{"id":"https://openalex.org/W2170163131","doi":"https://doi.org/10.1109/clustr.2003.1253321","title":"Coordinated checkpoint versus message log for fault tolerant MPI","display_name":"Coordinated checkpoint versus message log for fault tolerant MPI","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2170163131","doi":"https://doi.org/10.1109/clustr.2003.1253321","mag":"2170163131"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2003.1253321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2003.1253321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE International Conference on Cluster Computing CLUSTR-03","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113937737","display_name":"Bouteiller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144804","display_name":"Laboratoire de Recherche en Informatique","ror":"https://ror.org/04e3ktk27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210144804","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Bouteiller","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LRI, Universit\u00e9 de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I204730241","https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088833068","display_name":"Pierre Lemarinier","orcid":"https://orcid.org/0000-0002-6353-4136"},"institutions":[{"id":"https://openalex.org/I4210144804","display_name":"Laboratoire de Recherche en Informatique","ror":"https://ror.org/04e3ktk27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210144804","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lemarinier","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LRI, Universit\u00e9 de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I204730241","https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096841541","display_name":"Krawezik","orcid":null},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210144804","display_name":"Laboratoire de Recherche en Informatique","ror":"https://ror.org/04e3ktk27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210144804","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Krawezik","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France"],"affiliations":[{"raw_affiliation_string":"LRI, Universit\u00e9 de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I204730241","https://openalex.org/I4210144804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5096868819","display_name":"Capello","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144804","display_name":"Laboratoire de Recherche en Informatique","ror":"https://ror.org/04e3ktk27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210144804","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Capello","raw_affiliation_strings":["LRI, Univ. de Paris Sud, France"],"affiliations":[{"raw_affiliation_string":"LRI, Univ. de Paris Sud, France","institution_ids":["https://openalex.org/I4210144804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113937737"],"corresponding_institution_ids":["https://openalex.org/I102197404","https://openalex.org/I204730241","https://openalex.org/I4210144804"],"apc_list":null,"apc_paid":null,"fwci":4.2494,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.95009615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8724635243415833},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6806595325469971},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6055874228477478},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5817431211471558},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5516220927238464},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4937838017940521},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4877391755580902},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4222254455089569},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3205055296421051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8724635243415833},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6806595325469971},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6055874228477478},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5817431211471558},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5516220927238464},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4937838017940521},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4877391755580902},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4222254455089569},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3205055296421051},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/clustr.2003.1253321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2003.1253321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE International Conference on Cluster Computing CLUSTR-03","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W21025594","https://openalex.org/W1510894298","https://openalex.org/W1581312614","https://openalex.org/W1848988118","https://openalex.org/W1911403303","https://openalex.org/W1923741182","https://openalex.org/W2005867208","https://openalex.org/W2013639878","https://openalex.org/W2017838136","https://openalex.org/W2052915895","https://openalex.org/W2081612620","https://openalex.org/W2100970777","https://openalex.org/W2105039796","https://openalex.org/W2108686966","https://openalex.org/W2125776594","https://openalex.org/W2126071114","https://openalex.org/W2131053137","https://openalex.org/W2134533588","https://openalex.org/W2135917956","https://openalex.org/W2142234387","https://openalex.org/W2160123909","https://openalex.org/W2171453084","https://openalex.org/W4285719527","https://openalex.org/W6630659090","https://openalex.org/W6675270725","https://openalex.org/W6675705929"],"related_works":["https://openalex.org/W2978729728","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W4254638342","https://openalex.org/W2897533804","https://openalex.org/W2098482419","https://openalex.org/W2890506991","https://openalex.org/W2054468904","https://openalex.org/W2082659044","https://openalex.org/W2811255748"],"abstract_inverted_index":{"MPI":[0],"is":[1,144],"one":[2,156],"of":[3,29,75,99,123],"the":[4,27,73,120],"most":[5],"adopted":[6],"programming":[7],"models":[8],"for":[9,35,61,150,160],"large":[10,152,163],"clusters":[11],"and":[12,38,59,109,118],"grid":[13],"deployments.":[14],"However,":[15],"these":[16,62],"systems":[17],"often":[18],"suffer":[19],"from":[20,103,155],"network":[21],"or":[22,47],"node":[23],"failures.":[24],"This":[25],"raises":[26],"issue":[28],"selecting":[30],"a":[31,76,86,92,126,151],"fault":[32,81,135,157],"tolerance":[33],"approach":[34],"MPI.":[36],"Automatic":[37],"transparent":[39],"ones":[40],"are":[41,55],"based":[42],"on":[43,80,129],"either":[44],"coordinated":[45,100],"checkpointing":[46],"message":[48,87,94,146],"logging":[49,88,147],"associated":[50],"with":[51,125,162],"uncoordinated":[52],"checkpoint.":[53],"There":[54],"many":[56],"protocols,":[57],"implementations":[58],"optimizations":[60],"approaches":[63],"but":[64],"few":[65],"results":[66],"about":[67],"their":[68,130],"comparison.":[69],"Coordinated":[70],"checkpoint":[71,101,108],"has":[72],"advantage":[74],"very":[77],"low":[78],"overhead":[79],"free":[82],"executions.":[83],"In":[84,112],"contrary":[85],"protocol":[89],"systematically":[90],"adds":[91],"significant":[93],"transfer":[95],"penalty.":[96],"The":[97,137],"drawbacks":[98],"come":[102],"its":[104],"synchronization":[105],"cost":[106],"at":[107],"restart":[110],"times.":[111],"this":[113],"paper":[114],"we":[115],"implement,":[116],"evaluate":[117],"compare":[119],"two":[121],"kinds":[122],"protocols":[124],"special":[127],"emphasis":[128],"respective":[131],"performance":[132],"according":[133],"to":[134],"frequency.":[136],"main":[138],"conclusion":[139],"(under":[140],"our":[141],"experimental":[142],"conditions)":[143],"that":[145],"becomes":[148],"relevant":[149],"scale":[153],"cluster":[154],"every":[158],"hour":[159],"applications":[161],"dataset.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
