Show simple item record

dc.contributor.authorSubasi, Omer
dc.contributor.authorMartsinkevich, Tatiana
dc.contributor.authorZyulkyarov, Ferad
dc.contributor.authorUnsal, Osman Sabri
dc.contributor.authorLabarta Mancho, Jesús José
dc.contributor.authorCappello, Franck
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2016-10-19T13:17:56Z
dc.date.available2017-10-03T00:30:37Z
dc.date.issued2016-09-26
dc.identifier.citationSubasi, Omer [et al.]. Unified fault-tolerance framework for hybrid task-parallel message-passing applications. "International Journal of High Performance Computing Applications", 26 Setembre 2016.
dc.identifier.issn1094-3420
dc.identifier.urihttp://hdl.handle.net/2117/90874
dc.description.abstractWe present a unified fault-tolerance framework for task-parallel message-passing applications to mitigate transient errors. First, we propose a fault-tolerant message-logging protocol that only requires the restart of the task that experienced the error and transparently handles any message passing interface calls inside the task. In our experiments we demonstrate that our fault-tolerant solution has a reasonable overhead, with a maximum observed overhead of 4.5%. We also show that fine-grained parallelization is important for hiding the overheads related to the protocol as well as the recovery of tasks. Secondly, we develop a mathematical model to unify task-level checkpointing and our protocol with system-wide checkpointing in order to provide complete failure coverage. We provide closed formulas for the optimal checkpointing interval and the performance score of the unified scheme. Experimental results show that the performance improvement can be as high as 98% with the unified scheme.
dc.description.sponsorshipThe author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the FI-DGR 2013 scholarship and the European Community’s Seventh Framework Programme [FP7/2007-2013] under the Mont-blanc 2 Project (www.montblanc-project.eu), grant agreement no. 610402 and TIN2015-65316-P.
dc.format.extent17 p.
dc.language.isoeng
dc.publisherSAGE Publications
dc.subjectÀrees temàtiques de la UPC::Enginyeria electrònica
dc.subject.lcshFault-tolerant computing
dc.subject.lcshMathematical modeling and computation
dc.subject.otherFault-tolerance
dc.subject.otherMessage logging
dc.subject.otherCheckpoint/restart
dc.subject.otherTask-based programming model
dc.subject.otherOptimal checkpointing interval
dc.titleUnified fault-tolerance framework for hybrid task-parallel message-passing applications
dc.typeArticle
dc.subject.lemacModels matemàtics
dc.subject.lemacProgramació (Ordinadors)
dc.identifier.doi10.1177/1094342016669416
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://hpc.sagepub.com/content/early/2016/09/26/1094342016669416.abstract
dc.rights.accessOpen Access
local.identifier.drac23515513
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/1PE/TIN2015-65316-P
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/610402/EU/Mont-Blanc 2, European scalable and power efficient HPC platform based onlow-power embedded technology/MONT-BLANC 2
local.citation.publicationNameInternational Journal of High Performance Computing Applications
local.citation.volume32
local.citation.number5
local.citation.startingPage641
local.citation.endingPage657


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder