The Department of Computer Science at PSU's Maseeh College of Engineering and Computer Science presents as part of the Computer Science Colloquium Series, BlueGene/L: Overcoming the Challenges of Massive Parallelism.
Title: "BlueGene/L: Overcoming the Challenges of Massive Parallelism"
Speaker: Bronis R. de Supinski, Data Analysis Group Leader, Center for Applied Scientific Computing, Lawrence Livermore National Laboratory
Date: April 10, 2006
Time: 12:00 - 1:00 p.m.
Location: Room 2500B, 1900 Building, 1900 SW Fourth Avenue, Portland, Oregon 97201 (map)
This series is free and open to the public. For further information, contact the Department of Computer Science, (503) 725-2416 or firstname.lastname@example.org.
Unprecedented levels of performance have been achieved on BlueGene/L (BG/L) designed by IBM Research in partnership with the Advanced Simulation and Computing (ASC) Program, part of the U.S. Department of Energy's National Nuclear Security Administration. The order of magnitude improvement in performance was enabled by an order of magnitude increase in processors. This unprecedented scale has presented unique challenges for system software and tools as well as applications, from diverse domains such as molecular dynamics and breadth-first search. This talk will present details of the system architecture and software and results for several applications, many of which have achieved record levels of performance. It will conclude with a discussion of our novel solution to support dynamic instrumentation when dynamic loading is unavailable.
Bronis R. de Supinski is the Data Analysis Group Leader in the Center for Applied Scientific Computing (CASC) at Lawrence Livermore National Laboratory (LLNL). His research interests include high performance computer architectures, performance modeling and analysis, message passing implementations and tools, memory performance improvement, cache coherence and distributed shared memory, consistency semantics and programming models. Bronis earned his Ph.D. in Computer Science from the University of Virginia in 1998 and he joined CASC in July 1998. Currently, his projects include work on the BlueGene/L System software project, applications of data mining techniques to performance analysis and modeling, investigations into mechanisms and tools to improve memory performace, and a variety of optimization techniques and tools for MPI. He is a member of the ACM and the IEEE Computer Society.