{"id":"https://openalex.org/W4415024298","doi":"https://doi.org/10.1177/10943420251379278","title":"Fixed-work versus fixed-time checkpointing on large-scale failure-prone platforms","display_name":"Fixed-work versus fixed-time checkpointing on large-scale failure-prone platforms","publication_year":2025,"publication_date":"2025-10-10","ids":{"openalex":"https://openalex.org/W4415024298","doi":"https://doi.org/10.1177/10943420251379278"},"language":"en","primary_location":{"id":"doi:10.1177/10943420251379278","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420251379278","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":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-05232847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092932387","display_name":"Quentin Barbut","orcid":"https://orcid.org/0009-0007-9161-0101"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Quentin Barbut","raw_affiliation_strings":["Laboratoire LIP & Inria","ENS Lyon, Laboratoire LIP & Inria, Lyon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire LIP & Inria","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"ENS Lyon, Laboratoire LIP & Inria, Lyon, France","institution_ids":["https://openalex.org/I113428412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008190319","display_name":"Lucas Perotin","orcid":"https://orcid.org/0000-0002-9739-7440"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucas Perotin","raw_affiliation_strings":["Vanderbilt University","Vanderbilt University, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037778045","display_name":"Anne Beno\u00eet","orcid":"https://orcid.org/0000-0003-2910-3540"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I185839726","display_name":"Institut Universitaire de France","ror":"https://ror.org/055khg266","country_code":"FR","type":"education","lineage":["https://openalex.org/I185839726"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anne Benoit","raw_affiliation_strings":["Institut Universitaire de France","Laboratoire LIP & Inria","ENS Lyon, Laboratoire LIP & Inria, Lyon, France","Institut Universitaire de France, France"],"affiliations":[{"raw_affiliation_string":"Institut Universitaire de France","institution_ids":["https://openalex.org/I185839726"]},{"raw_affiliation_string":"Laboratoire LIP & Inria","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"ENS Lyon, Laboratoire LIP & Inria, Lyon, France","institution_ids":["https://openalex.org/I113428412"]},{"raw_affiliation_string":"Institut Universitaire de France, France","institution_ids":["https://openalex.org/I185839726"]}]},{"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/I2799495847","display_name":"University of Tennessee System","ror":"https://ror.org/00xzqjh13","country_code":"US","type":"education","lineage":["https://openalex.org/I2799495847"]},{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"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":["University Tennessee Knoxville","University Tennessee Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"University Tennessee Knoxville","institution_ids":["https://openalex.org/I2799495847"]},{"raw_affiliation_string":"University Tennessee Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704","https://openalex.org/I2802706902"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001838181","display_name":"Yves Robert","orcid":"https://orcid.org/0000-0003-2361-055X"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Yves Robert","raw_affiliation_strings":["Laboratoire LIP & Inria","ENS Lyon, Laboratoire LIP & Inria, Lyon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire LIP & Inria","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"ENS Lyon, Laboratoire LIP & Inria, Lyon, France","institution_ids":["https://openalex.org/I113428412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086100728","display_name":"Fr\u00e9d\u00e9ric Vivien","orcid":"https://orcid.org/0000-0002-0663-6152"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric Vivien","raw_affiliation_strings":["Laboratoire LIP & Inria","ENS Lyon, Laboratoire LIP & Inria, Lyon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire LIP & Inria","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"ENS Lyon, Laboratoire LIP & Inria, Lyon, France","institution_ids":["https://openalex.org/I113428412"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001838181"],"corresponding_institution_ids":["https://openalex.org/I113428412","https://openalex.org/I1326498283"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33356295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"96","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":0.9998999834060669,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9955000281333923,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9866999983787537,"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/fraction","display_name":"Fraction (chemistry)","score":0.5404000282287598},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5371999740600586},{"id":"https://openalex.org/keywords/reservation","display_name":"Reservation","score":0.5090000033378601},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5011000037193298},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4027000069618225},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.3840000033378601},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700000166893005},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5404000282287598},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C2777632111","wikidata":"https://www.wikidata.org/wiki/Q1937518","display_name":"Reservation","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2777145635","wikidata":"https://www.wikidata.org/wiki/Q515636","display_name":"FIFO (computing and electronics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C141042865","wikidata":"https://www.wikidata.org/wiki/Q200125","display_name":"Expected value","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/10943420251379278","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420251379278","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:HAL:hal-05232847v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05232847","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of High Performance Computing Applications, 2025, 40 (1), pp.96-114. ⟨10.1177/10943420251379278⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05232847v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05232847","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of High Performance Computing Applications, 2025, 40 (1), pp.96-114. ⟨10.1177/10943420251379278⟩","raw_type":"Journal articles"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1524054144","https://openalex.org/W1584278023","https://openalex.org/W2031260715","https://openalex.org/W2033656974","https://openalex.org/W2063924830","https://openalex.org/W2064388050","https://openalex.org/W2089536264","https://openalex.org/W2132860930","https://openalex.org/W2133046454","https://openalex.org/W2296772319","https://openalex.org/W3048433980","https://openalex.org/W4205724691","https://openalex.org/W4386943870","https://openalex.org/W4387001714","https://openalex.org/W4401350386","https://openalex.org/W4404789056","https://openalex.org/W4410605732"],"related_works":[],"abstract_inverted_index":{"Consider":[0],"a":[1,8,27,33,84,93,102,130,143,169],"High-Performance":[2],"Computing":[3],"(HPC)":[4],"application":[5],"executing":[6],"on":[7],"large-scale":[9],"failure-prone":[10],"platform.":[11],"The":[12,73,150],"Fixed-Work":[13],"Checkpointing":[14,62],"(":[15,63],"FWC":[16,44,115],")":[17,65],"problem":[18,45,75,116,151,179],"consists":[19,76],"in":[20,77],"minimizing":[21],"the":[22,36,39,43,54,56,60,79,90,97,114,125,147,174,178],"expected":[23,80],"time":[24,88,192],"to":[25,96,120,154,161,172,189,191,194,205],"execute":[26],"fixed":[28,85],"amount":[29,86],"of":[30,38,87,92,105,146,177,184],"work":[31,81,100],"(namely":[32,89],"fraction":[34],"or":[35,164],"totality":[37],"application).":[40,98],"Strategies":[41],"for":[42,113],"have":[46,188],"received":[47],"considerable":[48],"attention":[49],"and":[50,117,186],"are":[51],"well-understood.":[52],"On":[53],"contrary,":[55],"dual":[57],"problem,":[58,66],"namely":[59],"Fixed-Time":[61],"FTC":[64,74,148],"has":[67],"been":[68],"considered":[69],"only":[70],"very":[71],"recently.":[72],"maximizing":[78],"achieved":[82],"during":[83],"duration":[91],"reservation":[94],"granted":[95],"This":[99],"provides":[101],"comparative":[103],"overview":[104],"both":[106],"problems.":[107],"First":[108],"we":[109,141,187],"review":[110],"existing":[111],"strategies":[112],"extend":[118,201],"them":[119],"stochastic":[121,206],"checkpoints,":[122,185],"i.e.,":[123],"when":[124,159],"checkpoint":[126],"is":[127],"no":[128],"longer":[129],"deterministic":[131],"constant":[132],"but":[133],"obeys":[134],"some":[135],"probability":[136],"distribution":[137],"law":[138],"instead.":[139],"Then":[140],"provide":[142,168,195],"comprehensive":[144],"study":[145],"problem.":[149],"turns":[152],"out":[153],"be":[155],"surprisingly":[156],"difficult,":[157],"even":[158],"restricting":[160],"taking":[162],"one":[163],"two":[165],"checkpoints.":[166,207],"We":[167,199],"threshold-based":[170],"heuristic":[171],"solve":[173],"general":[175],"instance":[176],"with":[180],"an":[181,196],"arbitrary":[182],"number":[183],"resort":[190],"discretization":[193],"optimal":[197],"strategy.":[198],"further":[200],"this":[202],"latter":[203],"strategy":[204]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}