Parallelization of a 3-Dimensional Hydrodynamics Model Using a Hybrid Method with MPI and OpenMP

Process-based numerical models developed to perform hydraulic/hydrologic/water quality analysis of watersheds and rivers have become highly sophisticated, with a corresponding increase in their computation time. However, for incidents such as water pollution, rapid analysis and decision-making are critical. This paper proposes an optimized parallelization scheme to reduce the computation time of the Environmental Fluid Dynamics Code-National Institute of Environmental Research (EFDC-NIER) model, which has been continuously developed for water pollution or algal bloom prediction in rivers. An existing source code and a parallel computational code with open multi-processing (OpenMP) and a message passing interface (MPI) were optimized, and their computation times compared. Subsequently, the simulation results for the existing EFDC model and the model with the parallel computation code were compared. Furthermore, the optimal parallel combination for hybrid parallel computation was evaluated by comparing the simulation time based on the number of cores and threads. When code parallelization was applied, the performance improved by a factor of approximately five compared to the existing source code. Thus, if the parallel computational source code applied in this study is used, urgent decision-making will be easier for events such as water pollution incidents.

[1]  B. Stump,et al.  Spatiotemporal parallelization of an analytical heat conduction model for additive manufacturing via a hybrid OpenMP + MPI approach , 2020 .

[2]  Torsten Hoefler,et al.  Using Advanced MPI: Modern Features of the Message-Passing Interface , 2014 .

[3]  Emanuele Ragnoli,et al.  Parallelisation study of a three-dimensional environmental flow model , 2014, Comput. Geosci..

[4]  Raghavan Srinivasan,et al.  A parallelization framework for calibration of hydrological models , 2012, Environ. Model. Softw..

[5]  G. Amdhal,et al.  Validity of the single processor approach to achieving large scale computing capabilities , 1967, AFIPS '67 (Spring).

[6]  Timothy Fewtrell,et al.  Parallelisation of storage cell flood models using OpenMP , 2009, Environ. Model. Softw..

[7]  Taegu Kang,et al.  Predicting Cyanobacterial Blooms Using Hyperspectral Images in a Regulated River , 2021, Sensors.

[8]  Adnan Eghtesad,et al.  OpenMP and MPI implementations of an elasto-viscoplastic fast Fourier transform-based micromechanical solver for fast crystal plasticity modeling , 2018, Adv. Eng. Softw..

[9]  Gabor Toth,et al.  Efficient OpenMP parallelization to a complex MPI parallel magnetohydrodynamics code , 2020, J. Parallel Distributed Comput..

[10]  Diego Avesani,et al.  A dual-layer MPI continuous large-scale hydrological model including Human Systems , 2021, Environ. Model. Softw..

[11]  A-Xing Zhu,et al.  A layered approach to parallel computing for spatially distributed hydrological modeling , 2014, Environ. Model. Softw..

[12]  Xinghua Chang,et al.  An efficient large-scale mesh deformation method based on MPI/OpenMP hybrid parallel radial basis function interpolation , 2020 .

[13]  Taegu Kang,et al.  Predicting Cyanobacterial Harmful Algal Blooms (CyanoHABs) in a Regulated River Using a Revised EFDC Model , 2021, Water.

[14]  Barbara Chapman,et al.  Using OpenMP - portable shared memory parallel programming , 2007, Scientific and engineering computation.

[15]  Stephen Pond,et al.  A Numerical Model of the Circulation in Knight Inlet, British Columbia, Canada , 1995 .

[16]  A. Bomers,et al.  The influence of grid shape and grid size on hydraulic river modelling performance , 2019, Environmental Fluid Mechanics.

[17]  Paul D. Bates,et al.  A comparison of three parallelisation methods for 2D flood inundation models , 2010, Environ. Model. Softw..

[18]  Thorsten Stoesser,et al.  Scalability of an Eulerian-Lagrangian large-eddy simulation solver with hybrid MPI/OpenMP parallelisation , 2019, Computers & Fluids.

[19]  Young Do Kim,et al.  Effect of Abrupt Topographical Characteristic Change on Water Quality in a River , 2019, KSCE Journal of Civil Engineering.

[20]  Seungsoo Lee,et al.  Hyper-resolution 1D-2D urban flood modelling using LiDAR data and hybrid parallelization , 2018, Environ. Model. Softw..

[21]  Anthony Skjellum,et al.  A High-Performance, Portable Implementation of the MPI Message Passing Interface Standard , 1996, Parallel Comput..

[22]  W. Winston,et al.  Geochemical variations during flash flooding, Meramec River basin, May 2000 , 2002 .

[23]  Wojciech Kwedlo,et al.  A Hybrid MPI/OpenMP Parallelization of $K$ -Means Algorithms Accelerated Using the Triangle Inequality , 2019, IEEE Access.

[24]  Qiang Zhao,et al.  A hybrid MPI/OpenMP parallel computing model for spherical discontinuous deformation analysis , 2019, Computers and Geotechnics.

[25]  Jannis Klinkenberg,et al.  CHAMELEON: Reactive Load Balancing for Hybrid MPI+OpenMP Task-Parallel Applications , 2020, J. Parallel Distributed Comput..

[26]  John M. Hamrick,et al.  A Three-Dimensional Environmental Fluid Dynamics Computer Code : Theoretical and computational aspects , 1992 .

[27]  Alistair Adcroft,et al.  Rescaled height coordinates for accurate representation of free-surface flows in ocean circulation models , 2004 .