NAS experiences with a prototype cluster of workstations
K. Castagnera, D. Y. Cheng, R. Fatoohi, E B Hook, Brad A. Kramer, Cheryl A. Manning, J. Musch, C. Niggley, William C. Saphir, Dennis Sheppard, Merritt H. Smith, I. E. Stockdale, S. Welch, Rosemary H. Williams, David Yip · 1994
This paper discusses the year-long activity at NAS to implement a large, loose cluster of worksta-tions from the existing Silicon Graphics, Inc. (SGI) pool of systems. Issues related to establishing a loosely coupled cluster of workstations are pre-sented. Included are steps needed to resolve system management issues intended to provided reason-able cycle recovery from these systems without dis-rupting the primary system users. Performance evaluation tests were run based on the NAS Paral-lel Benchmarks (NPB) and other codes, including OVERFLOW-PVM, a full-fledged Computational Fluid Dynamics (CFD) application. This paper summarizes the activities related to the prototype cluster and identifies areas that need improvement, development, and research in order to make work-station clusters a viable computing environment for solving aeroscience problems.