{"id":"https://openalex.org/W4304820086","doi":"https://doi.org/10.1109/ipccc55026.2022.9894345","title":"PickyMan: A Preemptive Scheduler for Deep Learning Jobs on GPU Clusters","display_name":"PickyMan: A Preemptive Scheduler for Deep Learning Jobs on GPU Clusters","publication_year":2022,"publication_date":"2022-10-12","ids":{"openalex":"https://openalex.org/W4304820086","doi":"https://doi.org/10.1109/ipccc55026.2022.9894345"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc55026.2022.9894345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc55026.2022.9894345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100418505","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-9090-5836"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101637287","display_name":"Yingwen Chen","orcid":"https://orcid.org/0000-0002-8171-1861"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingwen Chen","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981758","display_name":"Zhaoyun Chen","orcid":"https://orcid.org/0000-0003-1552-8396"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyun Chen","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037285929","display_name":"Jianchen Han","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchen Han","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101490654","display_name":"Guangtao Xue","orcid":"https://orcid.org/0000-0002-1617-3593"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Xue","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5025,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63050088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8431491851806641},{"id":"https://openalex.org/keywords/preemption","display_name":"Preemption","score":0.8012895584106445},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6347157955169678},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6235017776489258},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.5676433444023132},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.4846647381782532},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.4594806432723999},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41884803771972656},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4170175790786743},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.31733494997024536},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.18415579199790955},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18020710349082947},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.1284383237361908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431491851806641},{"id":"https://openalex.org/C206952183","wikidata":"https://www.wikidata.org/wiki/Q1193100","display_name":"Preemption","level":2,"score":0.8012895584106445},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6347157955169678},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6235017776489258},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.5676433444023132},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.4846647381782532},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.4594806432723999},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41884803771972656},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4170175790786743},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.31733494997024536},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.18415579199790955},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18020710349082947},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.1284383237361908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc55026.2022.9894345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc55026.2022.9894345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1493774699","https://openalex.org/W1585314083","https://openalex.org/W2041517243","https://openalex.org/W2070235786","https://openalex.org/W2083842231","https://openalex.org/W2798515322","https://openalex.org/W2964667342","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3209503812","https://openalex.org/W4287572644","https://openalex.org/W6634769544","https://openalex.org/W6756009870","https://openalex.org/W6759814162","https://openalex.org/W6769424276","https://openalex.org/W6781728138","https://openalex.org/W6782839094","https://openalex.org/W6784871562","https://openalex.org/W6785115463","https://openalex.org/W6786756185","https://openalex.org/W6801004768"],"related_works":["https://openalex.org/W2794663421","https://openalex.org/W4290043243","https://openalex.org/W3115567997","https://openalex.org/W2917736609","https://openalex.org/W2092966558","https://openalex.org/W1956651153","https://openalex.org/W1984267569","https://openalex.org/W2347561926","https://openalex.org/W2315766899","https://openalex.org/W2327547880"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"jobs":[3,11,73,99,164,220,235],"normally":[4],"run":[5],"on":[6,247],"GPU":[7],"clusters.":[8],"Some":[9],"DL":[10,25,129],"need":[12],"to":[13,17,37,49,93,100,139,165,194,271,274],"be":[14],"scheduled":[15],"preemptively":[16],"avoid":[18],"long":[19],"waiting":[20,80,104,260],"times.":[21],"However,":[22],"preempting":[23,67,98],"a":[24,90,128,144,192,241],"job":[26,130,200],"is":[27],"time-consuming,":[28],"which":[29],"consists":[30],"of":[31,42,66,97,127,149,161,176,188,199,208,216,225,230,233],"suspending":[32],"and":[33,46,53,82,106,120,142,174,202,236,252,264],"resuming.":[34],"Suspending":[35],"needs":[36,48],"complete":[38],"the":[39,43,51,54,64,79,83,95,102,107,124,133,147,154,167,177,186,196,214,218,231,248,258,267],"training":[40,55],"process":[41],"current":[44],"epoch,":[45],"resuming":[47],"reload":[50],"model":[52,193],"data.":[56],"The":[57],"existing":[58,275],"schedulers":[59],"almost":[60],"do":[61],"not":[62],"consider":[63],"overhead":[65,96,187],"jobs;":[68],"thus,":[69],"they":[70],"may":[71],"preempt":[72],"with":[74,204,240],"large":[75],"time":[76,81,105,116,126,197,261],"loss,":[77],"increasing":[78],"makespan.In":[84],"this":[85],"paper,":[86],"we":[87],"present":[88],"PickyMan,":[89],"preemptive":[91],"scheduler":[92],"minimize":[94],"reduce":[101],"average":[103,206,259],"makespan.":[108],"PickyMan":[109,256],"has":[110],"some":[111],"innovations.":[112],"(1)":[113],"Predict":[114],"execution":[115,125,168],"using":[117,143],"network":[118,134],"traffic":[119,135],"database.":[121],"It":[122,156,190],"predicts":[123],"by":[131,262,269],"profiling":[132],"from":[136,153],"storage":[137],"nodes":[138,141],"computation":[140],"database,":[145],"without":[146],"requirement":[148],"allocating":[150],"extra":[151],"resources":[152],"cluster.":[155],"can":[157],"use":[158],"profiled":[159],"information":[160],"only":[162],"four":[163],"predict":[166,195],"times":[169],"for":[170,221],"other":[171],"same-model":[172],"jobs,":[173],"most":[175],"predicted":[178],"errors":[179],"are":[180],"less":[181,209],"than":[182,210],"10%.":[183],"(2)":[184],"Modeling":[185],"preemption.":[189],"builds":[191],"loss":[198],"suspensions":[201],"resumptions":[203],"an":[205,227],"error":[207],"5%.":[211],"(3)We":[212],"abstract":[213],"problem":[215],"choosing":[217],"appropriate":[219],"preemption":[222],"as":[223],"one":[224],"finding":[226],"ordered":[228],"division":[229],"set":[232],"running":[234],"solve":[237],"it":[238],"quickly":[239],"greedy":[242],"algorithm.":[243],"By":[244],"conducting":[245],"experiments":[246],"small-scale":[249],"actual":[250],"cluster":[251],"making":[253],"large-scale":[254],"simulations,":[255],"reduces":[257,266],"10%\u201392%":[263],"further":[265],"makespan":[268],"up":[270],"14%,":[272],"compared":[273],"methods.":[276]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}