PARALLEL COMPUTING IN NETWORKS OF WORKSTATIONS WITH PARALEX

Modern distributed systems consisting of powerful workstations and hig h-speed interconnection networks are an economical alternative to spec ial-purpose supercomputers. The technical issues that need to be addre ssed in exploiting the parallelism inherent in a distributed system in clude heterogeneity, high-latency communication, fault tolerance and d ynamic load balancing. Current software systems for parallel programmi ng provide little or no automatic support towards these issues and req uire users to be experts in fault-tolerant distributed computing. The Paralex system is aimed at exploring the extent to which the parallel application programmer can be liberated from the complexities of distr ibuted systems. Paralex is a complete programming environment and make s extensive use of graphics to define, edit, execute, and debug parall el scientific applications. All of the necessary code for distributing the computation across a network and replicating it to achieve fault tolerance and dynamic load balancing is automatically generated by the system. In this paper we give an overview of Paralex and present our experiences with a prototype implementation.