Supporting efficient execution of MPI applications across multiple sites

Abstract

One of the main goals of the CrossGrid Project [1] is to provide explicit support to parallel and interactive compute- and dataintensive applications. The CrossBroker job manager provides services as part of the CrossGrid middleware and allows execution of parallel MPI applications on Grid resources in a transparent and automatic way. This document describes the design and implementation of the key components responsible for an efficient and reliable execution of MPI jobs splitted over multiple Grid sites, executed either in an on-line or batch manner. We also provide details on the overheads introduced by our system, as well as an experimental study showing that our system is well-suited for embarrassingly parallel applications. © Springer-Verlag Berlin Heidelberg 2006.