Euro-Par 2000 August 28 to September 1st in Munich
Munich 12 September 2000 The 6th edition of the Euro-Par Conference, a union of several, former independent conferences, attracted more than 400 participants from all over the world. Additionally to the keynote and invited talks, 167 have been accepted from 326 papers. The proceedings have been published in Springer Verlag, Lecture Notes in Computer Science, Volume 1900. Around the Conference tutorials and two other conferences have been organised, SCI Europe 2000 (Scalable Coherent Interface), proceedings are available and APART 2000, Automatic Performance Analysis.
Professor Arndt Bode and his team from the Informatics Departure at Technical University Munich, Lehrstuhl für Rechnertechnik und Rechnerorganisation (LRR), successfully organised the Conference. Additionally there was an exhibition with Fujitsu Siemens Computers, AEA Technology, Dolphin, RasDaMan and KONWIHR in the reguistration area.
About 167 talks have been given in the Conference. Six invited talks highlighted the Performance of Parallel Simulations based on Partial Differential Equations, E2K Technology and Implementation (Elbrus International), Grid-based Computing, Communication Modes for Parallel Computing, Moore's Law and the Top500 project.
The talks can be grouped in 20 topics:
-
Support Tools and Environments
-
Performance Evaluation and Prediction
-
Scheduling and Load Balalancing
-
Compilers and High Performance
-
Parallel and Distributed Databases and Applications
-
Complexity Theory and Algorithms
-
Applications on High-Performance Computers
-
Parallel Computer Architectures
-
Distributed Systems and Algorithms
-
Parallel Programming: Models, Methods and Programming Languages
-
Numerical Algorithms for Linear and Nonlinear Algebra
-
European Projects
-
Routing and Communication in Interconnection Networks
-
Instruction-Level Parallelism and Architecture
-
Object Oriented Architectures, Tools and Applications
-
Architectures and Algorithms for Multimedia Applications
-
Cluster Computing
-
Metacomputing
-
Parallel I/O and Storage Technology
-
Problem Solving Environments
It was quite interesting to hear David Keyes talk, Old Dominion Univ. Norfolk, Law. Livermore Lab and Nasa, on "Four Horizons for Enhancing the Performance of Parallel Simulations Based on Partial Differential Equations (PDE)". As PDE simulations require a balanced computing architecture between the components not necessarily in a machine. He proposed four possible ways:
1. expand the number of processors
2. more efficient use of faster processors
3. more architecture-friendly algorithms
4. Algorithms delivering more "Science per Flop".
Beneath that he proposed that the user has direct access to the L2 caches. This reminds me of the good old times with the Control Data Cyber 76 and its Large Core Memory which could be accessed by the user through Level2 statements. On the other hand he wanted to switch off the cache coherence, as the user could be responsible for this with his data to save computer cycles for the solution of PDEs.
The proceedings, mo re than 1360 pages, are published with Springer-Verlag in Lecture Notes in Computer Science, Vol. 1900.
In parallel the 3rd International Conference on SCI-based Technology and Research took place. The 14 talks covered the topics:
-
Message Passing Programming
-
Middleware for SCI based clusters
-
SCI Monitoring
-
SCI Hardware Developments
-
SCI-based Data Acquisition in High-Energy Physics
-
SCI Switch Evaluation and Design
.
The Proceedings are available from Dr. Wolfgang Karl (LRR), email: karlw@in.tum.de or by telephone: +49 89 289 28278
Uwe Harms
[News on Advanced IT][Calendar][Analysis][IT in Medicine]
|