Coscheduling under Memory Constraints in a NOW

dc.contributor.authorGiné, Francesc
dc.contributor.authorSolsona Tehàs, Francesc
dc.contributor.authorHernández Budé, Porfidio
dc.contributor.authorLuque, Emilio
dc.date.accessioned2016-06-23T08:52:36Z
dc.date.embargoEndDate2025-01-01
dc.date.issued2001
dc.description.abstractNetworks of Workstations (NOW) have become important and cost-effective parallel platforms for scientific computations. In practice, a NOW system is heterogeneous and non-dedicated. These two unique factors make scheduling policies on multiprocessor/multicomputer systems unsuitable for NOWs. However, the coscheduling principle is still an important basis for parallel process scheduling in these environments. We propose a new coscheduling algorithm for reducing the number of page faults across a non-dedicated cluster by increasing the execution priority of parallel tasks with lower page fault rate. Our method is based on knowledge of events obtained during execution, as communication activity and memory size of every task. The performance of our proposal has been analyzed and compared with other coscheduling implementations by means of simulation.ca_ES
dc.description.sponsorshipThis wor kwas supported by the CICYT under contract TIC98-0433ca_ES
dc.identifier.doihttps://doi.org/10.1007/3-540-45540-X_4
dc.identifier.idgrec006691
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/10459.1/57273
dc.language.isoengca_ES
dc.publisherSpringer Verlagca_ES
dc.relationinfo:eu-repo/grantAgreement/MIECU//TIC98-0433/ES/ca_ES
dc.relation.isformatofReproducció del document publicat a https://doi.org/10.1007/3-540-45540-X_4ca_ES
dc.relation.ispartofLecture Notes in Computer Science, 2000, vol. 2221, p. 41-65ca_ES
dc.rights(c) Springer Verlag, 2001ca_ES
dc.rights.accessRightsinfo:eu-repo/semantics/restrictedAccessca_ES
dc.titleCoscheduling under Memory Constraints in a NOWca_ES
dc.typearticleca_ES
dc.type.versionpublishedVersionca_ES
Files
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: