Job Scheduling Strategies for Parallel Processing (eBook, PDF)

11th International Workshop, JSSPP 2005, Cambridge, MA, USA, June 19, 2005, Revised Selected Papers
Redaktion: Feitelson, Dror; Schwiegelshohn, Uwe; Rudolph, Larry; Frachtenberg, Eitan

• Format: PDF

Produktdetails

• Verlag: Springer Berlin Heidelberg
• Seitenzahl: 283
• Erscheinungstermin: 9. Dezember 2005
• Englisch
• ISBN-13: 9783540316176
• Artikelnr.: 44126741

Autorenporträt

Dror Feitelson, Hebrew University, Jerusalem, Israel / Eitan Frachtenberg, Los Alamos National Laboratory, NM, USA / Larry Rudolph, Massachusetts Institute of Technology, Cambridge, MA, USA / Uwe Schwiegelshohn, University of Dortmund, Germany

Inhaltsangabe

Modeling User Runtime Estimates.- Workload Analysis of a Cluster in a Grid Environment.- ScoPred-Scalable User-Directed Performance Prediction Using Complexity Modeling and Historical Data.- Open Job Management Architecture for the Blue Gene/L Supercomputer.- AnthillSched: A Scheduling Strategy for Irregular and Iterative I/O-Intensive Parallel Jobs.- An Extended Evaluation of Two-Phase Scheduling Methods for Animation Rendering.- Co-scheduling with User-Settable Reservations.- Scheduling Moldable BSP Tasks.- Evolving Toward the Perfect Schedule: Co-scheduling Job Assignments and Data Replication in Wide-Area Systems Using a Genetic Algorithm.- Wave Scheduler: Scheduling for Faster Turnaround Time in Peer-Based Desktop Grid Systems.- Enhancing Security of Real-Time Applications on Grids Through Dynamic Scheduling.- Unfairness Metrics for Space-Sharing Parallel Job Schedulers.- Pitfalls in Parallel Job Scheduling Evaluation.