Multi-GPU implementation of a time-explicit finite volume solver using CUDA and a CUDA-aware version of OpenMPI with application to shallow water flows
From MaRDI portal
Publication:6156956
DOI10.1016/J.CPC.2021.108190arXiv2010.14416OpenAlexW3206983896MaRDI QIDQ6156956FDOQ6156956
Authors: Vincent Delmas, Azzeddine Soulaimani 
Publication date: 19 June 2023
Published in: Computer Physics Communications (Search for Journal in Brave)
Abstract: This paper shows the development of a multi-GPU version of a time-explicit finite volume solver for the Shallow-Water Equations (SWE) on a multi-GPU architecture. MPI is combined with CUDA-Fortran in order to use as many GPUs as needed. The METIS library is leveraged to perform a domain decomposition on the 2D unstructured triangular meshes of interest. A CUDA-Aware OpenMPI version is adopted to speed up the messages between the MPI processes. A study of both speed-up and efficiency is conducted; first, for a classic dam-break flow in a canal, and then for two real domains with complex bathymetries: the Mille ^Iles river and the Montreal archipelago. In both cases, meshes with up to 13 million cells are used. Using 24 to 28 GPUs on these meshes leads to an efficiency of 80% and more. Finally, the multi-GPU version is compared to the pure MPI multi-CPU version, and it is concluded that in this particular case, about 100 CPU cores would be needed to achieve the same performance as one GPU.
Full work available at URL: https://arxiv.org/abs/2010.14416
Cites Work
- On Upstream Differencing and Godunov-Type Schemes for Hyperbolic Conservation Laws
- High resolution schemes for hyperbolic conservation laws
- Riemann Solvers and Numerical Methods for Fluid Dynamics
- A Fast and Stable Well-Balanced Scheme with Hydrostatic Reconstruction for Shallow Water Flows
- High-order finite-element seismic wave propagation modeling with MPI on a large GPU cluster
- A well-balanced positivity preserving ``second-order scheme for shallow water flows on unstructured meshes
- Shock-capturing methods for free-surface shallow flows
- Towards a generalised GPU/CPU shallow-flow modelling tool
- Efficient shallow water simulations on GPUs: implementation, visualization, verification, and validation
- Zero mass error using unsteady wetting–drying conditions in shallow flows over dry irregular topography
- Modeling of wetting-drying transitions in free surface flows over complex topographies
- A multi-GPU parallel algorithm in hypersonic flow computations
- Simulation and visualization of the Saint-Venant system using GPUs
- An edge-based stabilized finite element method for solving compressible flows: formulation and parallel implementation.
- Efficient GPU implementation of a two waves TVD-WAF method for the two-dimensional one layer shallow water system on structured meshes
- Title not available (Why is that?)
- A GPU accelerated adjoint-based optimizer for inverse modeling of the two-dimensional shallow water equations
- Non-hydrostatic pressure shallow flows: GPU implementation using finite volume and finite difference scheme
- Non-intrusive reduced-order modeling using uncertainty-aware deep neural networks and proper orthogonal decomposition: application to flood modeling
- Title not available (Why is that?)
Cited In (6)
- Hybrid OpenMP/AVX acceleration of a split HLL finite volume method for the shallow water and Euler equations
- Parallel high-order resolution of the shallow-water equations on real large-scale meshes with complex bathymetries
- Finite-Difference in Time-Domain Scalable Implementations on CUDA and OpenCL
- On the benefits of using GPUs to simulate shallow flows with finite volume schemes
- Fully parallel and pipelined sparse direct solver for large symmetric indefinite finite element problems
- Heterogeneous CPU-GPU parallelization for modeling supersonic reacting flows with detailed chemical kinetics
This page was built for publication: Multi-GPU implementation of a time-explicit finite volume solver using CUDA and a CUDA-aware version of OpenMPI with application to shallow water flows
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6156956)
