{"id":"https://openalex.org/W1527754331","doi":"https://doi.org/10.1109/clustr.2004.1392609","title":"Improved message logging versus improved coordinated checkpointing for fault tolerant MPI","display_name":"Improved message logging versus improved coordinated checkpointing for fault tolerant MPI","publication_year":2005,"publication_date":"2005-04-06","ids":{"openalex":"https://openalex.org/W1527754331","doi":"https://doi.org/10.1109/clustr.2004.1392609","mag":"1527754331"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2004.1392609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2004.1392609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Cluster Computing (IEEE Cat. No.04EX935)","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/A5088833068","display_name":"Pierre Lemarinier","orcid":"https://orcid.org/0000-0002-6353-4136"},"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":true,"raw_author_name":"P. Lemarinier","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France","LRI, Univ. 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"]},{"raw_affiliation_string":"LRI, Univ. de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054873210","display_name":"Aur\u00e9lien Bouteiller","orcid":"https://orcid.org/0000-0001-5108-509X"},"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":false,"raw_author_name":"A. Bouteiller","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France","LRI, Univ. 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"]},{"raw_affiliation_string":"LRI, Univ. de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008117654","display_name":"Thomas H\u00e9rault","orcid":"https://orcid.org/0000-0001-6756-6189"},"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":"T. Herault","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France","LRI, Univ. 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"]},{"raw_affiliation_string":"LRI, Univ. de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051888885","display_name":"G\u00e9raud Krawezik","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":false,"raw_author_name":"G. Krawezik","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France","LRI, Univ. 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"]},{"raw_affiliation_string":"LRI, Univ. de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I4210144804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"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"]},{"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":false,"raw_author_name":"F. Cappello","raw_affiliation_strings":["LRI, Universit\u00e9 de Paris Sud, Orsay, France","LRI, Univ. 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"]},{"raw_affiliation_string":"LRI, Univ. de Paris Sud, Orsay, France","institution_ids":["https://openalex.org/I4210144804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088833068"],"corresponding_institution_ids":["https://openalex.org/I102197404","https://openalex.org/I204730241","https://openalex.org/I4210144804"],"apc_list":null,"apc_paid":null,"fwci":4.1059,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.94391188,"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":"115","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9957000017166138,"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"}},{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8622498512268066},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7023357152938843},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6212211847305298},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.617733359336853},{"id":"https://openalex.org/keywords/logging","display_name":"Logging","score":0.5076688528060913},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.49017056822776794},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.47552087903022766},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.43809816241264343},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4364948868751526},{"id":"https://openalex.org/keywords/communication-source","display_name":"Communication source","score":0.4169943928718567},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.380983829498291},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3468475937843323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622498512268066},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7023357152938843},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6212211847305298},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.617733359336853},{"id":"https://openalex.org/C125620115","wikidata":"https://www.wikidata.org/wiki/Q845249","display_name":"Logging","level":2,"score":0.5076688528060913},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.49017056822776794},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.47552087903022766},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.43809816241264343},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4364948868751526},{"id":"https://openalex.org/C198104137","wikidata":"https://www.wikidata.org/wiki/Q974688","display_name":"Communication source","level":2,"score":0.4169943928718567},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.380983829498291},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3468475937843323},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/clustr.2004.1392609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2004.1392609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Cluster Computing (IEEE Cat. No.04EX935)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.99.8108","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.8108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mpich-v.lri.fr/papers/Cluster2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W4871647","https://openalex.org/W307918303","https://openalex.org/W1510894298","https://openalex.org/W1576341769","https://openalex.org/W1581312614","https://openalex.org/W1589918049","https://openalex.org/W1848988118","https://openalex.org/W1903306973","https://openalex.org/W1954990415","https://openalex.org/W2045879521","https://openalex.org/W2052915895","https://openalex.org/W2081612620","https://openalex.org/W2100970777","https://openalex.org/W2105039796","https://openalex.org/W2112121929","https://openalex.org/W2113824616","https://openalex.org/W2125776594","https://openalex.org/W2131053137","https://openalex.org/W2134533588","https://openalex.org/W2134693673","https://openalex.org/W2142234387","https://openalex.org/W2160123909","https://openalex.org/W2170163131","https://openalex.org/W4285719527","https://openalex.org/W6600210833","https://openalex.org/W6630659090","https://openalex.org/W6634580932","https://openalex.org/W6634607017","https://openalex.org/W6639932168","https://openalex.org/W6662107652","https://openalex.org/W6675705929"],"related_works":["https://openalex.org/W2993833576","https://openalex.org/W2776877297","https://openalex.org/W3125718803","https://openalex.org/W2127920220","https://openalex.org/W3119288169","https://openalex.org/W2945097178","https://openalex.org/W4388741024","https://openalex.org/W3122953031","https://openalex.org/W2082659044","https://openalex.org/W2811255748"],"abstract_inverted_index":{"Fault":[0],"tolerance":[1],"is":[2,205],"a":[3,41,46,95,101,110,189,196],"very":[4],"important":[5],"concern":[6],"for":[7,26],"critical":[8],"high":[9,42,96,191,197],"performance":[10,35,73,103,165,192],"applications":[11],"using":[12,184],"the":[13,37,53,67,72,83,114,134,142,150,156,167,173,179,185,221],"MPI":[14],"library.":[15],"Several":[16],"protocols":[17,130,151,177],"provide":[18],"automatic":[19],"and":[20,24,36,62,70,127,141,152,170,213,219],"transparent":[21],"fault":[22,43,159],"detection":[23],"recovery":[25],"message":[27,60,80,106,125,139,175,210],"passing":[28],"systems":[29],"with":[30,195],"different":[31],"impact":[32],"on":[33,113,188],"application":[34],"capacity":[38],"to":[39,86,109,121],"tolerate":[40],"rate.":[44],"In":[45],"recent":[47],"paper,":[48],"we":[49,171],"have":[50],"demonstrated":[51],"that":[52],"main":[54],"differences":[55],"between":[56,223],"pessimistic":[57,138],"sender":[58],"based":[59],"logging":[61,81,107,126,140,176,211],"coordinated":[63,98,128,146,181,216],"checkpointing":[64,99,182,217],"are:":[65],"1)":[66],"communication":[68],"latency":[69,135],"2)":[71],"penalty":[74,104],"in":[75],"case":[76],"of":[77,124,137,145,202],"faults.":[78],"Pessimistic":[79],"increases":[82],"latency,":[84],"due":[85,108],"additional":[87],"blocking":[88],"control":[89],"messages.":[90],"When":[91],"faults":[92],"occur":[93],"at":[94],"rate,":[97],"implies":[100],"higher":[102,111],"than":[105],"stress":[112,144],"checkpoint":[115,129],"server.":[116],"We":[117,148,162],"extend":[118],"this":[119],"study":[120],"improved":[122,180,215],"versions":[123,169],"which":[131],"respectively":[132],"reduces":[133],"overhead":[136],"server":[143],"checkpoint.":[147],"detail":[149],"their":[153,164],"implementation":[154],"into":[155],"new":[157],"MPICH-V":[158],"tolerant":[160],"framework.":[161],"compare":[163,172],"against":[166,178],"previous":[168],"novel":[174],"one":[183],"NAS":[186],"benchmark":[187],"typical":[190],"cluster":[193],"equipped":[194],"speed":[198],"network.":[199],"The":[200],"contribution":[201],"This":[203],"work":[204],"twofold:":[206],"a)":[207],"an":[208,214],"original":[209],"protocol":[212,218],"b)":[220],"comparison":[222],"them.":[224]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
