Level 7, Gehrmann Laboratories

The coordinated use of geographically distributed computers, or metacomputing, can in principle provide more accessible and cost-eective supercomputing than do conventional high-performance systems. However, we lack evidence that metacom-puting systems can be made easily usable or that large numbers of applications are able to exploit metacomputing resources. In this article, we present work that ad-dresses both these concerns. The basis for this work is a system called Nimrod that provides a desktop problem-solving environment for parametric experiments. We describe how Nimrod has been extended to support the scheduling of computational resources located in a wide-area environment and report on an experiment in which Nimrod was used to schedule a large parametric study across the Australian Inter-net. The experiment provided both new scientic results and insights into Nimrod capabilities. We relate the results of this experiment to lessons learned from the I-WAY distributed computing experiment and draw conclusions as to how Nimrod and I-WAY{like computing environments should be developed to support desktop metacomputing.