Asynchronous transfer mode and other network technologies for wide-area and high-performance cluster computing

We review fast networking technologies for both wide-area and high performa nce cluster computer systems. We describe our experiences in constructing a synchronous transfer mode (ATM)-based local- and wide-area clusters and the tools and technologies this experience led us to develop. We discuss our e xperiences using Internet Protocol on such systems as well as native ATM pr otocols and the problems facing wide-area integration of cluster systems. W e are presently constructing Beowulf-class computer clusters using a mix of Fast Ethernet and Gigabit Ethernet technology and we anticipate how such s ystems will integrate into a new local-area Gigabit Ethernet network and wh at technologies will be used for connecting shared HPC resources across wid e-areas. High latencies on wide-area cluster systems led us to develop a me tacomputing problem-solving environment known as distributed information sy stems control world (DISCWorld). We summarize our main developments in this project as well as the key features and research directions for software t o exploit computational services running on fast networked cluster systems.