In this paper we demonstrate that a class of molecular dynamics applications can be effectively parallelized on the scale required for efficient execution on a massively parallel computer with millions of concurrent threads of execution. Such cellular architectures have been advocated as one approach to building Petaflop-scale computers, as proposed in the IBM Blue Gene project. Starting from the sequential version of a well known molecular dynamics code, we developed a new application that exploits the multiple levels of parallelism in a cellular architecture. We perform both an analytical and a simulation study of the behavior of this application when executed on a very large number of threads. We demonstrate that this class of applications can execute efficiently on a large cellular machine and, thus, provide support for this approach to achieving a Petaflop computer.
By: George S. Almasi, Calin Cascaval, Jose G. Castanos, Monty Denneau, Wilm Donath, Maria Eleftheriou, Mark Giampapa, Howard Ho, Derek Lieber, Jose E. Moreira, Dennis Newns, Marc Snir, Henry S. Warren, Jr.
Published in: RC21965 in 2001
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .