Grid and Cluster Matrix Computation with Persistent Storage and Out-of-Core Programming
Lamine M. Aouad, Serge G. Petiton, and Mitsuhisa Sato
IEEE International Conference on Cluster Computing (Cluster 2005)
Boston, Massachusetts, USA, September 27 - 30, 2005
Abstract
In this paper we present a performance evaluation of a large-scale numerical application on a cluster and a global Grid/Cluster platform. We use computational resources distributed on two geographic sites: in Japan (Tsukuba university) and France (university of Lille I). We compare a classical MPI version with global Grid/Cluster versions and present and test some techniques for numerical applications on a Grid/Cluster infrastructure based on out-of-core programming and an efficient data placement. We discuss the performances of a block-based Gauss-Jordan method for large matrix inversion. As experimental Grid middleware we use the XtremWeb system to manage non-dedicated distributed resources.