Scalable Lattice Boltzmann Solvers for CUDA GPU Clusters
EDF R&D, Departement EnerBAT, 77818 Moret-sur-Loing Cedex, France
hal-00931058, (11 June 2014)
@article{obrecht:hal-00931058,
hal_id={hal-00931058},
url={http://hal.archives-ouvertes.fr/hal-00931058},
title={Scalable Lattice Boltzmann Solvers for CUDA GPU Clusters},
author={Obrecht, Christian and Kuznik, Fr{‘e}d{‘e}ric and Tourancheau, Bernard and Roux, Jean-Jacques},
keywords={GPU clusters; CUDA; Lattice Boltzmann method},
language={Anglais},
affiliation={Centre de Thermique de Lyon – CETHIL , Laboratoire d’Informatique de Grenoble – LIG},
pages={259-270},
journal={Parallel Computing},
volume={39},
number={6-7},
audience={internationale},
doi={10.1016/j.parco.2013.04.001},
year={2013},
month={Jun},
pdf={http://hal.archives-ouvertes.fr/hal-00931058/PDF/ACL35.pdf}
}
The lattice Boltzmann method (LBM) is an innovative and promising approach in computational fluid dynamics. From an algorithmic standpoint it reduces to a regular data parallel procedure and is therefore well-suited to high performance computations. Numerous works report efficient implementations of the LBM for the GPU, but very few mention multi-GPU versions and even fewer GPU cluster implementations. Yet, to be of practical interest, GPU LBM solvers need to be able to perform large scale simulations. In the present contribution, we describe an efficient LBM implementation for CUDA GPU clusters. Our solver consists of a set of MPI communication routines and a CUDA kernel specifically designed to handle three-dimensional partitioning of the computation domain. Performance measurement were carried out on a small cluster. We show that the results are satisfying, both in terms of data throughput and parallelisation efficiency.
June 15, 2014 by hgpu
