Exascale Computing: The last rehearsal before the post-Moore era
Dr. Marc Snir
Math and Computer Science (MCS) Division
Argonne National Laboratory
Michael Faiman and Saburo Muroga Professor
Department of Computer Science
University of Illinois at Urbana-Champaign
Stuart Building 113
Tuesday, November 29th, 2011
12:45PM - 1:45PM
Abstract: The continued shrinking in silicon device size represented by Moore's Law is very likely to slow down or even stop in the next decade. No other device technology seems ready to take over. When this happens, continued performance improvements in computing systems (when algorithmic improvements are unavailable or inadequate) will have to come from increased "silicon efficiency": The ability to compute more with the same number of devices and the same energy budget. This pressure for higher silicon efficiency is already extant in large supercomputing systems and will become paramount at exascale: Current hardware and software architectures do not seem to promise exascale performance at reasonable power, so that an exascale system will need much higher silicon efficiency than current systems. It is likely that exascale systems will need to pioneer fundamentally new hardware and software designs that will become prevalent in the next decade. The magnitude of the needed technological changes, and the disruptions entailed by an abrupt slow-down in the rate at which computer performance improves, mandate significant research investments in technologies needed for increasing silicon efficiency. We shall describe in our talk some of the possible research directions.
Bio: Marc Snir is Director of the Mathematics and Computer Science Division at the Argonne National Laboratory and Michael Faiman and Saburo Muroga Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign. He currently pursues research in parallel computing. Marc was head of the Computer Science Department from 2001 to 2007. Until 2001 he was a senior manager at the IBM T. J. Watson Research Center where he led the Scalable Parallel Systems research group that was responsible for major contributions to the IBM SP scalable parallel system and to the IBM Blue Gene system. Marc Snir received a Ph.D. in Mathematics from the Hebrew University of Jerusalem in 1979, worked at NYU on the NYU Ultracomputer project in 1980-1982, and was at the Hebrew University of Jerusalem in 1982-1986, before joining IBM. Marc Snir was a major contributor to the design of the Message Passing Interface. He has published numerous papers and given many presentations on computational complexity, parallel algorithms, parallel architectures, interconnection networks, parallel languages and libraries and parallel programming environments. Marc is AAAS Fellow, ACM Fellow, and IEEE Fellow. He has Erdos number 2 and is a mathematical descendant ofJacques Salomon Hadamard.