{"id":"https://openalex.org/W2157157670","doi":"https://doi.org/10.1093/comjnl/bxs158","title":"Failure Avoidance in MPI Applications Using an Application-Level Approach","display_name":"Failure Avoidance in MPI Applications Using an Application-Level Approach","publication_year":2012,"publication_date":"2012-12-18","ids":{"openalex":"https://openalex.org/W2157157670","doi":"https://doi.org/10.1093/comjnl/bxs158","mag":"2157157670"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxs158","is_oa":true,"landing_page_url":"https://doi.org/10.1093/comjnl/bxs158","pdf_url":"https://academic.oup.com/comjnl/article-pdf/57/1/100/1141882/bxs158.pdf","source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/comjnl/article-pdf/57/1/100/1141882/bxs158.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016371856","display_name":"Iv\u00e1n Cores","orcid":"https://orcid.org/0000-0003-3380-2459"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"I. Cores","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026273204","display_name":"Gabriel Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-0338-3655"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"G. Rodriguez","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076637748","display_name":"Patricia Gonz\u00e1lez","orcid":"https://orcid.org/0000-0003-0378-9222"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"P. Gonzalez","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021488012","display_name":"Mar\u00eda J. Mart\u00edn","orcid":"https://orcid.org/0000-0002-9153-0909"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"M. J. Martin","raw_affiliation_strings":["Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Architecture Group, University of A Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016371856"],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":1.1263,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81218754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"57","issue":"1","first_page":"100","last_page":"114"},"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":0.9980000257492065,"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":0.9976999759674072,"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/architecture","display_name":"Architecture","score":0.780813455581665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4206656217575073},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.3919258415699005},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.3237687945365906},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.26311320066452026},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.20844754576683044}],"concepts":[{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.780813455581665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4206656217575073},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.3919258415699005},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.3237687945365906},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.26311320066452026},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.20844754576683044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxs158","is_oa":true,"landing_page_url":"https://doi.org/10.1093/comjnl/bxs158","pdf_url":"https://academic.oup.com/comjnl/article-pdf/57/1/100/1141882/bxs158.pdf","source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1093/comjnl/bxs158","is_oa":true,"landing_page_url":"https://doi.org/10.1093/comjnl/bxs158","pdf_url":"https://academic.oup.com/comjnl/article-pdf/57/1/100/1141882/bxs158.pdf","source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2157157670.pdf","grobid_xml":"https://content.openalex.org/works/W2157157670.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W68307295","https://openalex.org/W1493735863","https://openalex.org/W1510894298","https://openalex.org/W1996213431","https://openalex.org/W2004885674","https://openalex.org/W2016411419","https://openalex.org/W2032858539","https://openalex.org/W2036741878","https://openalex.org/W2047535713","https://openalex.org/W2053691501","https://openalex.org/W2078548322","https://openalex.org/W2081413727","https://openalex.org/W2094924503","https://openalex.org/W2096611465","https://openalex.org/W2098272924","https://openalex.org/W2100970777","https://openalex.org/W2103849716","https://openalex.org/W2107303919","https://openalex.org/W2112310547","https://openalex.org/W2112748121","https://openalex.org/W2113169534","https://openalex.org/W2119018856","https://openalex.org/W2125693462","https://openalex.org/W2131726714","https://openalex.org/W2132462387","https://openalex.org/W2133789477","https://openalex.org/W2134366067","https://openalex.org/W2135895123","https://openalex.org/W2141826252","https://openalex.org/W2152419477","https://openalex.org/W2155043308","https://openalex.org/W2155662278","https://openalex.org/W2161551433","https://openalex.org/W2163197638","https://openalex.org/W2164463086","https://openalex.org/W2170500888","https://openalex.org/W2526559026","https://openalex.org/W4206909927","https://openalex.org/W4237816542","https://openalex.org/W4239407309","https://openalex.org/W4244704438"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W93312527","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Execution":[0],"times":[1],"of":[2,45,70,83,91,112,150,176,179,199],"large-scale":[3],"computational":[4],"science":[5],"and":[6,40,182,203,207],"engineering":[7],"parallel":[8,56,72],"applications":[9,26],"are":[10,98,107,138],"usually":[11],"longer":[12],"than":[13],"the":[14,25,46,71,75,81,89,110,113,144,151,161,177,193,197],"mean-time-between-failures.":[15],"For":[16],"this":[17,120],"reason,":[18],"hardware":[19,84],"failures":[20,85,106,137],"must":[21],"be":[22],"tolerated":[23],"by":[24,174],"to":[27,50,55,88,127,142,165,185,196],"ensure":[28],"that":[29],"not":[30,212],"all":[31],"computation":[32],"done":[33],"is":[34,43,211],"lost":[35],"on":[36],"machine":[37],"failures.":[38],"Checkpointing":[39],"rollback":[41],"recovery":[42],"one":[44],"most":[47,63],"popular":[48],"techniques":[49],"provide":[51],"fault":[52],"tolerance":[53],"support":[54],"applications.":[57],"However,":[58],"when":[59,104,135],"a":[60,67,101,180,187,200,204,215],"failure":[61],"occurs,":[62],"checkpointing":[64,125],"mechanisms":[65],"require":[66],"complete":[68],"restart":[69,111,143],"application":[73],"from":[74],"last":[76],"checkpoint.":[77],"New":[78],"advances":[79],"in":[80,100,119,157],"prediction":[82],"have":[86],"led":[87],"development":[90],"proactive":[92],"process":[93],"migration":[94,172],"approaches,":[95],"where":[96],"tasks":[97],"migrated":[99],"preventive":[102],"way":[103],"node":[105],"anticipated,":[108],"avoiding":[109,160],"whole":[114],"application.":[115,146],"The":[116,147],"work":[117],"presented":[118],"paper":[121],"extends":[122],"an":[123],"application-level":[124],"framework":[126],"proactively":[128],"migrate":[129],"message":[130],"passing":[131],"interface":[132],"(MPI)":[133],"processes":[134],"impending":[136],"notified,":[139],"without":[140],"having":[141],"entire":[145],"main":[148],"features":[149],"proposed":[152],"solution":[153],"are:":[154],"low":[155,169],"overhead":[156,170],"failure-free":[158],"executions,":[159],"checkpoint":[162],"dumping":[163],"associated":[164],"rolling":[166],"back":[167],"strategies;":[168],"at":[171],"time,":[173],"means":[175],"design":[178],"light":[181],"asynchronous":[183],"protocol":[184],"achieve":[186],"consistent":[188],"global":[189],"state;":[190],"transparency":[191],"for":[192],"user,":[194],"thanks":[195],"use":[198],"compiler":[201],"tool":[202],"runtime":[205],"library":[206],"portability,":[208],"as":[209],"it":[210],"locked":[213],"into":[214],"particular":[216],"architecture,":[217],"operating":[218],"system":[219],"or":[220],"MPI":[221],"implementation.":[222]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
