{"id":"https://openalex.org/W2001495258","doi":"https://doi.org/10.1177/1094342009106189","title":"Fault Tolerance in Petascale/ Exascale Systems: Current Knowledge, Challenges and Research Opportunities","display_name":"Fault Tolerance in Petascale/ Exascale Systems: Current Knowledge, Challenges and Research Opportunities","publication_year":2009,"publication_date":"2009-07-20","ids":{"openalex":"https://openalex.org/W2001495258","doi":"https://doi.org/10.1177/1094342009106189","mag":"2001495258"},"language":"en","primary_location":{"id":"doi:10.1177/1094342009106189","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342009106189","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/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I183874917","display_name":"Urbana University","ror":"https://ror.org/04kp3hw27","country_code":"US","type":"education","lineage":["https://openalex.org/I183874917"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["INRIA AND UIUC, THOMAS M. SIEBEL CENTER FOR COMPUTER\rSCIENCE, 201 N GOODWIN AVE, URBANA, IL 61801-2302, USA,","INRIA AND UIUC, THOMAS M. SIEBEL CENTER FOR COMPUTER#R#SCIENCE, 201 N GOODWIN AVE, URBANA, IL 61801-2302, USA,"],"affiliations":[{"raw_affiliation_string":"INRIA AND UIUC, THOMAS M. SIEBEL CENTER FOR COMPUTER\rSCIENCE, 201 N GOODWIN AVE, URBANA, IL 61801-2302, USA,","institution_ids":["https://openalex.org/I183874917"]},{"raw_affiliation_string":"INRIA AND UIUC, THOMAS M. SIEBEL CENTER FOR COMPUTER#R#SCIENCE, 201 N GOODWIN AVE, URBANA, IL 61801-2302, USA,","institution_ids":["https://openalex.org/I183874917"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046613458"],"corresponding_institution_ids":["https://openalex.org/I183874917"],"apc_list":null,"apc_paid":null,"fwci":11.6015,"has_fulltext":false,"cited_by_count":202,"citation_normalized_percentile":{"value":0.9867612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"23","issue":"3","first_page":"212","last_page":"226"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.978600025177002,"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/petascale-computing","display_name":"Petascale computing","score":0.9824051856994629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8708020448684692},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7512466907501221},{"id":"https://openalex.org/keywords/software-transactional-memory","display_name":"Software transactional memory","score":0.615064799785614},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.5787715911865234},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5699363350868225},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5004827976226807},{"id":"https://openalex.org/keywords/exascale-computing","display_name":"Exascale computing","score":0.4950098395347595},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4649082124233246},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.4498615562915802},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4162978529930115},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2342904806137085},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.22307509183883667},{"id":"https://openalex.org/keywords/transactional-memory","display_name":"Transactional memory","score":0.20578518509864807},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.09197327494621277},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0894019603729248}],"concepts":[{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.9824051856994629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8708020448684692},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7512466907501221},{"id":"https://openalex.org/C167149655","wikidata":"https://www.wikidata.org/wiki/Q1189004","display_name":"Software transactional memory","level":4,"score":0.615064799785614},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.5787715911865234},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5699363350868225},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5004827976226807},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.4950098395347595},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4649082124233246},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.4498615562915802},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4162978529930115},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2342904806137085},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.22307509183883667},{"id":"https://openalex.org/C134277064","wikidata":"https://www.wikidata.org/wiki/Q878206","display_name":"Transactional memory","level":3,"score":0.20578518509864807},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.09197327494621277},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0894019603729248},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342009106189","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342009106189","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W28511425","https://openalex.org/W169659540","https://openalex.org/W1493735863","https://openalex.org/W1585274809","https://openalex.org/W1847519410","https://openalex.org/W1969617086","https://openalex.org/W1987608073","https://openalex.org/W2083613288","https://openalex.org/W2089536264","https://openalex.org/W2100970777","https://openalex.org/W2105039796","https://openalex.org/W2107263349","https://openalex.org/W2109769503","https://openalex.org/W2111132249","https://openalex.org/W2123646449","https://openalex.org/W2131053137","https://openalex.org/W2139156547","https://openalex.org/W2146924779","https://openalex.org/W2156514327","https://openalex.org/W2158907675","https://openalex.org/W2171453084","https://openalex.org/W2296772319","https://openalex.org/W2731397968","https://openalex.org/W4252679991","https://openalex.org/W4301447929"],"related_works":["https://openalex.org/W3202772396","https://openalex.org/W2943694728","https://openalex.org/W2605376433","https://openalex.org/W3033495450","https://openalex.org/W2000112181","https://openalex.org/W3047227485","https://openalex.org/W2520782116","https://openalex.org/W2899269093","https://openalex.org/W2222431521","https://openalex.org/W2001495258"],"abstract_inverted_index":{"The":[0,133],"emergence":[1],"of":[2,8,35,41,72,80,87,99,135,177,206],"petascale":[3],"systems":[4,11,24],"and":[5,25,105,144,155,181,189],"the":[6,14,42,59,63,75,96,146,150,158,178,191,194,203],"promise":[7],"future":[9],"exascale":[10],"have":[12,68,198],"reinvigorated":[13],"community":[15,76,196],"interest":[16],"in":[17,22,53,152,170,208],"how":[18],"to":[19,199],"manage":[20],"failures":[21,151,207],"such":[23],"ensure":[26],"that":[27,193],"large":[28],"applications,":[29],"lasting":[30],"several":[31,46],"hours":[32],"or":[33,164],"tens":[34],"hours,":[36],"are":[37,138],"completed":[38],"successfully.":[39],"Most":[40],"existing":[43,89,147],"results":[44,148],"for":[45,109,161,167,201],"key":[47],"mechanisms":[48,67],"associated":[49,184],"with":[50,77,95],"fault":[51,121,168],"tolerance":[52,169],"high-performance":[54],"computing":[55],"(HPC)":[56],"platforms":[57],"follow":[58],"rollback\u2014recovery":[60],"approach.":[61],"Over":[62],"last":[64],"decade,":[65],"these":[66,171],"received":[69],"a":[70,107],"lot":[71],"attention":[73],"from":[74,115],"different":[78,116],"levels":[79],"success.":[81],"Unfortunately,":[82],"despite":[83],"their":[84,183],"high":[85],"degree":[86],"optimization,":[88],"approaches":[90,166],"do":[91],"not":[92],"fit":[93],"well":[94],"challenging":[97],"evolutions":[98],"large-scale":[100,153],"systems.":[101,210],"There":[102],"is":[103],"room":[104],"even":[106],"need":[108,160],"new":[110],"approaches.":[111],"Opportunities":[112],"may":[113],"come":[114],"origins:":[117],"diskless":[118],"checkpointing,":[119],"algorithmic-based":[120],"tolerance,":[122],"proactive":[123],"operation,":[124],"speculative":[125],"execution,":[126],"software":[127],"transactional":[128],"memory,":[129],"forward":[130],"recovery,":[131],"etc.":[132],"contributions":[134],"this":[136],"paper":[137],"as":[139],"follows:":[140],"(1)":[141],"we":[142,174,187],"summarize":[143],"analyze":[145,182],"concerning":[149],"computers":[154],"point":[156],"out":[157],"urgent":[159],"drastic":[162],"improvements":[163],"disruptive":[165],"systems;":[172],"(2)":[173],"sketch":[175],"most":[176],"known":[179],"opportunities":[180],"limitations;":[185],"(3)":[186],"extract":[188],"express":[190],"challenges":[192],"HPC":[195,209],"will":[197],"face":[200],"addressing":[202],"stringent":[204],"issue":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":24},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
