Nisha Agrawal
ABSTRACT
The performance analysis of ANUGA, a Python-based finite volume solver on the unstructured grid for shallow water model in two dimensions, on recent Intel and AMD processor-based HPC clusters, form the focus of the present study. The analysis uses three datasets with different resolutions of the underlying triangular mesh for discretizing the region of interest. The computational workload depends on the resolution of the grid, which impacts the computation time required for the simulation of the flow. The factors influencing the parallel performance: workload distribution across different processes, and the bulk of the data exchange (the communication overhead), are studied systematically. This paper is an account of the preliminary study to understand the impact of the memory hierarchy (due to the relative sizes of cache) available on different architecture on the performance of this application.
- M. Arafa, B. Fahim, S. Kottapalli, A. Kumar, L. P. Looi, S. Mandava, A. Rudoff, I. M. Steiner, B. Valentine, G. Vedaraman, and S. Vora. 2019. Cascade Lake: Next generation Intel Xeon scalable processor. IEEE Micro 39, 2 (2019), 29–36. https://doi.org/10.1109/MM.2019.2899330Google Scholar
Cross Ref
- Lorenzo Begnudelli and Brett F. Sanders. 2006. Unstructured grid finite-volume algorithm for shallow-water flow and scalar transport with wetting and drying. Journal of Hydraulic Engineering 132 (2006), 371–384. https://doi.org/10.1061/ASCE0733-94292006132:4371Google ScholarCross Ref
- M. J. Castro, J. A. García-Rodríguez, J. M. González-Vida, and C. Parés. 2006. A parallel 2D finite volume scheme for solving systems of balance laws with nonconservative products: Application to shallow flows. Computer Methods in Applied Mechanics and Engineering 195 (2006), 2788–2815. https://doi.org/10.1016/j.cma.2005.07.007Google ScholarCross Ref
- Phillip Colella. 2004. Defining software requirements for scientific computing. DARPA HPCS Presentation.Google Scholar
- Intel Corporation. 2021. Intel Trace Analyzer and Collector: MPI Profiling for Cluster Applications. https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/trace-analyzer.htmlGoogle Scholar
- G. Davies and S. Roberts. 2015. Open source flood simulation with a 2D discontinuous-elevation hydrodynamic model. In Proceedings of International Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand, MODSIM 2015, T. Weber, M. J. McPhee, and R. S. Anderssen(Eds.). 2130–2136. https://www.mssanz.org.au/modsim2015/Google Scholar
- J. Doweck, W. Kao, A. K. Lu, J. Mandelblat, A. Rahatekar, L. Rappoport, E. Rotem, A. Yasin, and A. Yoaz. 2017. Inside 6th-Generation Intel Core: New microarchitecture code-named Skylake. IEEE Micro 37, 2 (2017), 52–62. https://doi.org/10.1109/MM.2017.38Google ScholarDigital Library
- Domenico Ferraro, Pierfranco Costabile, Carmelina Costanzo, Gabriella Petaccia, and Francesco Macchione. 2020. A spectral analysis approach for the a priori generation of computational grids in the 2-D hydrodynamic-based runoff simulations at a basin scale. Journal of Hydrology 582(2020), 124508. https://doi.org/10.1016/j.jhydrol.2019.124508Google ScholarCross Ref
- Bobby Minola Ginting, Punit Kumar Bhola, Christoph Ertl, Ralf-Peter Mundani, Markus Disse, and Ernst Rank. 2020. Hybrid-parallel simulations and visualisations of real flood and tsunami events using unstructured meshes on high-performance cluster systems. In Advances in Hydroinformatics, Models for Extreme Situations and Crisis Management, SimHydro 2019(Springer Water book series), P. Gourbesville and G. Caignaert (Eds.). 867–888. https://10.1007/978-981-15-5436-0_67Google Scholar
- Bobby Minola Ginting and Ralf-Peter Mundani. 2019. Comparison of shallow water solvers: Applications for dam-break and tsunami cases with reordering strategy for efficient vectorization on modern hardware. Water 11(2019), 639 (1–32). https://doi.org/10.3390/w11040639Google Scholar
- Carlos H. González, Basilio B. Fraguela, Diego Andrade, José A. García, and Manuel J. Castro. 2013. Numerical simulation of pollutant transport in a shallow-water system on the Cell heterogeneous processor. Journal of Supercomputing 65 (2013), 1089–1103. https://doi.org/10.1007/s11227-012-0862-yGoogle ScholarDigital Library
- Ioan Hadade, Feng Wang, Mauro Carnevale, and Luca di Mare. 2019. Some useful optimisations for unstructured computational fluid dynamics codes on multicore and manycore architectures. Computer Physics Communications 235 (2019), 305–323. https://doi.org/10.1016/j.cpc.2018.07.001Google ScholarCross Ref
- George Karypis and Vipin Kumar. 2013. METIS - Serial Graph Partitioning and Fill-reducing Matrix Ordering. http://glaros.dtc.umn.edu/gkhome/metis/metis/overviewGoogle Scholar
- D. K. Kaushik and D. E. Keyes. 1999. Efficient parallelization of an unstructured grid solver: A memory-centric approach. Technical Report. Istambul Technical University.Google Scholar
- M. K. Kumashikar, S. G. Bendi, S. Nimmagadda, A. J. Deka, and A. Agarwal. 2017. 14nm Broadwell Xeon® processor family: Design methodologies and optimizations. In 2017 IEEE Asian Solid-State Circuits Conference (A-SSCC). 17–20. https://doi.org/10.1109/ASSCC.2017.8240205Google ScholarCross Ref
- Asier Lacasta, Mario Morales-Hernández, Javier Murillo, and Pilar García-Navarro. 2015. GPU implementation of the 2D shallow water equations for the simulation of rainfall/runoff events. Environmental Earth Sciences 74 (2015), 7295–7305. https://doi.org/10.1007/s12665-015-4215-zGoogle ScholarCross Ref
- Qiuhua Liang. 2010. Flood simulation using a well-balanced shallow flow model. Journal of Hydraulic Engineering 136 (2010), 669–675. https://doi.org/(ASCE)HY.1943-7900.0000219Google ScholarCross Ref
- Zhanyan Liu, Hongbin Zhang, and Qiuhua Liang. 2019. A coupled hydrological and hydrodynamic model for flood simulation. Hydrology Research 50(2019), 589–606. https://doi.org/10.2166/nh.2018.090Google ScholarCross Ref
- Jacobo Lobeiras, Moisés Vinās, Margarita Amor, Basilio B. Fraguela, Manuel Arenaz, J. A. García-Rodríguez, and Manuel J. Castro. 2012. Parallelization of shallow water simulations on current multi-threaded systems. International Journal of High Performance Computing Applications 27 (2012), 493–512. https://doi.org/10.1177/1094342012464800Google ScholarDigital Library
- Sudi Mungkasi and J. B. Budi Darmawan. 2015. Fast and efficient parallel computations using a cluster of workstations to simulate flood flows. In Intelligence in the Era of Big Data: Proceedings of International Conference on Soft Computing, Intelligence Systems, and Information Technology, ICSIIT 2015(Communications in Computer and Information Science, Vol. 516), R. Intan, Chi-Hung Chi, H. N. Palit, and L. W. Santoso (Eds.). 469–477. https://link.springer.com/book/10.1007/978-3-662-46742-8Google Scholar
- Sudi Mungkasi and Stephen Gwyn Roberts. 2011. A finite volume method for shallow water flows on triangular computational grids. In Proceedings of IEEE International Conference on Advanced Computer Science and Information Systems, ICACSIS 2011. 79–84. https://ieeexplore.ieee.org/xpl/conhome/6132213/proceedingGoogle Scholar
- Ole Møller Nielsen, Stephen G. Roberts, D. Gray, Andrew McPherson, and A. Hitchman. 2005. Hydrodynamic modelling of coastal inundation. In Proceedings of International Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand, MODSIM 2005, A. Zerger and R. M. Argent (Eds.). 518–523. https://www.mssanz.org.au/modsim05/index.htmGoogle Scholar
- G. Petaccia, F. Leporati, and E. Torti. 2016. OpenMP and CUDA simulations of Sella Zerbino Dam break on unstructured grids. Computational Geosciences 20 (2016), 1123–1132. https://doi.org/10.1007/s10596-016-9580-5Google ScholarCross Ref
- Stephen Gwyn Roberts and Ole Møller Nielsen. 2007. Parallelisation of a finite volume method for hydrodynamic inundation modelling. In Proceedings of the 13th Biennial Computational Techniques and Applications Conference, CTAC-2006(ANZIAM Journal, Vol. 48), Wayne Readand A. J. Roberts (Eds.). C558–C572. https://journal.austms.org.au/ojs/index.php/ANZIAMJ/article/view/153Google ScholarCross Ref
- Stephen G Roberts, Yusuke Oishi, and Michael Li. 2013. High resolution tsunami inundation simulations. In Proceedings of International Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand, MODSIM 2013, J. Piantadosi, R. S. Anderssen, and J. Boland (Eds.). 310–316. https://www.mssanz.org.au/modsim2013/Google Scholar
- Jonathan Richard Shewchuk. 2005. A Two-Dimensional Quality Mesh Generator and Delaunay Triangulator. https://www.cs.cmu.edu/~quake/triangle.htmlGoogle Scholar
- Francisco J. M. Simões. 2011. Finite volume model for two-dimensional shallow environmental flow. Journal of Hydraulic Engineering 137 (2011), 173–182. https://doi.org/10.1061/(ASCE)HY.1943-7900.0000292Google ScholarCross Ref
- D. Suggs, M. Subramony, and D. Bouvier. 2020. The AMD “Zen 2” processor. IEEE Micro 40, 2 (2020), 45–52. https://doi.org/10.1109/MM.2020.2974217Google ScholarCross Ref
- András Attila Sulyok, Gábor Dániel Balogh, István Zoltan Reguly, and Gihan R. Mudalige. 2018. Improving locality of unstructured mesh algorithms on GPUs. arXiv:1802.03749 [cs.MS].Google Scholar
- Zhe Weng and Peter E. Strazdins. 2014. Acceleration of a Python-based tsunami modelling application via CUDA and OpenHMPP. In Proceedings of International Symposium on Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014. 1275 –1284. https://ieeexplore.ieee.org/xpl/conhome/6967893/proceedingGoogle ScholarDigital Library
- Xinya Ying, Jeff Jorgeson, and Sam S. Y. Wang. 2009. Modeling dam-break flows using finite volume method on unstructured grid. Engineering Applications of Computational Fluid Mechanics 3 (2009), 184–194. https://doi.org/10.1080/19942060.2009.11015264Google ScholarCross Ref
Recommendations
Hardware Counter-based Performance Analysis of ANUGA Flood Simulator
IC3-2023: Proceedings of the 2023 Fifteenth International Conference on Contemporary ComputingANUGA is a Python-based finite volume solver on the unstructured grid for shallow water model in two dimensions for flood modelling. This paper is an account of the hardware counter-based performance study to understand the impact of the memory ...
Vectorizing Unstructured Mesh Computations for Many-core Architectures
PMAM'14: Proceedings of Programming Models and Applications on Multicores and ManycoresAchieving optimal performance on the latest multi-core and many-core architectures depends more and more on making efficient use of the hardware's vector processing capabilities. While auto-vectorizing compilers do not require the use of vector ...
Vectorizing Unstructured Mesh Computations for Many-core Architectures
PMAM'14: Proceedings of Programming Models and Applications on Multicores and ManycoresAchieving optimal performance on the latest multi-core and many-core architectures depends more and more on making efficient use of the hardware's vector processing capabilities. While auto-vectorizing compilers do not require the use of vector ...
Comments