A CUBLAS-CUDA Implementation of PCG Method of an Ocean Circulation Model
Abstract
A numerical model of an ocean global circulation is presented. It consists of the discretization of Laplace's problem by means of finite differences scheme of second order that gives a linear system solved by Preconditioned Conjugate Gradient Method (PCG). In this work, we observe that the performance and the accuracy of PCG solver depend on the grid resolution and the ratio of Laplace's coefficients. Moreover, a case study of an implementation of PCG solver with diagonal preconditioner on multi-core GPU architecture based on CUBLAS library is proposed.
- Publication:
-
Numerical Analysis and Applied Mathematics ICNAAM 2011: International Conference on Numerical Analysis and Applied Mathematics
- Pub Date:
- September 2011
- DOI:
- 10.1063/1.3636988
- Bibcode:
- 2011AIPC.1389.1923F
- Keywords:
-
- ocean waves;
- finite difference methods;
- matrix algebra;
- computers;
- 92.10.ab;
- 02.70.Bf;
- 02.10.Yn;
- 07.05.Bx;
- General circulation;
- Finite-difference methods;
- Matrix theory;
- Computer systems: hardware operating systems computer languages and utilities