Implementation of a Lattice Boltzmann kernel using the Compute Unified Device Architecture developed by nVIDIA

Authors:
Jonas Tölke
Affiliations:
Institute for computer based modeling in civil engineering, TU Braunschweig, Pockelstr. 3, 38106, Braunschweig, Germany
Venue:
Computing and Visualization in Science
Year:
2009

Citing 0
Cited 11

3.5-D Blocking Optimization for Stencil Computations on Modern CPUs and GPUs

Proceedings of the 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis
Free surface flow simulations on GPGPUs using the LBM

Computers & Mathematics with Applications
The TheLMA project: Multi-GPU implementation of the lattice Boltzmann method

International Journal of High Performance Computing Applications
Fast ARFTIS reconstruction algorithms using CUDA

HPCA'09 Proceedings of the Second international conference on High Performance Computing and Applications
Non-body-fitted Cartesian-mesh simulation of highly turbulent flows using multi-relaxation-time lattice Boltzmann method

Computers & Mathematics with Applications
A Multi-GPU implementation of a d2q37 lattice boltzmann code

PPAM'11 Proceedings of the 9th international conference on Parallel Processing and Applied Mathematics - Volume Part I
On enhanced non-linear free surface flow simulations with a hybrid LBM-VOF model

Computers & Mathematics with Applications
Lattice Boltzmann study of flow and mixing characteristics of two-dimensional confined impinging streams with uniform and non-uniform inlet jets

Computers & Mathematics with Applications
Cellular Automata and GPGPU: An Application to Lava Flow Modeling

International Journal of Grid and High Performance Computing
GPU implementation of a novel hybrid lattice Boltzmann method for non-isothermal flows

Proceedings of the 5th ACM COMPUTE Conference: Intelligent & scalable system technologies
Visualizing 3D/4D environmental data using many-core graphics processing units (GPUs) and multi-core central processing units (CPUs)

Computers & Geosciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article a very efficient implementation of a 2D-Lattice Boltzmann kernel using the Compute Unified Device Architecture (CUDA™) interface developed by nVIDIA® is presented. By exploiting the explicit parallelism exposed in the graphics hardware we obtain more than one order in performance gain compared to standard CPUs. A non-trivial example, the flow through a generic porous medium, shows the performance of the implementation.