{"id":"https://openalex.org/W2170454619","doi":"https://doi.org/10.1177/1094342006067469","title":"MPICH-V Project: A Multiprotocol Automatic Fault-Tolerant MPI","display_name":"MPICH-V Project: A Multiprotocol Automatic Fault-Tolerant MPI","publication_year":2006,"publication_date":"2006-08-01","ids":{"openalex":"https://openalex.org/W2170454619","doi":"https://doi.org/10.1177/1094342006067469","mag":"2170454619"},"language":"en","primary_location":{"id":"doi:10.1177/1094342006067469","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342006067469","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5054873210","display_name":"Aur\u00e9lien Bouteiller","orcid":"https://orcid.org/0000-0001-5108-509X"},"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/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/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"A. Bouteiller","raw_affiliation_strings":["INRIA/LRI, Universit\u00e9 Paris-Sud, Orsay, France"],"affiliations":[{"raw_affiliation_string":"INRIA/LRI, Universit\u00e9 Paris-Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1326498283","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Herault","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051888885","display_name":"G\u00e9raud Krawezik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G. Krawezik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088833068","display_name":"Pierre Lemarinier","orcid":"https://orcid.org/0000-0002-6353-4136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Lemarinier","raw_affiliation_strings":[],"affiliations":[]},{"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"]},{"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/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F. Cappello","raw_affiliation_strings":["INRIA/LRI, Universit\u00e9 Paris-Sud, Orsay, France"],"affiliations":[{"raw_affiliation_string":"INRIA/LRI, Universit\u00e9 Paris-Sud, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1326498283","https://openalex.org/I4210144804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054873210"],"corresponding_institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1326498283","https://openalex.org/I4210144804"],"apc_list":null,"apc_paid":null,"fwci":12.9303,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.98852757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"20","issue":"3","first_page":"319","last_page":"333"},"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":0.998199999332428,"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":0.9980999827384949,"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":0.8594355583190918},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7896892428398132},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.649029016494751},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.597088098526001},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.48862820863723755},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.46095848083496094},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45089486241340637},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.43878427147865295},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32607191801071167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8594355583190918},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7896892428398132},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.649029016494751},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.597088098526001},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.48862820863723755},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.46095848083496094},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45089486241340637},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.43878427147865295},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32607191801071167},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":3,"locations":[{"id":"doi:10.1177/1094342006067469","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342006067469","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.614","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utk.edu/~lemarini/papers/multi.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00688637v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00688637","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of High Performance Computing Applications, 2006, 20 (3), pp.319-333. &#x27E8;10.1177/1094342006067469&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W633893551","https://openalex.org/W1506585574","https://openalex.org/W1510894298","https://openalex.org/W1527754331","https://openalex.org/W1576341769","https://openalex.org/W1581312614","https://openalex.org/W1582282055","https://openalex.org/W1589918049","https://openalex.org/W1630105971","https://openalex.org/W1848988118","https://openalex.org/W1903306973","https://openalex.org/W1911403303","https://openalex.org/W1915893077","https://openalex.org/W1923741182","https://openalex.org/W1954990415","https://openalex.org/W2013639878","https://openalex.org/W2017838136","https://openalex.org/W2045879521","https://openalex.org/W2052915895","https://openalex.org/W2081413727","https://openalex.org/W2081612620","https://openalex.org/W2082659044","https://openalex.org/W2100970777","https://openalex.org/W2105039796","https://openalex.org/W2112121929","https://openalex.org/W2123669573","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/W2163755682","https://openalex.org/W2170163131","https://openalex.org/W2171453084","https://openalex.org/W2171711727","https://openalex.org/W4242865030","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W2794038527","https://openalex.org/W2151092287","https://openalex.org/W2523801036","https://openalex.org/W4255172949"],"abstract_inverted_index":{"High":[0],"performance":[1,112],"computing":[2],"platforms":[3],"such":[4],"as":[5],"Clusters,":[6],"Grid":[7],"and":[8,14,49,71,119],"Desktop":[9],"Grids":[10],"are":[11],"becoming":[12],"larger":[13],"subject":[15],"to":[16,101],"more":[17],"frequent":[18],"failures.":[19],"MPI":[20,56,146],"is":[21],"one":[22],"of":[23,68,95,113,145],"the":[24,37,66,72,111,123,135],"most":[25],"used":[26],"message":[27,107],"passing":[28],"libraries":[29],"in":[30,82,140],"HPC":[31],"applications.":[32,57,147],"These":[33],"two":[34],"trends":[35],"raise":[36],"need":[38],"for":[39,55,87],"fault-tolerant":[40,53,79,88,142],"MPI.":[41],"The":[42],"MPICH-V":[43],"project":[44],"focuses":[45],"on":[46,116],"designing,":[47],"implementing":[48],"comparing":[50],"several":[51],"automatic":[52],"protocols":[54,80,115],"We":[58,75,109],"present":[59,77],"an":[60,127],"extensive":[61],"related":[62],"work":[63],"section":[64],"highlighting":[65],"originality":[67],"our":[69],"approach":[70],"proposed":[73],"protocols.":[74],"then":[76],"four":[78],"implemented":[81],"a":[83,92,117],"new":[84],"generic":[85],"framework":[86],"protocol":[89,143],"comparison,":[90],"covering":[91],"large":[93],"spectrum":[94],"known":[96],"approaches":[97],"from":[98,138],"coordinated":[99],"checkpoint,":[100],"uncoordinated":[102],"checkpoint":[103],"associated":[104],"with":[105,122],"causal":[106],"logging.":[108],"measure":[110],"these":[114],"micro-benchmark":[118],"compare":[120],"them":[121],"NAS":[124],"benchmark,":[125],"using":[126],"original":[128],"fault":[129],"tolerance":[130],"test.":[131],"Finally,":[132],"we":[133],"outline":[134],"lessons":[136],"learned":[137],"this":[139],"depth":[141],"comparison":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
