Browsing by Author "Küster, Uwe"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    Demonstration of supercomputing activities
    (1996) Geiger, Alfred; Wierse, Andreas; Helf, Clemens; Schmidt, Thomas; Warendorf, Katina; Küster, Uwe; Loebich, Isabel; Lepper, Jürgen
    During the inauguration of HLRS a broad variety of supercomputing-activities was demonstrated. As HLRS is involved in the development of Software for supercomputers as well as in their usage, the demos concentrated on the development of novel simulation-codes in the field of Computational Fluid Dynamics, the software-tools which are necessary for the developper and on the presentation of typical applications from engineering in the VR-lab.
  • Thumbnail Image
    ItemOpen Access
    The NEC SX-4 at HWW
    (1996) Geiger, Alfred; Küster, Uwe
    The NEC SX-4 which started production at Stuttgart on July 15th 1996, is jointly operated by university and industry in the framework of the HWW Betriebs GmbH. The major goal of HWW is to provide the users in academia and industry with the quality to solve larger problems, the capacity for better throughput and a broader diversity of usable architectures. The machine in Stuttgart is actually the only installed SX-4 equipped with 32 processors worldwide. In the Top 500 list of Summer 1996 [1], it is ranked as the most powerful system overall in Europe and the most powerful shared memory system worldwide. This article is a first description of the system and the HWW environment. It gives some performance numbers in comparison to the Cray C94D, which served Stuttgart University in the last years and makes some links to informations about how to access the system.
  • Thumbnail Image
    ItemOpen Access
    A parallel Lanczos algorithm for eigensystem calculation
    (1998) Kersken, Hans-Peter; Küster, Uwe
    Eigenvalue problems arise in many fields of physics and engineering science for example in structural engineering from prediction of dynamic stability of structures or vibrations of a fluid in a closed cavity. Their solution consumes a large amount of memory and CPU time if more than very few (1-5) vibrational modes are desired. Both make the problem a natural candidate for parallel processing. Here we shall present some aspects of the solution of the generalized eigenvalue problem on parallel architectures with distributed memory. The research was carried out as a part of the EC founded project ACTIVATE. This project combines various activities to increase the performance vibro-acoustic software. It brings together end users form space, aviation, and automotive industry with software developers and numerical analysts.
  • Thumbnail Image
    ItemOpen Access
    Technisch-Wissenschaftliches Rechnen mit modernen PCs
    (1996) Helf, Clemens; Küster, Uwe; Zürn, Manuela
    Intel hat im vergangenen Jahr mit dem Pentium Pro den ersten PC-Prozessor auf den Markt gebracht, der hohe Leistung, PC-Funktionalität und -Kosten miteinander vereinigen soll. Er wird in Home Computern, Workstations, Servern und Supercomputern stecken. Seine nominelle Leistung ist so hoch wie die einer CRAY-1, das Memory wenigstens das Achtfache. In der Vergangenheit waren aufwendige numerische Berechnungen an Supercomputer gebunden, danach eine Domäne der Workstations. Wird der PC in Zukunft die Alternative im Technisch-Wissenschaftlichen Rechnen?