{"id":"https://openalex.org/W4390263770","doi":"https://doi.org/10.1145/3638757","title":"Deep Learning Workload Scheduling in GPU Datacenters: A Survey","display_name":"Deep Learning Workload Scheduling in GPU Datacenters: A Survey","publication_year":2023,"publication_date":"2023-12-27","ids":{"openalex":"https://openalex.org/W4390263770","doi":"https://doi.org/10.1145/3638757"},"language":"en","primary_location":{"id":"doi:10.1145/3638757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3638757","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3638757","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3638757","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103041352","display_name":"Zhisheng Ye","orcid":"https://orcid.org/0000-0002-4568-0244"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisheng Ye","raw_affiliation_strings":["Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-4568-0244","affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732619","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0002-7048-1722"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Gao","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7048-1722","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035921543","display_name":"Qinghao Hu","orcid":"https://orcid.org/0000-0003-1034-7502"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qinghao Hu","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1034-7502","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614087","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0001-8456-0491"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["Shanghai AI Laboratory & SenseTime Research, China"],"raw_orcid":"https://orcid.org/0000-0001-8456-0491","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory & SenseTime Research, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395154","display_name":"Xiaolin Wang","orcid":"https://orcid.org/0000-0002-6951-1613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Wang","raw_affiliation_strings":["Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-6951-1613","affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028194980","display_name":"Yingwei Luo","orcid":"https://orcid.org/0000-0002-7903-0717"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingwei Luo","raw_affiliation_strings":["Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-7903-0717","affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101591101","display_name":"Tianwei Zhang","orcid":"https://orcid.org/0000-0001-6595-6650"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianwei Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6595-6650","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041572550","display_name":"Yonggang Wen","orcid":"https://orcid.org/0000-0002-2751-5114"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yonggang Wen","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2751-5114","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":45.0613,"has_fulltext":true,"cited_by_count":102,"citation_normalized_percentile":{"value":0.99887347,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"56","issue":"6","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9140259027481079},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7534539103507996},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6773453950881958},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5057432651519775},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49747684597969055},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42955300211906433},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3855721056461334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31345221400260925},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25139564275741577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9140259027481079},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7534539103507996},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6773453950881958},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5057432651519775},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49747684597969055},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42955300211906433},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3855721056461334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31345221400260925},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25139564275741577},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3638757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3638757","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3638757","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/178253","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/178253","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1145/3638757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3638757","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3638757","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1447753631","display_name":null,"funder_award_id":"62032001, 62032008, 62372011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4460768019","display_name":null,"funder_award_id":"62032001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6188817956","display_name":null,"funder_award_id":"62032008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6724539047","display_name":null,"funder_award_id":"2022YFB4500701","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390263770.pdf","grobid_xml":"https://content.openalex.org/works/W4390263770.grobid-xml"},"referenced_works_count":137,"referenced_works":["https://openalex.org/W1528656891","https://openalex.org/W1982648554","https://openalex.org/W1996212904","https://openalex.org/W2022501047","https://openalex.org/W2081904683","https://openalex.org/W2091520147","https://openalex.org/W2096125134","https://openalex.org/W2100297710","https://openalex.org/W2105947650","https://openalex.org/W2112168774","https://openalex.org/W2129542763","https://openalex.org/W2159588611","https://openalex.org/W2335814492","https://openalex.org/W2489529491","https://openalex.org/W2533800772","https://openalex.org/W2605643718","https://openalex.org/W2609354095","https://openalex.org/W2612358188","https://openalex.org/W2621285457","https://openalex.org/W2623397635","https://openalex.org/W2766447205","https://openalex.org/W2766630095","https://openalex.org/W2767239597","https://openalex.org/W2772678505","https://openalex.org/W2794513473","https://openalex.org/W2794670651","https://openalex.org/W2798291715","https://openalex.org/W2798515322","https://openalex.org/W2799240483","https://openalex.org/W2901394833","https://openalex.org/W2911714797","https://openalex.org/W2919897868","https://openalex.org/W2934208298","https://openalex.org/W2934853022","https://openalex.org/W2941938531","https://openalex.org/W2944614352","https://openalex.org/W2962684017","https://openalex.org/W2962746093","https://openalex.org/W2963149401","https://openalex.org/W2963988417","https://openalex.org/W2964667342","https://openalex.org/W2965057263","https://openalex.org/W2970587001","https://openalex.org/W2972392561","https://openalex.org/W2977714483","https://openalex.org/W2979044977","https://openalex.org/W2981449041","https://openalex.org/W2982157693","https://openalex.org/W2982674764","https://openalex.org/W2982899198","https://openalex.org/W2987954639","https://openalex.org/W2988216516","https://openalex.org/W3004495293","https://openalex.org/W3010528756","https://openalex.org/W3012121966","https://openalex.org/W3012536640","https://openalex.org/W3022298203","https://openalex.org/W3026530461","https://openalex.org/W3034464255","https://openalex.org/W3034987706","https://openalex.org/W3037110041","https://openalex.org/W3037639655","https://openalex.org/W3042495273","https://openalex.org/W3043302551","https://openalex.org/W3043433718","https://openalex.org/W3047783725","https://openalex.org/W3048104376","https://openalex.org/W3091992486","https://openalex.org/W3092727424","https://openalex.org/W3095283736","https://openalex.org/W3095488153","https://openalex.org/W3097411828","https://openalex.org/W3102385572","https://openalex.org/W3102606411","https://openalex.org/W3102873192","https://openalex.org/W3105227206","https://openalex.org/W3106772683","https://openalex.org/W3106918569","https://openalex.org/W3108033633","https://openalex.org/W3113635268","https://openalex.org/W3121689374","https://openalex.org/W3122047047","https://openalex.org/W3127688686","https://openalex.org/W3130934537","https://openalex.org/W3131071874","https://openalex.org/W3131369229","https://openalex.org/W3134991928","https://openalex.org/W3136172274","https://openalex.org/W3137147200","https://openalex.org/W3155194266","https://openalex.org/W3156353042","https://openalex.org/W3156449479","https://openalex.org/W3156987284","https://openalex.org/W3157306683","https://openalex.org/W3158363129","https://openalex.org/W3159050454","https://openalex.org/W3165292244","https://openalex.org/W3166863226","https://openalex.org/W3169109617","https://openalex.org/W3184606595","https://openalex.org/W3186289964","https://openalex.org/W3203600045","https://openalex.org/W3204075005","https://openalex.org/W3204998121","https://openalex.org/W3206418100","https://openalex.org/W3209503812","https://openalex.org/W3210591562","https://openalex.org/W3210776666","https://openalex.org/W3212545986","https://openalex.org/W3214993172","https://openalex.org/W4205500752","https://openalex.org/W4205916020","https://openalex.org/W4206174365","https://openalex.org/W4206374842","https://openalex.org/W4206790491","https://openalex.org/W4220942599","https://openalex.org/W4221149636","https://openalex.org/W4254052724","https://openalex.org/W4254672563","https://openalex.org/W4255361718","https://openalex.org/W4287991080","https://openalex.org/W4289083201","https://openalex.org/W4290991121","https://openalex.org/W4302383593","https://openalex.org/W4308426163","https://openalex.org/W4313169701","https://openalex.org/W4313229743","https://openalex.org/W4366564134","https://openalex.org/W4368755837","https://openalex.org/W4372261197","https://openalex.org/W4372263604","https://openalex.org/W4387321109","https://openalex.org/W4388874804","https://openalex.org/W4394998727","https://openalex.org/W6757364461","https://openalex.org/W6767541031","https://openalex.org/W6771893701"],"related_works":["https://openalex.org/W986318368","https://openalex.org/W2000785801","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W4390608645","https://openalex.org/W2990194547","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W1480123525","https://openalex.org/W2620865396"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"has":[3],"demonstrated":[4],"its":[5],"remarkable":[6],"success":[7],"in":[8,89],"a":[9,17,21,35,43],"wide":[10],"variety":[11],"of":[12,16,147],"fields.":[13],"The":[14],"development":[15],"DL":[18,71,87,133],"model":[19],"is":[20,46],"time-consuming":[22],"and":[23,53,101,118,139,151],"resource-intensive":[24],"procedure.":[25],"Hence,":[26],"dedicated":[27],"GPU":[28,36,44,77,90],"accelerators":[29],"have":[30],"been":[31],"collectively":[32],"constructed":[33],"into":[34],"datacenter.":[37],"An":[38],"efficient":[39],"scheduler":[40],"design":[41],"for":[42,61,86,98],"datacenter":[45],"crucially":[47],"important":[48],"to":[49,73,84],"reduce":[50],"operational":[51],"cost":[52],"improve":[54],"resource":[55,119],"utilization.":[56],"However,":[57],"traditional":[58],"approaches":[59],"designed":[60],"big":[62],"data":[63],"or":[64],"high-performance":[65],"computing":[66],"workloads":[67,72,88,113],"can":[68,154],"not":[69],"support":[70],"fully":[74],"utilize":[75],"the":[76,111,115,148],"resources.":[78,142],"Recently,":[79],"many":[80],"schedulers":[81,109],"are":[82],"proposed":[83],"tailor":[85],"datacenters.":[91],"This":[92],"article":[93],"surveys":[94],"existing":[95,108],"research":[96,129],"efforts":[97],"both":[99],"training":[100],"inference":[102],"workloads.":[103],"We":[104],"primarily":[105],"present":[106],"how":[107],"facilitate":[110],"respective":[112],"from":[114],"scheduling":[116,136],"objectives":[117],"utilization":[120],"manner":[121],".":[122],"Finally,":[123],"we":[124],"discuss":[125],"several":[126],"promising":[127],"future":[128],"directions":[130],"including":[131],"emerging":[132],"workloads,":[134],"advanced":[135],"decision":[137],"making,":[138],"underlying":[140],"hardware":[141],"A":[143],"more":[144],"detailed":[145],"summary":[146],"surveyed":[149],"paper":[150],"code":[152],"links":[153],"be":[155],"found":[156],"at":[157],"our":[158],"project":[159],"website:":[160],"https://github.com/S-Lab-System-Group/Awesome-DL-Scheduling-Papers":[161]},"counts_by_year":[{"year":2026,"cited_by_count":33},{"year":2025,"cited_by_count":60},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}