Application of Graphics Processing Units for self-consistent modelling of shallow water dynamics and sediment transport

TL;DR

This paper presents a GPU-accelerated numerical algorithm for simulating shallow water and sediment transport dynamics, achieving significant speedups on supercomputing systems using advanced parallel computing technologies.

Contribution

It introduces a novel parallel CSPH-TVD method leveraging OpenMP-CUDA and GPUDirect for efficient large-scale simulations of water and sediment flow.

Findings

Max speedup of 1800 on Nvidia Tesla GPUs.

Calculation time reduced by 95 times on V100 compared to C2070.

High efficiency demonstrated on supercomputing configurations.

Abstract

In this paper, we describe a numerical algorithm for the self-consistent simulations of surface water and sediment dynamics. The method is based on the original Lagrangian-Eulerian CSPH-TVD approach for solving the Saint-Venant and Exner equations, taking into account the physical factors essential for the understanding of the shallow water and surface soil layer motions, including complex terrain structure and its evolution due to sediment transport. Additional Exner equation for sediment transport has been used for the numerical CSPH-TVD scheme stability criteria definition. By using OpenMP-CUDA and GPUDirect technologies for hybrid computing systems (supercomputers) with several graphic coprocessors (GPUs) interacting with each other via the PCI-E / NVLINK interface we also develop a parallel numerical algorithm for the CSPH-TVD method. The developed parallel version of the algorithm demonstrates high efficiency for various configurations of Nvidia Tesla CPU + GPU computing systems. In particular, maximal speed up is 1800 for a system with four C2070 GPUs compare to the serial version for the CPU. The calculation time on the GPU V100~(Volta architecture) is reduced by 95 times compared to the GPU C2070~(Fermi architecture).