{"id":"https://openalex.org/W2128577831","doi":"https://doi.org/10.1177/1094342013488238","title":"Post-failure recovery of MPI communication capability","display_name":"Post-failure recovery of MPI communication capability","publication_year":2013,"publication_date":"2013-06-03","ids":{"openalex":"https://openalex.org/W2128577831","doi":"https://doi.org/10.1177/1094342013488238","mag":"2128577831"},"language":"en","primary_location":{"id":"doi:10.1177/1094342013488238","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013488238","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","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/A5031869683","display_name":"Wesley Bland","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wesley Bland","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]","institution_ids":["https://openalex.org/I75027704"]}]},{"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/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aurelien Bouteiller","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]","institution_ids":["https://openalex.org/I75027704"]}]},{"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/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Herault","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010055736","display_name":"George Bosilca","orcid":"https://orcid.org/0000-0003-2411-8495"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"George Bosilca","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"[Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA]","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010055736"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":15.9354,"has_fulltext":false,"cited_by_count":191,"citation_normalized_percentile":{"value":0.99094909,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"27","issue":"3","first_page":"244","last_page":"254"},"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":0.9954000115394592,"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":0.9932000041007996,"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":0.8582682609558105},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6365624666213989},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6228693723678589},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.601314902305603},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.583512544631958},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5654058456420898},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5533018708229065},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5035757422447205},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.49668294191360474},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4601718783378601},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41159072518348694},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.29164794087409973},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2416968047618866},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09446638822555542},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07787752151489258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582682609558105},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6365624666213989},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6228693723678589},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.601314902305603},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.583512544631958},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5654058456420898},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5533018708229065},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5035757422447205},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.49668294191360474},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4601718783378601},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41159072518348694},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29164794087409973},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2416968047618866},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09446638822555542},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07787752151489258},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342013488238","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013488238","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W23377417","https://openalex.org/W163470805","https://openalex.org/W170768260","https://openalex.org/W1482022028","https://openalex.org/W1493735863","https://openalex.org/W1575350781","https://openalex.org/W1576341769","https://openalex.org/W1767718504","https://openalex.org/W1939822385","https://openalex.org/W1997021720","https://openalex.org/W2001495258","https://openalex.org/W2063924830","https://openalex.org/W2082659044","https://openalex.org/W2089536264","https://openalex.org/W2096327573","https://openalex.org/W2096504919","https://openalex.org/W2100970777","https://openalex.org/W2105524676","https://openalex.org/W2123500455","https://openalex.org/W2123646449","https://openalex.org/W2126163873","https://openalex.org/W2131053137","https://openalex.org/W2133943294","https://openalex.org/W2134533588","https://openalex.org/W2138544153","https://openalex.org/W2150798641","https://openalex.org/W2155662278","https://openalex.org/W2165009364","https://openalex.org/W2731397968","https://openalex.org/W2988677206"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W2378910916","https://openalex.org/W4386915331","https://openalex.org/W2116006827","https://openalex.org/W2086666199","https://openalex.org/W1511717675","https://openalex.org/W2361929291","https://openalex.org/W1493716264","https://openalex.org/W2082659044"],"abstract_inverted_index":{"As":[0],"supercomputers":[1],"are":[2,102],"entering":[3],"an":[4],"era":[5],"of":[6,12,25,71,87,116,125,140],"massive":[7],"parallelism":[8],"where":[9],"the":[10,16,23,34,44,55,84,99,114,118,121,126,137],"frequency":[11],"faults":[13],"is":[14,133],"increasing,":[15],"MPI":[17,28,54,74,91,112],"Standard":[18],"remains":[19],"distressingly":[20],"vague":[21],"on":[22,27],"consequence":[24],"failures":[26,59],"communications.":[29],"Advanced":[30],"fault-tolerance":[31],"techniques":[32,132],"have":[33,93],"potential":[35],"to":[36,57,73,79,89,145],"prevent":[37],"full-scale":[38],"application":[39],"restart":[40],"and":[41,60,120],"therefore":[42],"lower":[43],"cost":[45],"incurred":[46],"for":[47,128],"each":[48],"failure,":[49],"but":[50],"they":[51],"demand":[52],"from":[53,113],"capability":[56],"detect":[58],"resume":[61],"communications":[62],"afterward.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"present":[68],"a":[69,106],"set":[70],"extensions":[72],"that":[75,108],"allow":[76],"communication":[77],"capabilities":[78],"be":[80],"restored,":[81],"while":[82],"maintaining":[83],"extreme":[85],"level":[86],"performance":[88],"which":[90],"users":[92],"become":[94],"accustomed.":[95],"The":[96,123],"motivation":[97],"behind":[98],"design":[100],"choices":[101],"weighted":[103],"against":[104],"alternatives,":[105],"task":[107],"requires":[109],"simultaneously":[110],"considering":[111],"viewpoint":[115],"both":[117],"user":[119],"implementor.":[122],"usability":[124],"interfaces":[127],"expressing":[129],"advanced":[130],"recovery":[131],"then":[134],"discussed,":[135],"including":[136],"difficult":[138],"issue":[139],"enabling":[141],"separate":[142],"software":[143],"layers":[144],"coordinate":[146],"their":[147],"recovery.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}