Job Scheduling Strategies for Parallel Processing

This book constitutes the thoroughly refereed post-workshop proceedings of the 13th International Workshop on Job Scheduling Strategies for Parallel Processing, JSSPP 2007, held in Seattle, WA, USA, in June 2007, in conjunction with the 21st ACM International Conference on Supercomputing, ICS 2007.

The 10 revised full research papers presented went through the process of strict reviewing and subsequent improvement. The papers cover all current issues of job scheduling strategies for parallel processing from the supercomputer-centric viewpoint but also address many nontraditional high-performance computing and parallel environments that cannot or need not access a traditional supercomputer, such as grids, Web services, and commodity parallel computers. The papers are organized in topical sections on performance and tools, queueing systems, as well as grid and heterogeneous architectures.

Klappentext

This proceedings volume examines job scheduling strategies for parallel processing from the supercomputer-centric viewpoint. It also addresses many nontraditional high-performance computing and parallel environments that don't access a supercomputer.

Inhalt

New Challenges of Parallel Job Scheduling.- Group-Wise Performance Evaluation of Processor Co-allocation in Multi-cluster Systems.- Enhancing an Open Source Resource Manager with Multi-core/Multi-threaded Support.- A Job Self-scheduling Policy for HPC Infrastructures.- QBETS: Queue Bounds Estimation from Time Series.- Probabilistic Backfilling.- Impact of Reservations on Production Job Scheduling.- Prospects of Collaboration between Compute Providers by Means of Job Interchange.- GridARS: An Advance Reservation-Based Grid Co-allocation Framework for Distributed Computing and Network Resources.- A Self-optimized Job Scheduler for Heterogeneous Server Clusters.