Using graphics processors to accelerate the computation of the matrix inverse
Centro de Calculo – Instituto de Computacion, Universidad de la Republica, 11.300 Montevideo, Uruguay
The Journal of Supercomputing (14 April 2011), pp. 1-9
@article{ezzattiusing,
title={Using graphics processors to accelerate the computation of the matrix inverse},
author={Ezzatti, P. and Quintana-Ort{‘i}, ES and Rem{‘o}n, A.},
journal={The Journal of Supercomputing},
pages={1–9},
issn={0920-8542},
publisher={Springer}
}
We study the use of massively parallel architectures for computing a matrix inverse. Two different algorithms are reviewed, the traditional approach based on Gaussian elimination and the Gauss-Jordan elimination alternative, and several high performance implementations are presented and evaluated. The target architecture is a current general-purpose multicore processor (CPU) connected to a graphics processor (GPU). Numerical experiments show the efficiency attained by the proposed implementations and how the computation of large-scale inverses, which only a few years ago would have required a distributed-memory cluster, take only a few minutes on a hybrid architecture formed by a multicore CPU and a GPU.
April 21, 2011 by hgpu
