{"id":"https://openalex.org/W3125275612","doi":"https://doi.org/10.1109/tc.2021.3104747","title":"Resilient Scheduling of Moldable Parallel Jobs to Cope With Silent Errors","display_name":"Resilient Scheduling of Moldable Parallel Jobs to Cope With Silent Errors","publication_year":2021,"publication_date":"2021-08-13","ids":{"openalex":"https://openalex.org/W3125275612","doi":"https://doi.org/10.1109/tc.2021.3104747","mag":"3125275612"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2021.3104747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3104747","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-02614215","any_repository_has_fulltext":true},"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Anne Benoit","raw_affiliation_strings":["LIP Laboratory, Ecole Normale Supérieure de Lyon, Lyon, France"],"affiliations":[{"raw_affiliation_string":"LIP Laboratory, Ecole Normale Supérieure de Lyon, Lyon, France","institution_ids":["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/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Valentin Le Fevre","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"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/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/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Lucas Perotin","raw_affiliation_strings":["LIP Laboratory, Ecole Normale Supérieure de Lyon, Lyon, France","Vanderbilt University [Nashville] (Nashville, Tennessee, TN 37240 - United States)"],"affiliations":[{"raw_affiliation_string":"LIP Laboratory, Ecole Normale Supérieure de Lyon, Lyon, France","institution_ids":["https://openalex.org/I113428412"]},{"raw_affiliation_string":"Vanderbilt University [Nashville] (Nashville, Tennessee, TN 37240 - United States)","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102868534","display_name":"Padma Raghavan","orcid":"https://orcid.org/0009-0002-6785-2112"},"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":"Padma Raghavan","raw_affiliation_strings":["Vanderbilt University, Nashville, TN, USA","Vanderbilt University [Nashville] (Nashville, Tennessee, TN 37240 - United States)"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University [Nashville] (Nashville, Tennessee, TN 37240 - United States)","institution_ids":["https://openalex.org/I200719446"]}]},{"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/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Yves Robert","raw_affiliation_strings":["LIP Laboratory, Ecole Normale Supérieure de Lyon, Lyon, France","ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)"],"affiliations":[{"raw_affiliation_string":"LIP Laboratory, Ecole Normale Supérieure de Lyon, Lyon, France","institution_ids":["https://openalex.org/I113428412"]},{"raw_affiliation_string":"ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)","institution_ids":["https://openalex.org/I75027704"]}]},{"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/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]},{"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":["University of Kansas, Lawrence, KS, USA","University of Kansas [Kansas City] (Kansas City, KS, USA - United States)","Vanderbilt University [Nashville] (Nashville, Tennessee, TN 37240 - United States)"],"affiliations":[{"raw_affiliation_string":"University of Kansas, Lawrence, KS, USA","institution_ids":["https://openalex.org/I146416000"]},{"raw_affiliation_string":"University of Kansas [Kansas City] (Kansas City, KS, USA - United States)","institution_ids":["https://openalex.org/I146416000"]},{"raw_affiliation_string":"Vanderbilt University [Nashville] (Nashville, Tennessee, TN 37240 - United States)","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037778045"],"corresponding_institution_ids":["https://openalex.org/I113428412"],"apc_list":null,"apc_paid":null,"fwci":0.9045,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78071452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"71","issue":"7","first_page":"1696","last_page":"1710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9993000030517578,"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/T12288","display_name":"Optimization and Search Problems","score":0.9991999864578247,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987000226974487,"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":0.6908715963363647},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6869006752967834},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.6573038697242737},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.43252187967300415},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.430071622133255},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.41939109563827515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32523584365844727},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27450576424598694},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.21132639050483704},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1846085488796234},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12943685054779053},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12895920872688293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908715963363647},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6869006752967834},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.6573038697242737},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.43252187967300415},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.430071622133255},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.41939109563827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32523584365844727},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27450576424598694},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.21132639050483704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1846085488796234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12943685054779053},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12895920872688293},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tc.2021.3104747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3104747","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02614215v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02614215","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-9340, Inria - Research Centre Grenoble \u2013 Rh\u00f4ne-Alpes. 2021","raw_type":"Reports"},{"id":"pmh:oai:HAL:hal-03509760v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03509760","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Computers, 2021, pp.1-14. ⟨10.1109/TC.2021.3104747⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02614215v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02614215","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-9340, Inria - Research Centre Grenoble \u2013 Rh\u00f4ne-Alpes. 2021","raw_type":"Reports"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1496507101","https://openalex.org/W1548952399","https://openalex.org/W1605529813","https://openalex.org/W1916275345","https://openalex.org/W1918518755","https://openalex.org/W1974114807","https://openalex.org/W1985211757","https://openalex.org/W1986905947","https://openalex.org/W2001066639","https://openalex.org/W2018125025","https://openalex.org/W2028801713","https://openalex.org/W2035486547","https://openalex.org/W2041182977","https://openalex.org/W2045215405","https://openalex.org/W2048462504","https://openalex.org/W2052294974","https://openalex.org/W2054626117","https://openalex.org/W2057913648","https://openalex.org/W2061887253","https://openalex.org/W2071698746","https://openalex.org/W2081840458","https://openalex.org/W2086190489","https://openalex.org/W2086677494","https://openalex.org/W2090166506","https://openalex.org/W2115015692","https://openalex.org/W2142860409","https://openalex.org/W2150871235","https://openalex.org/W2152362214","https://openalex.org/W2152407222","https://openalex.org/W2159472851","https://openalex.org/W2528657027","https://openalex.org/W2787020575","https://openalex.org/W2808246216","https://openalex.org/W2963661393","https://openalex.org/W3095719590","https://openalex.org/W3120273551","https://openalex.org/W4233783938","https://openalex.org/W4247162781","https://openalex.org/W6607236798","https://openalex.org/W6639543110","https://openalex.org/W6661238359"],"related_works":["https://openalex.org/W2149404148","https://openalex.org/W3204654320","https://openalex.org/W1984267569","https://openalex.org/W2092966558","https://openalex.org/W1956651153","https://openalex.org/W2347561926","https://openalex.org/W2327547880","https://openalex.org/W44553394","https://openalex.org/W3153517983","https://openalex.org/W210339300"],"abstract_inverted_index":{"We":[0,154],"study":[1],"the":[2,37,42,68,98,105,130,137,159,189,193,220,232],"resilient":[3,83],"scheduling":[4,70,84],"of":[5,95,147,180,188,211,213,223,229],"moldable":[6],"parallel":[7],"jobs":[8,15,45,138],"on":[9,122,217],"high-performance":[10],"computing":[11],"(HPC)":[12],"platforms.":[13],"Moldable":[14],"allow":[16],"for":[17,72,158],"choosing":[18],"a":[19,109,123,144,174,209,214,227],"processor":[20],"allocation":[21],"before":[22],"execution,":[23],"and":[24,52,89,141,173,192,225],"their":[25],"execution":[26],"time":[27,40],"obeys":[28],"various":[29],"speedup":[30,165],"models.":[31],"The":[32],"objective":[33],"is":[34,182,207],"to":[35,49,56,103,126,129,184],"minimize":[36],"overall":[38],"completion":[39],"or":[41],"makespan,":[43],"when":[44],"can":[46],"fail":[47],"due":[48],"silent":[50,78],"errors":[51],"hence":[53],"may":[54],"need":[55],"be":[57],"re-executed":[58],"after":[59],"each":[60,114,152],"failure":[61],"until":[62],"successful":[63],"completion.":[64],"Our":[65],"work":[66],"generalizes":[67],"classical":[69],"framework":[71],"failure-free":[73],"jobs.":[74,106],"To":[75],"cope":[76],"with":[77],"errors,":[79],"we":[80],"introduce":[81],"two":[82,160,190],"algorithms,":[85,191],"Lpa-List":[88,120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Batch-List":[92,135],",":[93],"both":[94],"which":[96],"use":[97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">List":[101],"strategy":[102,125],"schedule":[104],"Without":[107],"knowing":[108],"priori":[110],"how":[111],"many":[112],"times":[113],"job":[115,150],"will":[116],"fail,":[117],"relies":[121],"local":[124],"allocate":[127],"processors":[128],"jobs,":[131],"while":[132],"schedules":[136],"in":[139,151,231],"batches":[140],"allows":[142],"only":[143],"restricted":[145],"number":[146],"failures":[148],"per":[149],"batch.":[153],"prove":[155],"approximation":[156],"ratios":[157],"algorithms":[161],"under":[162],"several":[163],"prominent":[164],"models":[166],"(e.g.,":[167],"roofline,":[168],"communication,":[169],"Amdahl,":[170],"power,":[171],"monotonic,":[172],"mix":[175],"model).":[176],"An":[177],"extensive":[178],"set":[179,222],"simulations":[181],"conducted":[183],"evaluate":[185],"different":[186],"variants":[187],"results":[194],"show":[195],"that":[196],"they":[197],"consistently":[198],"outperform":[199],"some":[200],"baseline":[201],"heuristics.":[202],"Overall,":[203],"our":[204],"best":[205],"algorithm":[206],"within":[208,226],"factor":[210,228],"1.6":[212],"lower":[215],"bound":[216],"average":[218],"over":[219],"entire":[221],"experiments,":[224],"4.2":[230],"worst":[233],"case.":[234]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}