Analyzing the Interaction of OpenMP Programs Within Multiprogramming Environments on a Sun Fire E25K System with PARbench

  • Rick Janda
  • Wolfgang E. Nagel
  • Bernd Trenkler
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4128)


Nowadays, most high performance computing systems run in multiprogramming mode with several user programs simultaneously utilizing the available CPUs. Even though most current SMP systems are implemented as ccNUMA to reduce the bottleneck of main memory access, the user programs still interact as they share other system resources and influence the scheduler decisions with their generated load. PARbench was designed to generate complete load scenarios based on synthetic jobs and to measure the job behavior during the execution of these scenarios. The E25K is a ccNUMA system with up to 72 dual core CPUs and a crossbar-based connection network. This paper describes the results of the examination of such a Sun Fire E25K system with PARbench. First, PARbench was used to investigate the performance impact caused by the interactions of jobs on fully loaded and overloaded machines. Second, the impact of operating system tasks to the performance of OpenMP parallelized programs in scenarios of full load as created by the cluster batch engine is quantized, especially when these system tasks are not considered in the initial load calculation. Additionally, the generated scenarios were used for a statistical analysis of the scheduling of OpenMP programs, focusing on data locality and migration frequency.


System Task Work Thread High Performance Computing System OpenMP Program Cache Usage 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Linn, M.A.: Eine Programmierumgebung zur Messung der wechselseitigen Einflüsse von Hintergrundlast und parallelem Programm. Techn. Report Jül-2416, Forschungszentrum Jülich (1990)Google Scholar
  2. 2.
    Nagel, W.E.: Performance evaluation of multitasking in a multiprogramming environment. Techn. Report KF-ZAM-IB-9004, Forschungszentrum Jülich (1990)Google Scholar
  3. 3.
    Boesler, S.: Performance-Analyse von Hochleistungsrechnern im Multiprogramming-Betrieb: Untersuchungen auf der SGI Origin. Diplomarbeit, Center for High Performance Computing, Dresden University of Technology (2001)Google Scholar
  4. 4.
    Kowarz, A.: Performance-Untersuchungen mit dem PARbench-System auf unterschiedlichen Parallelrechnern. Diplomarbeit, Zentrum für Hochleistungsrechnen, Technische Universität Dresden (2003)Google Scholar
  5. 5.
    Dietze, H.: Das PARbench-System: Untersuchungen zum Scheduling von parallelen Programmen auf der IBM p690. Diplomarbeit, Zentrum für Hochleistungsrechnen, Technische Universität Dresden (2004)Google Scholar
  6. 6.
    Sun Microsystems, Inc.: Sun Fire E25K/E20K Systems Overview (2004)Google Scholar
  7. 7.
    Sun Microsystems, Inc.: UltraSPARC IV Whitepaper (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rick Janda
    • 1
  • Wolfgang E. Nagel
    • 1
  • Bernd Trenkler
    • 1
  1. 1.Center of Information Services and High Performance ComputingDresden University of TechnologyDresdenGermany

Personalised recommendations