Hans W. Meuer

TOP500 Supercomputer sites 11/2000

To provide a better basis for statistics on high-performance computers, we list the sites that have the 500 most powerful computer systems installed. The best Linpack benchmark performance achieved is used as a performance measure in ranking the computers.

Editorial for the ISC'12 research paper sessions proceedings

The International Supercomputing Conference, founded in 1986 as the “Supercomputer Seminar”, has been held annually for the last 25 years. Originally organized by Professor Hans Meuer, Professor of Computer Science at the University of Mannheim and former director of the computer centre, the Seminar brought together a group of 81 scientists and industrial partners who all shared an interest in high performance computing. Since then the annual conference has become a major international event within the HPC community, and accompanying its growth in size over the years, the conference has moved from Mannheim to Heidelberg and then to Dresden and finally to Hamburg. With 2,400 attendees and more than 160 exhibitors from over 50 countries expected to attend this year’s conference , we are optimistic that this steady growth of interest will also turn ISC’12 into a powerful and memorable event. In 2007 we decided to strengthen the scientific part of the conference by presenting selected talks on relevant research results within the HPC field. These research paper sessions began as a separate day preceding the conference, where slides and accompanying papers were made available via the conference web site. The research paper sessions have since evolved into an integral part of the conference, and this year the scientific presentations are scheduled over a period of two days. The call for participation was issued in the winter of 2011, inviting researchers and developers to submit the latest results of their work as full research papers to the scientific sessions’ program committee.

ISC'11 research paper sessions proceedings

The International Supercomputing Conference started in 1986 as the “Supercomputer Seminar” organized by Prof. Hans Meuer, then director of the computer center and professor for computer science at the Universität Mannheim (Germany). At that time it attracted a group of 81 scientists and industrial partners who had a shared interest in high performance computing. Since these early days the annual conference became a major international event in the HPC community. As the conference grew bigger, it moved from Mannheim over Heidelberg and Dresden to Hamburg. In 2010 the conference celebrated its 25th birthday! About 2,000 attendees and more than 140 exhibitors from over 45 countries attend the conference. We are optimistic that this steady growth of interest will also turn ISC’11 into a powerful and memorable event. Over the years we decided to strengthen the scientific part of the conference and to present selected talks on relevant research results in the field of HPC. These research paper sessions started in 2007 as a separate day preceding the conference. Back then, slides and accompanying papers were made available via the conference web site. Now, the research paper sessions evolved into an integral part of the conference. In 2011 scientific presentations are scheduled on three afternoons. The call for participation was issued in winter 2010 inviting researchers and developers to submit

Editorial for the ISC’09 Scientific Day Proceedings

The International Supercomputing Conference started in 1986 as the “Supercomputer Seminar” organized by Prof. Hans Meuer, then director of the computer center and professor for computer science at the University of Mannheim (Germany). Since these early days the annual conference became a major international event in the HPC community. As the conference grew bigger, it moved from Mannheim over Heidelberg and Dresden to Hamburg. In 2009 we expect more than 1,500 participants who will attend the exhibition and the various scientific and technical sessions. Over the years we decided to strengthen the scientific part of the conference and present selected talks on relevant research results in the field of HPC. These scientific sessions started in 2007 and preceded the conference. Slides and accompanying papers were made available via the conference web site. For 2009 we changed this concept and give the scientific part of the conference a higher ranking and visibility. The scientific sessions now merge into the Scientific Day, which is an integral part of the conference. The Scientific Day is scheduled in the afternoon of the first day of the conference. The call for participation was issued in winter 2008 and invited researchers and developers to submit latest results of their work as full research papers to the program committee of the Scientific Day. We solicited contributions in the fields of applications, system architecture, and large-scale system

TOP500 Supercomputers for November 2004

22nd Edition of TOP500 List of World s Fastest Supercomputers Released MANNHEIM, Germany; KNOXVILLE, Tenn.; BERKELEY, Calif. In what has become a much-anticipated event in the world of high-performance computing, the 22nd edition of the TOP500 list of the worlds fastest supercomputers was released today (November 16, 2003). The Earth Simulator supercomputer retains the number one position with its Linpack benchmark performance of 35.86 Tflop/s (teraflops or trillions of calculations per second). It was built by NEC and installed last year at the Earth Simulator Center in Yokohama, Japan.

TOP500 Supercomputers for June 2002

19th Edition of TOP500 List of Worlds Fastest Supercomputers Released MANNHEIM, Germany; KNOXVILLE, Tenn.;&BERKELEY, Calif. In what has become a much-anticipated event in the world of high-performance computing, the 19th edition of the TOP500 list of the worlds fastest supercomputers was released today (June 20, 2002). The recently installed Earth Simulator supercomputer at the Earth Simulator Center in Yokohama, Japan, is as expected the clear new number 1. Its performance of 35.86 Tflop/s (trillions of calculations per second) running the Linpack benchmark is almost five times higher than the performance of the now No.2 IBM ASCI White system at Lawrence Livermore National Laboratory (7.2 Tflop/s). This powerful leap frogging to the top by a system so much faster than the previous top system is unparalleled in the history of the TOP500.

17th Edition of TOP500 List of World's Fastest SupercomputersReseased

17th Edition of TOP500 List of Worlds Fastest Supercomputers Released MANNHEIM, GERMANY; KNOXVILLE, TENN.; BERKELEY, CALIF. In what has become a much-anticipated event in the world of high-performance computing, the 17th edition of the TOP500 list of the worlds fastest supercomputers was released today (June 21). The latest edition of the twice-yearly ranking finds IBM as the leader in the field, with 40 percent in terms of installed systems and 43 percent in terms of total performance of all the installed systems. In second place in terms of installed systems is Sun Microsystems with 16 percent, while Cray Inc. retained second place in terms of performance (13 percent). SGI Inc. was third both with respect to systems with 63 (12.6 percent) and performance (10.2 percent).

Evolution of the HPC Market

Since 1993 a list of the top 500 supercomputer sites worldwide has been assembled twice a year and has been made freely available. The Top500 list, for the first time, provides a reliable base for a well-founded and detailed analysis of the state of High Performance Computing (HPC). This paper summarizes some of the most important observations about HPC during the period 1993–1996. In particular the observed growth in performance, the continued dominance of the world market in HPC by the U.S., the market penetration by commodity microprocessor based systems, and the growing industrial use of supercomputers are shown.

Parallelrechner in den 90er Jahren — Status und Entwicklungstendenzen

Die derzeit dominierende Supercomputer Architektur ist die Multi-Vektorrechner Architektur mit globalem Hauptspeicherkonzept. In Kapitel 1 wird auf diese Systeme eingegangen, ihre Entwicklung, ihr Status und ihre Grenzen werden aufgezeigt. Abschliesend wird die Situation auf dem Supercomputermarkt anhand von aktuellen Statistiken erlautert, insbesondere auch in Deutschland. In Kapitel 2 werden die eigentlichen Parallelrechner, basierend auf VLSI-Technik und insbesondere verteiltem Speicherkonzept, in die Uberlegungen mit einbezogen. Welche Vorteile, aber auch Nachteile diese Systeme mit lokalem Speicher haben, wird diskutiert. Ausfuhrlicher werden die Systeme von Intel, Parsytec, iP-Systems und Suprenum vorgestellt. Im 3.Kapitel schlieslich wird eine Prognose bis etwa zum Jahre 2000 gegeben anhand der zu erwartenden Entwicklung der Multi-Vektorrechner und es wird deduziert, das in der zweiten Halfte der 90er Jahre die Ablosung der auch in diesem Jahrzehnt dominierenden Architektur eingeleitet werden wird.