August 18 – 23 , 2002, Dagstuhl Seminar 02341

Performance Analysis and Distributed Computing


Michael Gerndt (TU München, DE)
Vladimir S. Getov (University of Westminder. – London, GB)
Adolfy Hoisie (Los Alamos National Lab., US)
Allen D. Malony (University of Oregon – Eugene, US)
Barton P. Miller (University of Wisconsin – Madison, US)

For support, please contact

Dagstuhl Service Team


External Homepage
List of Participants
Dagstuhl's Impact: Documents available
Dagstuhl-Seminar-Report 349


The performance of parallel and distributed systems and applications - its evaluation, analysis, prediction and optimization - is a fundamental topic for research investigation and a technological problem that requires innovations in tools and techniques to keep pace with system and application evolution. This dual view of performance "science" and performance "technology" jointly spans broad fields of performance modeling, evaluation, instrumentation, measurement, analysis, monitoring, optimization, and prediction.

Most of the past and current research on performance analysis is focused on high-performance computing using dedicated parallel machines since performance is the ultimate goal in this environment. Future applications in the area of high-performance computing will not only use individual parallel systems but a large set of networked resources. This scenario of computational and data grids is attracting a lot of attention from application scientists as well as from computer scientists. In addition to the inherent complexity of program tuning on parallel machines, the sharing of resources and the transparency of the actual available resources introduce new challenges on performance analysis systems and performance tuning techniques. To meet those challenges, experts in parallel computing have to work together with experts in distributed computing. Aspects such as network performance, quality-of-service, security, heterogeneity, middleware systems, and object-oriented modeling - just to mention a few - will have a big impact on grid computing strategies.

Therefore, the seminar will bring together people from high-performance and distributed computing to discuss the impact of the following aspects on performance analysis for grid environments. The seminar will develop perspectives for performance oriented program development not only in scientific computing but also in commercial distributed computing. The workshop is scheduled for the week before Euro-Par in Paderborn ( to allow people to attend both events.

Topics to be covered include:

  • Performance analysis tools and techniques for parallel computers
  • Performance tools for distributed applications
  • Network performance measurement and quality-of-service
  • Performance models
  • Performance data requirements of
    • adaptive algorithms, e.g. caching schemes for web services and video streaming as well as load balancing techniques
    • scheduling and resource management techniques
    • accounting for grid environments
  • Standard formats for performance data and protocols for accessing performance data
  • Automation techniques for the performance analysis process
  • Security requirements for performance analysis systems
  • Integration of performance analysis and performance tuning

Dagstuhl Seminar Series


In the series Dagstuhl Reports each Dagstuhl Seminar and Dagstuhl Perspectives Workshop is documented. The seminar organizers, in cooperation with the collector, prepare a report that includes contributions from the participants' talks together with a summary of the seminar.


Download overview leaflet (PDF).

Dagstuhl's Impact

Please inform us when a publication was published as a result from your seminar. These publications are listed in the category Dagstuhl's Impact and are presented on a special shelf on the ground floor of the library.


Furthermore, a comprehensive peer-reviewed collection of research papers can be published in the series Dagstuhl Follow-Ups.