{"id":"https://openalex.org/W2981033832","doi":"https://doi.org/10.1109/ipdpsw50202.2020.00099","title":"Design and Comparison of Resilient Scheduling Heuristics for Parallel Jobs","display_name":"Design and Comparison of Resilient Scheduling Heuristics for Parallel Jobs","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W2981033832","doi":"https://doi.org/10.1109/ipdpsw50202.2020.00099","mag":"2981033832"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw50202.2020.00099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw50202.2020.00099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-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/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/I4210144566","display_name":"Laboratoire de l'Informatique du Parall\u00e9lisme","ror":"https://ror.org/04msnz457","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210144566"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Anne Benoit","raw_affiliation_strings":["Laboratoire LIP, ENS Lyon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire LIP, ENS Lyon, France","institution_ids":["https://openalex.org/I4210144566","https://openalex.org/I113428412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068707481","display_name":"Valentin Le F\u00e8vre","orcid":"https://orcid.org/0000-0001-6853-5392"},"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/I4210144566","display_name":"Laboratoire de l'Informatique du Parall\u00e9lisme","ror":"https://ror.org/04msnz457","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210144566"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Valentin Le Fevre","raw_affiliation_strings":["Laboratoire LIP, ENS Lyon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire LIP, ENS Lyon, France","institution_ids":["https://openalex.org/I4210144566","https://openalex.org/I113428412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104052216","display_name":"Padma Raghavan","orcid":null},"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/I4210144566","display_name":"Laboratoire de l'Informatique du Parall\u00e9lisme","ror":"https://ror.org/04msnz457","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210144566"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Padma Raghavan","raw_affiliation_strings":["Laboratoire LIP, ENS Lyon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire LIP, ENS Lyon, France","institution_ids":["https://openalex.org/I4210144566","https://openalex.org/I113428412"]}]},{"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/I4210144566","display_name":"Laboratoire de l'Informatique du Parall\u00e9lisme","ror":"https://ror.org/04msnz457","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210144566"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yves Robert","raw_affiliation_strings":["Laboratoire LIP, ENS Lyon, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire LIP, ENS Lyon, France","institution_ids":["https://openalex.org/I4210144566","https://openalex.org/I113428412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076659753","display_name":"Hongyang Sun","orcid":"https://orcid.org/0000-0002-4379-4467"},"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":"Hongyang Sun","raw_affiliation_strings":["Vanderbilt University, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037778045"],"corresponding_institution_ids":["https://openalex.org/I113428412","https://openalex.org/I4210144566"],"apc_list":null,"apc_paid":null,"fwci":0.9251,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75838397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"567","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9995999932289124,"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/T12288","display_name":"Optimization and Search Problems","score":0.9995999932289124,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12176","display_name":"Optimization and Packing Problems","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/heuristics","display_name":"Heuristics","score":0.8663107752799988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.749927818775177},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7071134448051453},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.613076388835907},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6019093990325928},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5161067247390747},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.5006623268127441},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4920022189617157},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47663769125938416},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.42653992772102356},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21679294109344482},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11790835857391357},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11547061800956726},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10257408022880554},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.07760483026504517}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8663107752799988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749927818775177},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7071134448051453},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.613076388835907},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6019093990325928},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5161067247390747},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.5006623268127441},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4920022189617157},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47663769125938416},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.42653992772102356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21679294109344482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11790835857391357},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11547061800956726},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10257408022880554},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.07760483026504517},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw50202.2020.00099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw50202.2020.00099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1513326124","https://openalex.org/W1540493477","https://openalex.org/W1573602196","https://openalex.org/W1596936080","https://openalex.org/W1599248213","https://openalex.org/W1944778298","https://openalex.org/W1986905947","https://openalex.org/W1997959089","https://openalex.org/W2011039300","https://openalex.org/W2019261717","https://openalex.org/W2019318803","https://openalex.org/W2032392871","https://openalex.org/W2035486547","https://openalex.org/W2038303146","https://openalex.org/W2045215405","https://openalex.org/W2061887253","https://openalex.org/W2072637364","https://openalex.org/W2086190489","https://openalex.org/W2086677494","https://openalex.org/W2112168774","https://openalex.org/W2127960094","https://openalex.org/W2128282503","https://openalex.org/W2128511938","https://openalex.org/W2142932691","https://openalex.org/W2150074609","https://openalex.org/W2152407222","https://openalex.org/W2154305205","https://openalex.org/W2528657027","https://openalex.org/W2794563548","https://openalex.org/W2808246216","https://openalex.org/W2981033832","https://openalex.org/W4248621761","https://openalex.org/W6635793591","https://openalex.org/W6769989368"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2970302286","https://openalex.org/W2810352541","https://openalex.org/W2142195909"],"abstract_inverted_index":{"This":[0,53],"paper":[1,118],"focuses":[2,119],"on":[3,10,120],"the":[4,17,25,56,69,121,159],"resilient":[5],"scheduling":[6,73,113],"of":[7,123,149],"parallel":[8],"jobs":[9,31,60,79,101,154],"high-performance":[11],"computing":[12],"(HPC)":[13],"platforms":[14],"to":[15,34,43,50,77,82,88],"minimize":[16],"overall":[18],"completion":[19],"time,":[20],"or":[21,36],"makespan.":[22],"We":[23,97,139],"revisit":[24],"classical":[26,57,70],"problem":[27],"while":[28],"assuming":[29],"that":[30,74,99],"are":[32,61],"subject":[33],"transient":[35],"silent":[37],"errors,":[38],"and":[39,64,91,128,136,141,155],"hence":[40],"may":[41],"need":[42],"be":[44,83,107],"re-executed":[45],"each":[46],"time":[47],"they":[48],"fail":[49],"complete":[51],"successfully.":[52],"work":[54],"generalizes":[55],"framework":[58],"where":[59],"known":[62,81],"offline":[63],"do":[65],"not":[66],"fail:":[67],"in":[68],"framework,":[71],"list":[72,112],"gives":[75],"priority":[76,134],"longest":[78],"is":[80],"a":[84,92,115],"3-approximation":[85],"when":[86,100],"imposing":[87],"use":[89],"shelves,":[90],"2-approximation":[93],"without":[94],"this":[95],"restriction.":[96],"show":[98],"can":[102,106],"fail,":[103],"using":[104,151],"shelves":[105],"arbitrarily":[108],"bad,":[109],"but":[110],"unrestricted":[111],"remains":[114],"2-approximation.":[116],"The":[117],"design":[122],"several":[124],"heuristics,":[125],"some":[126,129],"list-based":[127],"shelf-based,":[130],"along":[131],"with":[132],"different":[133],"rules":[135],"backfilling":[137],"strategies.":[138],"assess":[140],"compare":[142],"their":[143],"performance":[144],"through":[145],"an":[146],"extensive":[147],"set":[148],"simulations,":[150],"both":[152],"synthetic":[153],"log":[156],"traces":[157],"from":[158],"Mira":[160],"supercomputer.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}