Topic 3

Scheduling and Load Balancing

Description

Scheduling and load balancing techniques are crucial for implementing efficient parallel and distributed applications. These techniques can be provided either at the application level or at the system level, and both approaches are of interest for this workshop. At the application level, the mapping of parallel computations onto parallel computer systems and the development of dynamic load balancing algorithms that are able to adapt to the particular characteristics of the underlying parallel computer system are of particular relevance. At the system level, areas of interest include checkpointing and migration, workload modeling, and resource management strategies. Theoretical results that can be used as solid foundations for designing efficient and robust scheduling, load-balancing, and/or resource management algorithms are particularly welcome together with novel such algorithms for modern parallel and distributed systems such as clusters, grids, and global computing platforms.

Focus

• Scheduling algorithms for homogeneous or heterogeneous platforms,
• Theoretical foundations of scheduling algorithms,
• Robustness of scheduling algorithms,
• Multi-criteria scheduling,
• Decentralized or hierarchical scheduling,
• Adaptable load balancing algorithms,
• Evaluation and analysis of load balancing and scheduling techniques,
• Implementations of scheduling and load-balancing algorithms,
• Tools and environments for load balancing and scheduling
• Workload characterization and modeling

Organization

Global Chair	Local Chair
Henri Casanova Dept. of Information and Computer Sciences University of Hawai`i at Manoa Honolulu, USA	Olivier Beaumont LaBRI, Haut carré, domaine Universitaire Talence, France
Vice Chair	Vice Chair
Uwe Schwiegelshohn Universitat Dortmund Institut for Roboterforschung Lehrstuhl for Datenverarbeitungssysteme Dortmund, Germany	Marek Tudruj Intitute of Computer Science Polish Academy of Science Warszawa, Poland