{"id":"https://openalex.org/W2095487435","doi":"https://doi.org/10.1145/1188455.1188587","title":"MPI tools and performance studies---Blocking vs. non-blocking coordinated checkpointing for large-scale fault tolerant MPI","display_name":"MPI tools and performance studies---Blocking vs. non-blocking coordinated checkpointing for large-scale fault tolerant MPI","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2095487435","doi":"https://doi.org/10.1145/1188455.1188587","mag":"2095487435"},"language":"en","primary_location":{"id":"doi:10.1145/1188455.1188587","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1188455.1188587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing - SC '06","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5001362684","display_name":"Camille Coti","orcid":"https://orcid.org/0000-0002-1224-7786"},"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":"Camille Coti","raw_affiliation_strings":["Universit\u00e9, Paris-XI, France","Lab. de Recherche en Informatique, Univ. Paris-XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9, Paris-XI, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Recherche en Informatique, Univ. Paris-XI","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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Herault","raw_affiliation_strings":["Universit\u00e9, Paris-XI, France","Lab. de Recherche en Informatique, Univ. Paris-XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9, Paris-XI, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Recherche en Informatique, Univ. Paris-XI","institution_ids":["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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Lemarinier","raw_affiliation_strings":["Universit\u00e9, Paris-XI, France","Lab. de Recherche en Informatique, Univ. Paris-XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9, Paris-XI, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Recherche en Informatique, Univ. Paris-XI","institution_ids":["https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038061684","display_name":"Laurence Pilard","orcid":"https://orcid.org/0000-0002-1104-8216"},"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":"Laurence Pilard","raw_affiliation_strings":["Universit\u00e9, Paris-XI, France","Lab. de Recherche en Informatique, Univ. Paris-XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9, Paris-XI, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Recherche en Informatique, Univ. Paris-XI","institution_ids":["https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051021449","display_name":"Ala Rezmerita","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":"Ala Rezmerita","raw_affiliation_strings":["Universit\u00e9, Paris-XI, France","Lab. de Recherche en Informatique, Univ. Paris-XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9, Paris-XI, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Recherche en Informatique, Univ. Paris-XI","institution_ids":["https://openalex.org/I4210144804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113568325","display_name":"Eric Rodriguez","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":"Eric Rodriguez","raw_affiliation_strings":["Universit\u00e9, Paris-XI, France","Lab. de Recherche en Informatique, Univ. Paris-XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9, Paris-XI, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Recherche en Informatique, Univ. Paris-XI","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/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":"Franck Cappello","raw_affiliation_strings":["Universit\u00e9, Paris-XI, France","Lab. de Recherche en Informatique, Univ. Paris-XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9, Paris-XI, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Recherche en Informatique, Univ. Paris-XI","institution_ids":["https://openalex.org/I4210144804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144804"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"127"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9959999918937683,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9909999966621399,"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":0.8902419805526733},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8715182542800903},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8455952405929565},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7741851806640625},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6936416029930115},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5566130876541138},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5199397802352905},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5091301798820496},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.4344971477985382},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3189525306224823},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16791224479675293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8902419805526733},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8715182542800903},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8455952405929565},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7741851806640625},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6936416029930115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5566130876541138},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5199397802352905},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5091301798820496},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.4344971477985382},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3189525306224823},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16791224479675293}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1188455.1188587","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1188455.1188587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM/IEEE conference on Supercomputing - SC '06","raw_type":"proceedings-article"},{"id":"pmh:oai:espace2.etsmtl.ca:26388","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/26388/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Compte rendu de conf\u00e9rence"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W16311991","https://openalex.org/W1510894298","https://openalex.org/W1527754331","https://openalex.org/W1581312614","https://openalex.org/W1589918049","https://openalex.org/W1825216778","https://openalex.org/W1862835629","https://openalex.org/W1923741182","https://openalex.org/W1997021720","https://openalex.org/W2028133900","https://openalex.org/W2040932846","https://openalex.org/W2045879521","https://openalex.org/W2052915895","https://openalex.org/W2081612620","https://openalex.org/W2098415863","https://openalex.org/W2100970777","https://openalex.org/W2105039796","https://openalex.org/W2114035455","https://openalex.org/W2121437290","https://openalex.org/W2131053137","https://openalex.org/W2133201251","https://openalex.org/W3035757797","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2971479921","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W2101077206","https://openalex.org/W2157727563","https://openalex.org/W2470343202","https://openalex.org/W1978919910","https://openalex.org/W2082659044","https://openalex.org/W1488443159"],"abstract_inverted_index":{"A":[0],"long-term":[1],"trend":[2],"in":[3,12,38],"high-performance":[4],"computing":[5,14],"is":[6,78,115],"the":[7,31,45,83,118,134,138,146],"increasing":[8],"number":[9],"of":[10,34,47,61,88,112,128],"nodes":[11],"parallel":[13,148],"platforms,":[15],"which":[16],"entails":[17],"a":[18,59,126],"higher":[19],"failure":[20],"probability.":[21],"Fault":[22],"tolerant":[23,40,50,63],"programming":[24],"environments":[25,140],"should":[26],"be":[27],"used":[28],"to":[29,44,116],"guarantee":[30],"safe":[32],"execution":[33],"critical":[35],"applications.":[36],"Research":[37],"fault":[39,49,62],"MPI":[41,51],"has":[42],"led":[43],"development":[46],"several":[48],"environments.":[52],"Different":[53],"approaches":[54,124,136],"are":[55],"being":[56],"proposed":[57],"using":[58,145],"variety":[60],"message":[64,72],"passing":[65],"protocols":[66],"based":[67],"on":[68],"coordinated":[69,80,89],"checkpointing":[70,90],"or":[71],"logging.":[73],"The":[74,110],"most":[75],"popular":[76],"approach":[77],"with":[79],"checkpointing.":[81],"In":[82],"literature,":[84],"two":[85,123,135],"different":[86],"concepts":[87],"have":[91,99,132],"been":[92,101],"proposed:":[93],"blocking":[94],"and":[95,104,125,141],"nonblocking.":[96],"However":[97],"they":[98],"never":[100],"compared":[102],"quantitatively":[103],"their":[105,129,143],"respective":[106],"scalability":[107],"remains":[108],"unknown.":[109],"contribution":[111],"this":[113],"paper":[114],"provide":[117],"first":[119],"comparison":[120],"between":[121],"these":[122],"study":[127],"scalability.":[130],"We":[131],"implemented":[133],"within":[137],"MPICH":[139],"evaluate":[142],"performance":[144],"NAS":[147],"benchmarks.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":11}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2016-06-24T00:00:00"}