Current advances in many-core technologies demand simulation algorithms suited for the corresponding architectures while with regard to the respective increase of computational power, real-time and interactive simulations become possible and desirable. We present an OpenCL implementation of a Lattice-Boltzmann-based free-surface solver for GPU architectures. The massively parallel execution especially requires special techniques to keep the interface region consistent, which is here addressed by a novel multipass method. We further compare different memory layouts according to their performance for both a basic driven cavity implementation and the free-surface method, pointing out the capabilities of our implementation in real-time and interactive scenarios, and shortly present visualizations of the flow, obtained in real-time.

@inproceedings{FLBSOMASNZ11,
	author	 = {Martin Schreiber and Philipp Neumann and Stefan Zimmer and Hans-Joachim Bungartz},
	title	 = {{Free-Surface Lattice Boltzmann Simulation on Many-Core Architectures}},
	year	 = {2011},
	booktitle	 = {{2011 International Conference on Computational Science}},
	publisher	 = {Elsevier},
	series	 = {Procedia Computer Science},
	number	 = {4},
	pages	 = {984--993},
	conference	 = {ICCS 2011},
	location	 = {Singapore},
	doi	 = {http://dx.doi.org/10.1016/j.procs.2011.04.104},
	abstract	 = {Current advances in many-core technologies demand simulation algorithms suited for the corresponding architectures while with regard to the respective increase of computational power, real-time and interactive simulations become possible and desirable. We present an OpenCL implementation of a Lattice-Boltzmann-based free-surface solver for GPU architectures. The massively parallel execution especially requires special techniques to keep the interface region consistent, which is here addressed by a novel multipass method. We further compare different memory layouts according to their performance for both a basic driven cavity implementation and the free-surface method, pointing out the capabilities of our implementation in real-time and interactive scenarios, and shortly present visualizations of the flow, obtained in real-time.},
}