Análise de Desempenho e de Requisitos Computacionais Utilizando o Modelo Roofline: Um estudo para Aplicações de Inteligência Artificial e do NAS-HPC
Abstract
In this work, we propose the use of the Roofline model for an understanding of the computational requirements of the applications. NAS-HPC benchmarks and Artificial Intelligence algorithms were executed, analyzed, and classified according to their computational bottlenecks. The results were very positive for the understanding and classification of the different computational requirements of the applications, highlighting the different patterns among them.References
Frumkin, M., Jin, H., and Yan, J. (2009). Implementation of nas parallel benchmarks in high performance fortran.
Ibrahim, K., Williams, S., and Oliker, L. (2020). Performance Analysis of GPU Programming Models Using the Rooine Scaling Trajectories, pages 3–19.
Kim, K.-H., Kim, K.-H., and Park, Q.-H. (2011). Performance analysis and optimization of three-dimensional fdtd on gpu using rooine model. Computer Physics Communications, 182:1201–1207.
Lopes, A., Pratas, F., Sousa, L., and Ilic, A. (2017). Exploring gpu performance, power and energy-efciency bounds with cache-aware rooine modeling. In 2017 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pages 259–268.
Marques, D., Duarte, H., Ilic, A., Sousa, L., Belenov, R., Thierry, P., and Matveev, Z. A. (2017). Performance analysis with cache-aware rooine model in intel advisor. In 2017 Int. Conference on HPC Simulation (HPCS), pages 898–907.
Williams, S., Waterman, A., and Patterson, D. (2009). Rooine: an insightful visual performance model for multicore architectures. Commun. ACM, 52(4):65–76.
Yang, C., Gayatri, R., Kurth, T., Basu, P., Ronaghi, Z., Adetokunbo, A., Friesen, B., Cook, B., Doerer, D., Oliker, L., Deslippe, J., and Williams, S. (2018). An empirical rooine methodology for quantitatively assessing performance portability. In 2018 IEEE/ACM Int. Workshop on Performance, Portability and Productivity in HPC (P3HPC), pages 14–23.
Ibrahim, K., Williams, S., and Oliker, L. (2020). Performance Analysis of GPU Programming Models Using the Rooine Scaling Trajectories, pages 3–19.
Kim, K.-H., Kim, K.-H., and Park, Q.-H. (2011). Performance analysis and optimization of three-dimensional fdtd on gpu using rooine model. Computer Physics Communications, 182:1201–1207.
Lopes, A., Pratas, F., Sousa, L., and Ilic, A. (2017). Exploring gpu performance, power and energy-efciency bounds with cache-aware rooine modeling. In 2017 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pages 259–268.
Marques, D., Duarte, H., Ilic, A., Sousa, L., Belenov, R., Thierry, P., and Matveev, Z. A. (2017). Performance analysis with cache-aware rooine model in intel advisor. In 2017 Int. Conference on HPC Simulation (HPCS), pages 898–907.
Williams, S., Waterman, A., and Patterson, D. (2009). Rooine: an insightful visual performance model for multicore architectures. Commun. ACM, 52(4):65–76.
Yang, C., Gayatri, R., Kurth, T., Basu, P., Ronaghi, Z., Adetokunbo, A., Friesen, B., Cook, B., Doerer, D., Oliker, L., Deslippe, J., and Williams, S. (2018). An empirical rooine methodology for quantitatively assessing performance portability. In 2018 IEEE/ACM Int. Workshop on Performance, Portability and Productivity in HPC (P3HPC), pages 14–23.
Published
2020-10-21
How to Cite
SÁ, Vitor; KLÔH, Vinícius; SCHULZE, Bruno; FERRO, Mariza.
Análise de Desempenho e de Requisitos Computacionais Utilizando o Modelo Roofline: Um estudo para Aplicações de Inteligência Artificial e do NAS-HPC. In: UNDERGRADUATE RESEARCH WORKSHOP - SYMPOSIUM ON HIGH PERFORMANCE COMPUTING SYSTEMS (SSCAD), 21. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 22-29.
DOI: https://doi.org/10.5753/wscad_estendido.2020.14085.
