Prof. Dr. Horst D. Simon
Associate Laboratory Director for Computing Sciences, Lawrence Berkeley National Laboratory, USA
Horst Simon is Associate Laboratory Director at Lawrence Berkeley National Laboratory for Computing Sciences and the Division Director for the Computational Research Division and Adjunct Professor of Computer Science at the University of California, Berkeley. His research interests are in the development of sparse matrix algorithms, algorithms for large-scale eigenvalue problems, and domain decomposition algorithms. His recursive spectral bisection algorithm is a breakthrough in parallel algorithms, honored with the 1988 Gordon Bell Prize. He has served as a senior manager for Silicon Graphics, the Computer Sciences Corporation, Boeing Computer Services, and has been a member of the faculty at the State University of New York. He is currently a member of the advisory boards of more than five research organizations located throughout the world and is a member of many journal editorial boards and one of four editors of the twice-yearly “TOP500” list of the world’s most powerful computing systems.
Horst Simon & ISC
Horst Simon was actively involved with ISC since 1992 and attended the conference ten times. For all conferences he made special contributions that added to the long term success of the conference series.
At his first attendance in Mannheim in 1992 he presented jointly with Chris Bischof a lecture on "Erfahrungen und Erwartungen mit massive parallelen Systemen" (Experiences and expectations with massive parallel systems), which was overview of the then nascent US HPCC initiative, and its implementation at NASA and DOE. In 1994 he attended again and reported about "The NAS Parallel Benchmarks: Review and Current Results". The transition to parallel systems was in full force at the time, and the NAS Parallel Benchmarks provided the first objective comparison of the new micro processor based systems on scientific codes of relevance. Since 1993 Horst also contributed in various ways to the TOP500 report. For example his paper “High Performance Computing in the U.S.,” pages 117-148, Chapter 6 in TOP500 Report 1993, contains several tables and statitics that were extracted from the TOP500 list, which subsequently became a standard for analyzing the trends latent in the list.
In 1995 Horst had joined SGI and attended the Mannheim symposium reporting about "Shared Memory Multiprocessors" in a special tutorial organized by Prof. Arndt Bode. In 1997 Horst (now Director at NERSC in Berkeley) reported about "High Performance Computing in the US - the next five years", and in 1999 about "Building the Teraflops/Petabytes Production Supercomputing Center". In 2001 the conference had moved to Heidelberg and Horst gave a tutorial on "Large Scale Data Intensive Computing" jointly with Michael Berry from the University of Tennessee. His invited presentation at the conference had the title "The Future of Supercomputers". In 2003 the Earth Simulator had arrived and the discussion on the merits of vector computing was intense, in particular in the U.S. Horst reported in Heidelberg about this topic with the presentation about "The Divergence Problem". He also gave short overview about "New Computing Initiatives in the U.S.".
Horst's many contributions to the conference finally made him the right candidate to be the conference keynote speaker in 2005, when ISC celebrated its 20th anniversary. Fitting for the occasion the title of his keynote was “Progress in Supercomputing: The Top Three Breakthroughs of the Last 20 and the Top Three Challenges for the Next 20 Years.”
In 2006 the ISC conference moved to Dresden and Horst participated as a session chair, and Hot Seat inquisitor. With the continued growth of ISC there were also many other events surrounding the conference, and Horst gave a presentation at the IDC HPC USer Forum.
Two new topics had emerged in 2008: Roadrunner had become the first Petaflops system, and energy efficiency was a hot topic. Horst attended ISC in Dresden and organized and chaired a panel session about "Is HPC turning Green?" as well as gave a US perspective on the Roadrunner accomplishments. In 2010 in Hamburg, Horst will chair another session with large scale perspective "From Konrad Zuse to Exascale Computing" that will include a pale discussion about Exaflops computing.