A Smart GPU Implementation of an Elliptic Kernel for an Ocean Global Circulation Model
Centro Euro-Mediterraneo sui Cambiamenti Climatici, Bologna, Viale Aldo Moro 44, Italy
Applied Mathematical Sciences, Vol. 7, no. 61-64, 2013
@article{farina2013smart,
title={A Smart GPU Implementation of an Elliptic Kernel for an Ocean Global Circulation Model},
author={Farina, R and Cuomo, S and De Michele, P and Piccialli, F},
journal={Applied Mathematical Sciences},
volume={7},
number={61},
pages={3007–3021},
year={2013}
}
In this paper, the preconditioning technique of an elliptic Laplace problem in a global circulation ocean model is analyzed. We suggest an inverse preconditioning technique in order to efficiently compute the numerical solution of the elliptic kernel. Moreover, we show how the convergence rate and the performance of the solver are strictly linked to the discretized grid resolution and to the Laplace coefficients of the oceanic model. Finally, we present an easy-to-implement version of the solver on the Graphics Processing Units (GPUs).
July 8, 2013 by hgpu
