@Article{FreitasMendIlic:2022:PeOpMG,
               author = "Freitas, Henrique Renn{\'o} de Azeredo and Mendes, Celso Luiz and 
                         Ilic, Aleksandar",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {Universidade de 
                         Lisboa}",
                title = "Performance optimization of the MGB hydrological model for 
                         multi-core and GPU architectures",
              journal = "Environmental Modelling and Software",
                 year = "2022",
               volume = "148",
                pages = "e105271",
                month = "Feb.",
             keywords = "High performance computing, Hydrology models, Parallel processing, 
                         Parameterization, Roofline model, Vectorization.",
             abstract = "Large-scale hydrological models simulate watershed processes with 
                         applications in water resources, climate change, land use, and 
                         forecast systems. The quality of the simulations mainly depends on 
                         calibrating optimal sets of watershed parameters, a time-consuming 
                         task that highly demands computational resources from repeated 
                         simulations. This work aims at performance optimizations on the 
                         MGB (Modelo de Grandes Bacias) hydrological model and the MOCOM-UA 
                         (Multi-Objective Complex Evolution) calibration method for two 
                         watersheds. The optimizations target state-of-the-art CPU/GPU 
                         systems, exploiting techniques that include AVX-512 vectorization, 
                         and multi-core (CPU) and many-core (GPU) parallelisms. Significant 
                         speedups of up to 20 × (CPU) were achieved for calibration, while 
                         the scalability analysis indicated 24 × (CPU) and 65 × (GPU) for 
                         simulations with larger problem sizes. The roofline analysis 
                         confirmed more effective use of the hardware resources, and the 
                         quantitative accuracy evaluation of the optimized implementations 
                         reached maximum relative errors of approximately 6% for discharges 
                         and objective functions.",
                  doi = "10.1016/j.envsoft.2021.105271",
                  url = "http://dx.doi.org/10.1016/j.envsoft.2021.105271",
                 issn = "1364-8152",
             language = "en",
           targetfile = "freitas_performance.pdf",
        urlaccessdate = "30 abr. 2024"
}