Domain decomposition and locality optimization for large-scale lattice Boltzmann simulations
From MaRDI portal
Publication:2446641
DOI10.1016/J.COMPFLUID.2012.02.007zbMATH Open1426.76621arXiv1111.1129OpenAlexW1983574265MaRDI QIDQ2446641FDOQ2446641
Thomas Zeiser, Markus Wittmann, Georg Hager, Gerhard Wellein
Publication date: 17 April 2014
Published in: Computers and Fluids (Search for Journal in Brave)
Abstract: We present a simple, parallel and distributed algorithm for setting up and partitioning a sparse representation of a regular discretized simulation domain. This method is scalable for a large number of processes even for complex geometries and ensures load balance between the domains, reasonable communication interfaces, and good data locality within the domain. Applying this scheme to a list-based lattice Boltzmann flow solver can achieve similar or even higher flow solver performance than widely used standard graph partition based tools such as METIS and PT-SCOTCH.
Full work available at URL: https://arxiv.org/abs/1111.1129
Cites Work
- A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
- The lattice Boltzmann equation. For fluid dynamics and beyond
- On the single processor performance of simple lattice Boltzmann kernels
- A high-performance lattice Boltzmann implementation to model flow in porous media
- On improving the performance of large parallel lattice Boltzmann flow simulations in heterogeneous porous media
- A parallelisation concept for a multi-physics lattice Boltzmann prototype based on hierarchical grids
Cited In (3)
- Lattice Boltzmann method-based efficient GPU simulator for vapor transport in the boundary layer over a moist soil: development and experimental validation
- A mesh partitioning algorithm for preserving spatial locality in arbitrary geometries
- Parametrization of the cumulant lattice Boltzmann method for fourth order accurate diffusion. I: Derivation and validation
Uses Software
Recommendations
- Title not available (Why is that?) π π
- Title not available (Why is that?) π π
- Advances in multi-domain lattice Boltzmann grid refinement π π
- Lattice Boltzmann Methods for Multiphase Flow Simulations across Scales π π
- Towards a hybrid parallelization of lattice Boltzmann methods π π
- Parallelization of lattice Boltzmann method for incompressible flow computations π π
- Massively parallel algorithms for the lattice Boltzmann method on nonuniform grids π π
- A scalable domain decomposition method and applications in simulation and optimization of fluids π π
- A distributed lattice Boltzmann method π π
This page was built for publication: Domain decomposition and locality optimization for large-scale lattice Boltzmann simulations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2446641)