., Carrington, L., e Snavely, A. (2013). PMaC's green queue: a framework for selecting energy optimal DVFS congurations in large scale MPI applications. Concurrency and Computation: Practice and Experience, páginas 1–20.
Saito, T., Sato, K., Sato, H., e Matsuoka, S. (2013). Energy-aware I/O optimization for checkpoint and restart on a NAND ash memory system. Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale FTXS '13, página 41.
Shang, P. e Wang, J. (2011). A novel power management for CMP systems in data-intensive environment. Proceedings 25th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2011, páginas 92–103.
Welch, B. e Noer, G. (2013). Optimizing a hybrid SSD/HDD HPC storage system based on le size distributions. Em 2013 IEEE 29th Symposium on Mass Storage Systems and Technologies (MSST), páginas 1–12.
Younge, A., von Laszewski, G., Wang, L., Lopez-Alarcon, S., e Carithers, W. (2010). Efcient resource management for cloud computing environments. Em International Conference on Green Computing, páginas 357–364. IEEE.
Zhu, Q., Chen, Z., Tan, L., Zhou, Y., Keeton, K., e Wilkes, J. (2005). Hibernator: helping disk arrays sleep through the winter. Proceedings of the twentieth ACM symposium on Operating systems principles SOSP '05, 39:177.
Blake, G., Dreslinski, R., e Mudge, T. (2009). A Survey of Multicore Processors. IEEE Signal Proc. Magazine, 26(6):26–37.
Cardosa, M., Singh, A., Pucha, H., e Chandra, A. (2012). Exploiting spatio-temporal traIEEE Transactions on Computers, deoffs for energy-aware MapReduce in the cloud. 61(12):1737–1751.
Carrera, E. V., Pinheiro, E., e Bianchini, R. (2003). Conserving disk energy in network servers. Proceedings of the 17th annual international conference on Supercomputing ICS '03, página 86.
Dunn, O. J. (1961). Multiple comparisons among means. Journal of the American Statistical Association, 56(293):52–64.
Ge, R., Feng, X., e Sun, X. H. (2012). SERA-IO: Integrating energy consciousness into parallel I/O middleware. Em Proceedings 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGrid 2012, páginas 204–211.
Gurumurthi, S., Sivasubramaniam, A., Kandemir, M., e Franke, H. (2003). DRPM: dynamic speed control for power management in server class disks. 30th Annual International Symposium on Computer Architecture, 2003. Proceedings.
Hosseinimotlagh, S., Khunjush, F., e Hosseinimotlagh, S. (2014). A cooperative twotier energy-aware scheduling for real-time tasks in computing clouds. Em Proceedings..., páginas 178–182. Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), IEEE.
Ibrahim, S., Phan, T.-D., Carpen-Amarie, A., Chihoub, H.-E., Moise, D., e Antoniu, G. (2016). Governing energy consumption in hadoop through cpu frequency scaling: An analysis. Future Generation Computer Systems, 54:219–232.
Kim, J., Chou, J., e Rotem, D. (2011). Energy proportionality and performance in data parallel computing clusters. Lecture Notes in Computer Science (including subseries Lecture Notes in Articial Intelligence and Lecture Notes in Bioinformatics), 6809 LNCS:414– 431.
Kogge, P., Bergman, K., Borkar, S., Campbell, D., Carson, W., Dally, W., Denneau, M., Franzon, P., Harrod, W., Hill, K., et al. (2008). Exascale computing study: Technology challenges in achieving exascale systems. páginas 1–297.
Lee, W. Y. (2009). Energy-saving dvfs scheduling of multiple periodic real-time tasks on multi-core processors. Em Proceedings..., páginas 216–223. International Symposium on Distributed Simulation and Real Time Applications, IEEE Computer Society.
Lilliefors, H. W. (1967). On the kolmogorov-smirnov test for normality with mean and variance unknown. Journal of the American Statistical Association, 62(318):399–402.
Lim, M. Y., Freeh, V. W., e Lowenthal, D. K. (2006). Adaptive, transparent frequency and voltage scaling of communication phases in MPI programs. Em Proceedings..., páginas 14–14. Supercomputers Conference (SC), ACM/IEEE.
Nijim, M., Manzanares, A., Ruan, X., e Qin, X. (2009). Hybud: An energy-efcient architecture for hybrid parallel disk systems. Proceedings International Conference on Computer Communications and Networks, ICCCN, 0845257(2005).
Padoin, E. L., Pilla, L. L., Boito, F. Z., Kassick, R. V., Velho, P., e Navaux, P. O. A. (2013). Evaluating application performance and energy consumption on hybrid CPU+GPU architecture. Cluster Computing, 16(3):511–525.
Padoin, E. L., Pilla, L. L., Castro, M., Boito, F. Z., Navaux, P. O. A., e Mehaut, J.-F. (2014). Performance/energy trade-off in scientic computing: The case of ARM big.LITTLE and Intel Sandy Bridge. IET Computers & Digital Techniques, 2(3):1–14.
Peraza, J., Tiwari, A., Laurenzano, M., Carrington, L., e Snavely, A. (2013). PMaC's green queue: a framework for selecting energy optimal DVFS congurations in large scale MPI applications. Concurrency and Computation: Practice and Experience, páginas 1–20.
Saito, T., Sato, K., Sato, H., e Matsuoka, S. (2013). Energy-aware I/O optimization for checkpoint and restart on a NAND ash memory system. Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale FTXS '13, página 41.
Shang, P. e Wang, J. (2011). A novel power management for CMP systems in data-intensive environment. Proceedings 25th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2011, páginas 92–103.
Welch, B. e Noer, G. (2013). Optimizing a hybrid SSD/HDD HPC storage system based on le size distributions. Em 2013 IEEE 29th Symposium on Mass Storage Systems and Technologies (MSST), páginas 1–12.
Younge, A., von Laszewski, G., Wang, L., Lopez-Alarcon, S., e Carithers, W. (2010). Efcient resource management for cloud computing environments. Em International Conference on Green Computing, páginas 357–364. IEEE.
Zhu, Q., Chen, Z., Tan, L., Zhou, Y., Keeton, K., e Wilkes, J. (2005). Hibernator: helping disk arrays sleep through the winter. Proceedings of the twentieth ACM symposium on Operating systems principles SOSP '05, 39:177.
Publicado
05/10/2016
Como Citar
PAVAN, Pablo; LORENZONI, Ricardo; BEZ, Jean; PADOIN, Edson; BOITO, Francieli; NAVAUX, Philipe; MÉHAUT, Jean-François.
Eficiência Energética e Desempenho de E/S com Arquiteturas de Baixa Potência. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 17. , 2016, Aracajú.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2016
.
p. 1-12.
DOI: https://doi.org/10.5753/wscad.2016.14243.
