PADC 2002
Workshop on Performance Analysis and Distributed Computing
19.-23.August 2002
Schloss Dagstuhl
Please visit the official seminar page at Dagstuhl.
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 workshop 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 workshop 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
| ||||||
| 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 |
Organizers
| Michael Gerndt, TU München |
| Vladimir Getov, University of Westminster |
| Adolfy Hoisie, Los Alamos National Laboratory |
| Allen Malony, University of Oregon |
| Bart Miller, University of Wisconsin-Madison |
Participation
Participation is by invitation only.
Pictures
