Parallelization of a Large-Scale Watersheds Hydrological Model using CPU and GPU

  • Henrique R. A. Freitas INPE
  • Celso Mendes INPE

Resumo


Hydrological models are commonly employed to calculate water flows on rivers and watersheds for the analysis of extreme events in nature. Computations in these models can grow depending on the numerical method, and also on the spatial and temporal resolutions, thus affecting the model efficiency and utility. This work parallelizes the MGB hydrological model on either CPU with OpenMP or GPU with OpenACC, respectively, aiming at the improvement in performance by employing computing resources of an HPC system. An analysis of the sequential and parallel executions is presented together with the runtime, speedup, efficiency, and load balance achieved.

Referências

Fan, F. M. and Pontes, P. R. M. and Paiva, R. C. D. (2014) “Avaliação de um método de propagação de cheias em rios com aproximação inercial das equações de Saint-Venant”, RBRH – Revista Brasileira de Recursos Hídricos, v. 19, n. 4, pages 137-147.

Lamb, R. and Crossley, A. and Waller, S. (2009) “Fast 2D floodplain modeling using computer game technology”, Flood Risk Management: Research and Practice.

Mendes, C. L. (2016) “Cluster LAQUIBRIDO”, http://www.lac.inpe.br/~celso/LAQUIBRIDO.html.

Neal, J. C. and Fewtrell, T. J. and Trigg, M. (2009) “Parallelisation of storage cell flood model using OpenMP”, Environmental Modelling & Software, v. 24, pages 872-877.

Paiva, R. C. D. and Collischonn, W. and Tucci, C. E. M. (2011) “Large scale hydrologic and hydrodynamic modeling using limited data and a GIS based approach”, Journal of Hydrology, v. 406, pages 170-181.

Pau, J. C. and Sanders, B. F. (2006) “Performance of parallel implementations of an explicit finitevolume shallow-water model”, Journal of Computing in Civil Engineering, v. 20, n. 2, pages 99-110.

Sarates, A. S. (2015), Optimizing Two-dimensional Shallow Water Based Flood Hydrological Model with Stream Architectures, Master Thesis, Universidade Federal do Rio Grande do Sul.
Publicado
13/04/2018
FREITAS, Henrique R. A.; MENDES, Celso. Parallelization of a Large-Scale Watersheds Hydrological Model using CPU and GPU. In: ESCOLA REGIONAL DE ALTO DESEMPENHO DE SÃO PAULO (ERAD-SP), 9. , 2018, São José dos Campos. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2018 . p. 65-68. DOI: https://doi.org/10.5753/eradsp.2018.13604.