Authors:
Gregory A. Koenig and Laxmikant V. Kale
Parallel Programming Laboratory, Department of Computer Science, University of Illinois at Urbana-Champaign

Proceedings of 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2005), Denver Colorado USA, April 2005.

One of the attractive features of Grid computing is that resources in geographically distant places can be mobilized to meet computational needs as they arise. A particularly challenging issue is that of executing a single application across multiple machines that are separated by large distances. While certain classes of applications such as pipeline style or master-slave style applications may run well in Grid computing environments with little or no modification, tightly-coupled applications require significant work to achieve good performance.

In this paper, we demonstrate that message-driven objects, implemented in the Charm++ and Adaptive MPI systems, can be used to mask the effects of latency in Grid computing environments without requiring modification of application software. We examine a simple five-point stencil decomposition application as well as a more complex molecular dynamics application running in an environment in which arbitrary artificial latencies can be induced between pairs of nodes. Performance of the applications running under artificial latencies are compared to the performance of the applications running across TeraGrid nodes located at the National Center for Supercomputing Applications and Argonne National Laboratory.

[postscript] [PDF] [bibtex] [text reference]