Análise da Eficiência Energética de uma Aplicação HPC de Geofísica em um Cluster de Baixo Consumo
Resumo
Neste artigo buscamos analisar a viabilidade e a eficiência energética ao utilizar um cluster não convencional de processadores ARM para executar uma aplicação científica real. Utilizamos, para este fim, o Ondes3D que permite simular eventos geofísicos. Apresentamos um comparativo entre a execução da aplicação empregando diferentes flags de compilação e diferentes valores para a frequência do processador. Os resultados demonstraram ganhos de até 54.24% no tempo para a solução e 53.24% na energia para a solução, quando comparado com a execução sem nenhuma otimização. Estes resultados apontam que é possível explorar tal plataforma através da correta configuração do ambiente para se obter um bom equilíbrio entre desempenho e custo energético.
Referências
Allwinner (2013). A20 User Manual. Technical Report 1, Allwinner Technology.
Allwinner (2015). Allwinner Technology Company. http://www.allwinnertech.com/en/about/company.htm. Accessed: 2015-05-30.
Appel, D. and Petersson, N. A. (2009). A Stable Finite Difference Method for the Elastic Wave Equation on Complex Geometries with Free Surfaces. Communications in Computational Physics, 5(1):84–107.
ARM (2015). ARM Processor Architecture. http://www.arm.com/products/ processors/instruction-set-architectures/index.php. Accessed: 2015-05-11.
Cebrián, J. M., Natvig, L., and Meyer, J. C. (2014). Performance and energy impact of parallelization and vectorization techniques in modern microprocessors. Computing, 96(12):1179–1193.
Cortex-A7 (2013). Cortex-A7 MPCore. Technical Report p5, ARM.
CPUFreq (2015). CPU Frequency Scaling. https://wiki.archlinux.org/index.php/CPU_frequency_scaling. Accessed: 2015-07-09.
Cubieboard (2015). Cubieboard Open-Source Main-Boards. http://docs.cubieboard.org/products/start. Accessed: 2015-05-30.
Dupros, F., Aochi, H., and Ducellier, A. (2008). Exploiting Intensive Multithreading for the Efcient Simulation of 3D Seismic Wave Propagation. 11th IEEE International Conference on Computational Science and Engineering, pages 253–260.
Dupros, F., Martina, F. D., Foerster, E., Komatitsch, D., and Romand, J. (2010). High-performance nite-element simulations of seismic wave propagation in threedimensional nonlinear inelastic geological media. Parallel Computing Parallel Matrix Algorithms and Applications, 36(5–5):308–325.
Keller, V. (2012). Energy-to-solution: a today’s metric for tomorrows’ concerns. http://www.ig.fpms.ac.be/sites/default/files/FGPS175-Keller.pdf. Accessed: 2015-07-05.
Laurenzano, M. A., Tiwari, A., Jundt, A., Peraza, J., Jr, W. A. W., Campbell, R., and Carrington, L. (2014). Characterizing the performance-energy tradeoff of small arm In Euro-Par 2014 Parallel Processing, pages 124–137. cores in hpc computation. Springer.
Ou, Z., Pang, B., Deng, Y., Nurminen, J. K., Ylä-Jääski, A., and Hui, P. (2012). Energyand cost-efciency analysis of arm-based clusters. In 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pages 115–123. IEEE/ACM.
Padoin, E. L., de Oliveira, D. A. G., Velho, P., and Navaux, P. O. A. (2012a). Evaluating Performance and Energy on ARM-based Clusters for High Performance Computing. In 41st International Conference on Parallel Processing Workshops Evaluating, pages 165–172.
Padoin, E. L., de Oliveira, D. A. G., Velho, P., and Navaux, P. O. A. (2012b). Time-toSolution and Energy-to-Solution: A Comparison Between ARM anx Xeon. In 2012 Third Workshop on Applications for Multi-Core Architecture, pages 48–53. IEEE.
Padoin, E. L., Velho, P., de Oliveira, D. A. G., Navaux, P. O. A., and Mehaut, J.-F. (2014). Tuning Performance and Energy Consumption of HPC Applications on ARM MPSoCs. In 5th Workshop on Applications for Multi-Core Architectures, pages 1–6.
Reed, D. A. and Dongarra, J. (2015). Exascale Computing and Big Data. Communications of the ACM, 58(7):56–68.
Tesser, R. K., Pilla, L. L., Dupros, F., Navaux, P. O. A., Mehau, J.-F., and Mendes, C. (2014). Improving the Performance of Seismic Wave Simulations with Dynamic Load Balancing. Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, pages 196–203.
Allwinner (2015). Allwinner Technology Company. http://www.allwinnertech.com/en/about/company.htm. Accessed: 2015-05-30.
Appel, D. and Petersson, N. A. (2009). A Stable Finite Difference Method for the Elastic Wave Equation on Complex Geometries with Free Surfaces. Communications in Computational Physics, 5(1):84–107.
ARM (2015). ARM Processor Architecture. http://www.arm.com/products/ processors/instruction-set-architectures/index.php. Accessed: 2015-05-11.
Cebrián, J. M., Natvig, L., and Meyer, J. C. (2014). Performance and energy impact of parallelization and vectorization techniques in modern microprocessors. Computing, 96(12):1179–1193.
Cortex-A7 (2013). Cortex-A7 MPCore. Technical Report p5, ARM.
CPUFreq (2015). CPU Frequency Scaling. https://wiki.archlinux.org/index.php/CPU_frequency_scaling. Accessed: 2015-07-09.
Cubieboard (2015). Cubieboard Open-Source Main-Boards. http://docs.cubieboard.org/products/start. Accessed: 2015-05-30.
Dupros, F., Aochi, H., and Ducellier, A. (2008). Exploiting Intensive Multithreading for the Efcient Simulation of 3D Seismic Wave Propagation. 11th IEEE International Conference on Computational Science and Engineering, pages 253–260.
Dupros, F., Martina, F. D., Foerster, E., Komatitsch, D., and Romand, J. (2010). High-performance nite-element simulations of seismic wave propagation in threedimensional nonlinear inelastic geological media. Parallel Computing Parallel Matrix Algorithms and Applications, 36(5–5):308–325.
Keller, V. (2012). Energy-to-solution: a today’s metric for tomorrows’ concerns. http://www.ig.fpms.ac.be/sites/default/files/FGPS175-Keller.pdf. Accessed: 2015-07-05.
Laurenzano, M. A., Tiwari, A., Jundt, A., Peraza, J., Jr, W. A. W., Campbell, R., and Carrington, L. (2014). Characterizing the performance-energy tradeoff of small arm In Euro-Par 2014 Parallel Processing, pages 124–137. cores in hpc computation. Springer.
Ou, Z., Pang, B., Deng, Y., Nurminen, J. K., Ylä-Jääski, A., and Hui, P. (2012). Energyand cost-efciency analysis of arm-based clusters. In 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pages 115–123. IEEE/ACM.
Padoin, E. L., de Oliveira, D. A. G., Velho, P., and Navaux, P. O. A. (2012a). Evaluating Performance and Energy on ARM-based Clusters for High Performance Computing. In 41st International Conference on Parallel Processing Workshops Evaluating, pages 165–172.
Padoin, E. L., de Oliveira, D. A. G., Velho, P., and Navaux, P. O. A. (2012b). Time-toSolution and Energy-to-Solution: A Comparison Between ARM anx Xeon. In 2012 Third Workshop on Applications for Multi-Core Architecture, pages 48–53. IEEE.
Padoin, E. L., Velho, P., de Oliveira, D. A. G., Navaux, P. O. A., and Mehaut, J.-F. (2014). Tuning Performance and Energy Consumption of HPC Applications on ARM MPSoCs. In 5th Workshop on Applications for Multi-Core Architectures, pages 1–6.
Reed, D. A. and Dongarra, J. (2015). Exascale Computing and Big Data. Communications of the ACM, 58(7):56–68.
Tesser, R. K., Pilla, L. L., Dupros, F., Navaux, P. O. A., Mehau, J.-F., and Mendes, C. (2014). Improving the Performance of Seismic Wave Simulations with Dynamic Load Balancing. Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, pages 196–203.
Publicado
18/10/2015
Como Citar
BEZ, Jean Luca; BERNART, Eliezer; DOS SANTOS, Fernando; SCHNORR, Lucas; NAVAUX, Phillipe.
Análise da Eficiência Energética de uma Aplicação HPC de Geofísica em um Cluster de Baixo Consumo. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 16. , 2015, Florianópolis.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2015
.
p. 228-239.
DOI: https://doi.org/10.5753/wscad.2015.14286.
