DC FieldValueLanguage
dc.contributor.authorSpeck, Robert-
dc.contributor.authorRuprecht, Daniel-
dc.date.accessioned2021-10-14T09:54:52Z-
dc.date.available2021-10-14T09:54:52Z-
dc.date.issued2017-02-
dc.identifier.citationParallel Computing 62: 20-37 (2017-02)de_DE
dc.identifier.issn1872-7336de_DE
dc.identifier.urihttp://hdl.handle.net/11420/10520-
dc.description.abstractWe introduce and analyze different strategies for the parallel-in-time integration method PFASST to recover from hard faults and subsequent data loss. Since PFASST stores solutions at multiple time steps on different processors, information from adjacent steps can be used to recover after a processor has failed. PFASST's multi-level hierarchy allows to use the coarse level for correcting the reconstructed solution, which can help to minimize overhead. A theoretical model is devised linking overhead to the number of additional PFASST iterations required for convergence after a fault. The potential efficiency of different strategies is assessed in terms of required additional iterations for examples of diffusive and advective type.en
dc.language.isoende_DE
dc.relation.ispartofParallel Computingde_DE
dc.subjectAlgorithm-based fault tolerancede_DE
dc.subjectBoussinesq equationsde_DE
dc.subjectGray–Scott modelde_DE
dc.subjectParallel-in-time integrationde_DE
dc.subjectResiliencede_DE
dc.subjectComputer Science - Distributed; Parallel; and Cluster Computingde_DE
dc.subjectComputer Science - Distributed; Parallel; and Cluster Computingde_DE
dc.titleToward fault-tolerant parallel-in-time integration with PFASSTde_DE
dc.typeArticlede_DE
dc.type.diniarticle-
dcterms.DCMITypeText-
tuhh.abstract.englishWe introduce and analyze different strategies for the parallel-in-time integration method PFASST to recover from hard faults and subsequent data loss. Since PFASST stores solutions at multiple time steps on different processors, information from adjacent steps can be used to recover after a processor has failed. PFASST's multi-level hierarchy allows to use the coarse level for correcting the reconstructed solution, which can help to minimize overhead. A theoretical model is devised linking overhead to the number of additional PFASST iterations required for convergence after a fault. The potential efficiency of different strategies is assessed in terms of required additional iterations for examples of diffusive and advective type.de_DE
tuhh.publisher.doi10.1016/j.parco.2016.12.001-
tuhh.type.opus(wissenschaftlicher) Artikel-
dc.type.driverarticle-
dc.type.casraiJournal Article-
tuhh.container.volume62de_DE
tuhh.container.startpage20de_DE
tuhh.container.endpage37de_DE
dc.identifier.arxiv1510.08334v2de_DE
dc.identifier.scopus2-s2.0-85009239984de_DE
local.publisher.peerreviewedtruede_DE
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.creatorOrcidSpeck, Robert-
item.creatorOrcidRuprecht, Daniel-
item.cerifentitytypePublications-
item.mappedtypeArticle-
item.openairetypeArticle-
item.fulltextNo Fulltext-
item.grantfulltextnone-
item.creatorGNDSpeck, Robert-
item.creatorGNDRuprecht, Daniel-
item.languageiso639-1en-
crisitem.author.deptMathematik E-10-
crisitem.author.orcid0000-0002-3879-1210-
crisitem.author.orcid0000-0003-1904-2473-
crisitem.author.parentorgStudiendekanat Elektrotechnik, Informatik und Mathematik-
Appears in Collections:Publications without fulltext
Show simple item record

Page view(s)

11
Last Week
0
Last month
0
checked on Dec 5, 2021

SCOPUSTM   
Citations

4
Last Week
0
Last month
checked on Nov 30, 2021

Google ScholarTM

Check

Add Files to Item

Note about this record

Cite this record

Export

Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.