{"id":"https://openalex.org/W2160576878","doi":"https://doi.org/10.1109/ipdps.2004.1303242","title":"A hierarchical checkpointing protocol for parallel applications in cluster federations","display_name":"A hierarchical checkpointing protocol for parallel applications in cluster federations","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2160576878","doi":"https://doi.org/10.1109/ipdps.2004.1303242","mag":"2160576878"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2004.1303242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00000990","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011009650","display_name":"S\u00e9bastien Monnet","orcid":"https://orcid.org/0000-0002-6036-3060"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"S. Monnet","raw_affiliation_strings":["IRISA, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRISA, France","institution_ids":["https://openalex.org/I2802519937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067422926","display_name":"C. Morin","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Morin","raw_affiliation_strings":["IRISA/INRIA, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRISA/INRIA, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2802519937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113334910","display_name":"R. Badrinath","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Badrinath","raw_affiliation_strings":["Hewlett-Packard ISO, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard ISO, Bangalore, India","institution_ids":["https://openalex.org/I4210117576"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1608,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.47289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":1.0,"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":1.0,"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/T12288","display_name":"Optimization and Search Problems","score":0.9901000261306763,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9900000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8362491130828857},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.6492898464202881},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.6250144243240356},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5969905853271484},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5846116542816162},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5641556978225708},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5144743919372559},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49384528398513794},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.49027135968208313},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.47904765605926514},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4201871454715729},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35481375455856323},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08639290928840637},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06495800614356995},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05994522571563721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362491130828857},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.6492898464202881},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6250144243240356},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5969905853271484},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5846116542816162},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5641556978225708},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5144743919372559},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49384528398513794},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.49027135968208313},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.47904765605926514},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4201871454715729},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35481375455856323},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08639290928840637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06495800614356995},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05994522571563721},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ipdps.2004.1303242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:hdl:10068/46899","is_oa":false,"landing_page_url":"http://hdl.handle.net/10068/46899","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"R - Report"},{"id":"pmh:oai:HAL:inria-00000990v2","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00000990","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"9th IEEE Workshop on Fault-Tolerant Parallel, Distributed and Network-Centric Systems, Apr 2004, Santa Fe, New Mexico, Mexico. pp.211","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:inria-00071492v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00071492","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-5091, INRIA. 2004","raw_type":"info:eu-repo/semantics/report"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00000990v2","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00000990","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"9th IEEE Workshop on Fault-Tolerant Parallel, Distributed and Network-Centric Systems, Apr 2004, Santa Fe, New Mexico, Mexico. pp.211","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W176969775","https://openalex.org/W2100970777","https://openalex.org/W2105039796","https://openalex.org/W2118074288","https://openalex.org/W2120478980","https://openalex.org/W2124458074","https://openalex.org/W2126071114","https://openalex.org/W2136295287","https://openalex.org/W2160576878","https://openalex.org/W2811255748","https://openalex.org/W6607227249","https://openalex.org/W6675705929","https://openalex.org/W6752943859"],"related_works":["https://openalex.org/W2978729728","https://openalex.org/W4288966080","https://openalex.org/W1530347314","https://openalex.org/W2510374584","https://openalex.org/W2134852660","https://openalex.org/W2901069556","https://openalex.org/W1556686321","https://openalex.org/W2111353101","https://openalex.org/W2411226825","https://openalex.org/W2122963874"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"Code":[4],"coupling":[5,105],"applications":[6],"can":[7],"be":[8,15],"divided":[9],"into":[10],"communicating":[11],"modules,":[12],"that":[13,50,98],"may":[14],"executed":[16],"on":[17],"different":[18],"clusters":[19,57],"in":[20],"a":[21,25,30,37,41,46,52,59,71,93],"cluster":[22,26,72],"federation.":[23],"As":[24],"federation":[27,73],"comprises":[28],"of":[29,33,40,70,76],"large":[31],"number":[32,75],"nodes,":[34,77],"there":[35],"is":[36,101],"high":[38,78],"probability":[39],"node":[42],"failure.":[43],"We":[44],"propose":[45],"hierarchical":[47],"checkpointing":[48,54],"protocol":[49,65,100],"combines":[51],"synchronized":[53],"technique":[55,61],"inside":[56],"and":[58,80],"communication-induced":[60],"between":[62,85],"clusters.":[63],"This":[64],"fits":[66],"to":[67],"the":[68,99],"characteristics":[69],"(large":[74],"latency":[79],"low":[81],"bandwidth":[82],"networking":[83],"technologies":[84],"clusters).":[86],"A":[87],"preliminary":[88],"performance":[89],"evaluation":[90],"performed":[91],"using":[92],"discrete":[94],"event":[95],"simulator":[96],"shows":[97],"suitable":[102],"for":[103],"code":[104],"applications.":[106]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
