Title :
Grid and Cluster Matrix Computation with Persistent Storage and Out-of-core Programming
Author :
Aouad, Lamine M. ; Petiton, Serge G. ; Sato, Mitsuhisa
Author_Institution :
LIFL, Univ. of Lille I
Abstract :
In this paper we present a performance evaluation of a large-scale numerical application on a cluster and a global grid/cluster platform. The computational resources are a cluster of clusters (34 nodes, 84 processors) and a local area network grid (128 nodes), distributed on two geographic sites: Tsukuba University (Japan) and University of Lille I (France). We compare a classical MPI (message passing interface) version with global grid/cluster versions. We also 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
Keywords :
grid computing; matrix inversion; matrix multiplication; message passing; middleware; workstation clusters; XtremWeb system; block-based Gauss-Jordan method; cluster of clusters; global computing; grid computing; grid middleware; grid/cluster infrastructure; large-scale numerical application; linear algebra; local area network grid; matrix computation; matrix inversion; message passing interface; nondedicated distributed resources; out-of-core programming; performance evaluation; persistent storage; Computer networks; Distributed computing; Gaussian processes; Grid computing; Large-scale systems; Local area networks; Message passing; Middleware; Resource management; Testing; Grid and global computing; Linear algebra; cluster of clusters; out-of-core programming; persistent storage;
Conference_Titel :
Cluster Computing, 2005. IEEE International
Conference_Location :
Burlington, MA
Print_ISBN :
0-7803-9486-0
Electronic_ISBN :
1552-5244
DOI :
10.1109/CLUSTR.2005.347071
