High-performance distributed computing: The I-Way experiment and beyond

Abstract

Recent developments in networking are enabling innovative applications that integrate geographically distributed high-performance computing, database, display, and networking resources. However, there is as yet little understanding of the higher-level services needed to support these applications, or of the techniques required to implement these services in a scalable, secure manner. In this brief paper, I describe the I-WAY networking experiment, a large-scale wide-area computing testbed that has been used to investigate these issues. I also introduce the Globus project, a multi-institutional effort that is developing key technologies for I-WAY-like systems, including mechanisms for resource location, scheduling, authentication, and automatic configuration of high-performance distributed computations.