Findings of the joint NSF-NASA initiative in evaluation

Abstract

The Joint NSF-NASA Initiative in Evaluation (JNNIE: pronounced "genie") is an important collaborative study among nine NASA and NSF high performance computing research centers to evaluate the capabilities and deficiencies of major commercial scalable parallel computing SYstems. JNNIE investigators are developing results that permit meaningful comparisons to be made among parallel systems and programming methodologies by employing a common set of metrics, sharing high performance computing resources, and investigating a wide array of scientific applications. JNNIE findings go beyond benchmarking and reveal the factors contributing to observed behavior of parallel systems. The focus of this year and a half long effort is on performance, sources of performance degradation, scalability, and ease-of-use. Among the important results presented will be architecture features, and software technology that supports or impedes parallel computing effectiveness. The purpose of the panel session at Supercomputing '94 is to announce the findings of this study to the supercomputing community. The panel session will present the experimental methodology, measurements, analysis, and conclusions. Also, recommendations of near term directions in the evolution of commercial scalable parallel computing systems will be given. An extended period for discussion will be provided to permit questions and views to be expressed by attendees. The panelists for this session will be: Wayne Pfeiffer (Moderator), NSF San Diego Supercomputer Center; Richard S. Hirsh, NSF Headquarters; Steven Hotovy, Cornell Theory Center; Nick Nystrom, Pittsburgh Supercomputing Center; David H. Rudy, NASA Langley Research Center; Paul H. Smith, NASA Headquarters; Thomas Sterling, Universities Space Research Association. Wayne Pfeiffer will be the Moderator for the panel session. Dr. Pfeiffer is Deputy Director for Research at the NSF San Diego Supercomputer Center (SDSC). Besides coordinating the research program, Dr. Pfeiffer is directly responsible for the thrust in parallel computing. An ongoing research interest of his is performance analysis of supercomputers. Dr. Pfeiffer has been at SDSC since its inception, having served as manager of both user services and applications. Prior to that he worked as a