Towards an Autonomous Framework for HPC Optimization: Using Machine Learning for Energy and Performance Modeling
Resumo
Alcançar altos nı́veis de desempenho com eficiência energética se tornou um grande desafio para a computação cientı́fica de alto desempenho. Para contornar esse desafio, espera-se que os próprios requisitos do problema cientı́fico orientem a orquestração de diferentes mecanismos de economia de energia, a fim de melhorar o equilı́brio entre o consumo de energia e o desempenho das aplicações. Para isso, é proposto o desenvolvimento de um framework autonômico para fazer essa orquestração. Neste trabalho são apresentadas as pesquisas em andamento para este desenvolvimento, mais especificamente, com foco na caracterização das aplicações cientı́ficas e das tarefas de modelagem de desempenho e consumo de energia utilizando técnicas de Aprendizado de Máquina.
Referências
Bhimani, J., Mi, N., Leeser, M., and Yang, Z. (2017). Fim: performance prediction for parallel computation in iterative data processing applications. In 2017 IEEE 10th International conference on cloud computing (CLOUD), pages 359–366. IEEE.
Carrington, L., Laurenzano, M. A., and Tiwari, A. (2013). Inferring large-scale computation behavior via trace extrapolation. In 2013 IEEE International Symposium on Parallel Distributed Processing, Workshops and Phd Forum, pages 1667–1674.
Ferro, M. (2015). Avaliação de Sistemas de Computação Massivamente Paralela e Distribuı́da: Uma metodologia voltada aos requisitos das aplicações cientı́ficas. Tese de doutorado, Laboratório Nacional de Computação Cientı́fica, Petrópolis - RJ.
Ferro, M., Mc Evoy, G., and Schulze, B. (2017a). Analysis of High Performance Applications Using Workload Requirements, pages 7–10. Springer International Publishing, Cham.
Ferro, M., Silva, G. D., Klóh, V. P., and Schulze, B. (2017b). Challenges in HPC Evaluation: Towards a methodology for scientific applications’ requirements. IOS Press, Amsterdam. accepted to publish.
Malakar, P., Balaprakash, P., Vishwanath, V., Morozov, V., and Kumaran, K. (2018). Benchmarking machine learning methods for performance modeling of scientific applications. 2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS).
Martı́nez, V., Dupros, F., Castro, M., and Navaux, P. (2017). Performance improvement of stencil computations for multi-core architectures based on machine learning. Procedia Computer Science, 108:305–314.
Messina, P. (2017). The exascale computing project. Computing in Science Engineering, 19(3):63–67.
Mury, A. R., Schulze, B., Licht, F., de Bona, L. C., and Ferro, M. (2015). A concurrency mitigation proposal for sharing environments: An affinity approach based on applications classes. In Al-Saidi, A., Fleischer, R., Maamar, Z., and Rana, O. F., editors, Intelligent Cloud Computing, volume 8993 of Lecture Notes in Computer Science, pages 26–45. Springer International Publishing.
Rajovic, N., Carpenter, P. M., Gelado, I., Puzovic, N., Ramirez, A., and Valero, M. (2013) Supercomputing with commodity cpus: Are mobile socs ready for hpc? In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC ’13, pages 40:1–40:12, New York, NY, USA. ACM.
Silva, G. D., Klôh, V. P., Yokoyama, A., Ferro, M., and Schulze, B. (2018) Smcis: Scientific applications monitoring tool for hpc environments. In 2018 Symposium on High Performance Computing Systems (WSCAD), pages 148–154. https://ieeexplore.ieee.org/document/8748925.
Simon, H. D. (2013). Barriers to Exascale Computing. Springer Berlin Heidelberg, Berlin, Heidelberg.
Wong, A., Rexachs, D., and Luque, E. (2015). Parallel application signature for performance analysis and prediction. IEEE Transactions on Parallel and Distributed Systems, 26(7):2009–2019.
Carrington, L., Laurenzano, M. A., and Tiwari, A. (2013). Inferring large-scale computation behavior via trace extrapolation. In 2013 IEEE International Symposium on Parallel Distributed Processing, Workshops and Phd Forum, pages 1667–1674.
Ferro, M. (2015). Avaliação de Sistemas de Computação Massivamente Paralela e Distribuı́da: Uma metodologia voltada aos requisitos das aplicações cientı́ficas. Tese de doutorado, Laboratório Nacional de Computação Cientı́fica, Petrópolis - RJ.
Ferro, M., Mc Evoy, G., and Schulze, B. (2017a). Analysis of High Performance Applications Using Workload Requirements, pages 7–10. Springer International Publishing, Cham.
Ferro, M., Silva, G. D., Klóh, V. P., and Schulze, B. (2017b). Challenges in HPC Evaluation: Towards a methodology for scientific applications’ requirements. IOS Press, Amsterdam. accepted to publish.
Malakar, P., Balaprakash, P., Vishwanath, V., Morozov, V., and Kumaran, K. (2018). Benchmarking machine learning methods for performance modeling of scientific applications. 2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS).
Martı́nez, V., Dupros, F., Castro, M., and Navaux, P. (2017). Performance improvement of stencil computations for multi-core architectures based on machine learning. Procedia Computer Science, 108:305–314.
Messina, P. (2017). The exascale computing project. Computing in Science Engineering, 19(3):63–67.
Mury, A. R., Schulze, B., Licht, F., de Bona, L. C., and Ferro, M. (2015). A concurrency mitigation proposal for sharing environments: An affinity approach based on applications classes. In Al-Saidi, A., Fleischer, R., Maamar, Z., and Rana, O. F., editors, Intelligent Cloud Computing, volume 8993 of Lecture Notes in Computer Science, pages 26–45. Springer International Publishing.
Rajovic, N., Carpenter, P. M., Gelado, I., Puzovic, N., Ramirez, A., and Valero, M. (2013) Supercomputing with commodity cpus: Are mobile socs ready for hpc? In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC ’13, pages 40:1–40:12, New York, NY, USA. ACM.
Silva, G. D., Klôh, V. P., Yokoyama, A., Ferro, M., and Schulze, B. (2018) Smcis: Scientific applications monitoring tool for hpc environments. In 2018 Symposium on High Performance Computing Systems (WSCAD), pages 148–154. https://ieeexplore.ieee.org/document/8748925.
Simon, H. D. (2013). Barriers to Exascale Computing. Springer Berlin Heidelberg, Berlin, Heidelberg.
Wong, A., Rexachs, D., and Luque, E. (2015). Parallel application signature for performance analysis and prediction. IEEE Transactions on Parallel and Distributed Systems, 26(7):2009–2019.
Publicado
08/11/2019
Como Citar
KLÔH, Vinícius; GRITZ, Matheus; SCHULZE, Bruno; FERRO, Mariza.
Towards an Autonomous Framework for HPC Optimization: Using Machine Learning for Energy and Performance Modeling. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 20. , 2019, Campo Grande.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 438-445.
DOI: https://doi.org/10.5753/wscad.2019.8689.
