{"id":"https://openalex.org/W4319068657","doi":"https://doi.org/10.1109/tc.2023.3242200","title":"Hydra: Deadline-Aware and Efficiency-Oriented Scheduling for Deep Learning Jobs on Heterogeneous GPUs","display_name":"Hydra: Deadline-Aware and Efficiency-Oriented Scheduling for Deep Learning Jobs on Heterogeneous GPUs","publication_year":2023,"publication_date":"2023-02-03","ids":{"openalex":"https://openalex.org/W4319068657","doi":"https://doi.org/10.1109/tc.2023.3242200"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2023.3242200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3242200","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101461003","display_name":"Zichao Yang","orcid":"https://orcid.org/0000-0003-0699-394X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zichao Yang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709659","display_name":"Heng Wu","orcid":"https://orcid.org/0000-0001-7903-5879"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Wu","raw_affiliation_strings":["Chongqing School, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing School, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101628515","display_name":"Yuanjia Xu","orcid":"https://orcid.org/0000-0003-0939-2381"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanjia Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017383055","display_name":"Yuewen Wu","orcid":"https://orcid.org/0000-0002-1323-2455"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Wu","raw_affiliation_strings":["State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046331935","display_name":"Hua Zhong","orcid":"https://orcid.org/0000-0003-0031-5283"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Zhong","raw_affiliation_strings":["State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398448","display_name":"Wenbo Zhang","orcid":"https://orcid.org/0000-0002-0237-5100"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Zhang","raw_affiliation_strings":["State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101461003"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":5.1425,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9613319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"72","issue":"8","first_page":"2224","last_page":"2236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"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":0.9979000091552734,"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/tardiness","display_name":"Tardiness","score":0.8622373342514038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8152649402618408},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7405146360397339},{"id":"https://openalex.org/keywords/lernaean-hydra","display_name":"Lernaean Hydra","score":0.5544400811195374},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5193894505500793},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4712396562099457},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.45178329944610596},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43399670720100403},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.3602692484855652},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.28003090620040894},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.20130014419555664},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10915565490722656}],"concepts":[{"id":"https://openalex.org/C2778047078","wikidata":"https://www.wikidata.org/wiki/Q82299449","display_name":"Tardiness","level":4,"score":0.8622373342514038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8152649402618408},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7405146360397339},{"id":"https://openalex.org/C34781881","wikidata":"https://www.wikidata.org/wiki/Q170379","display_name":"Lernaean Hydra","level":2,"score":0.5544400811195374},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5193894505500793},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4712396562099457},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.45178329944610596},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43399670720100403},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3602692484855652},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28003090620040894},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.20130014419555664},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10915565490722656},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C74916050","wikidata":"https://www.wikidata.org/wiki/Q841090","display_name":"Classics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2023.3242200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3242200","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G1109687085","display_name":null,"funder_award_id":"61972386","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2055748525","https://openalex.org/W2060393849","https://openalex.org/W2069533632","https://openalex.org/W2109488193","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2309679942","https://openalex.org/W2335814492","https://openalex.org/W2528415359","https://openalex.org/W2735065300","https://openalex.org/W2795361658","https://openalex.org/W2798515322","https://openalex.org/W2799240483","https://openalex.org/W2886481383","https://openalex.org/W2899071864","https://openalex.org/W2919594608","https://openalex.org/W2919897868","https://openalex.org/W2962752334","https://openalex.org/W2963150697","https://openalex.org/W2963446712","https://openalex.org/W2963684088","https://openalex.org/W2964667342","https://openalex.org/W2987954639","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3047783725","https://openalex.org/W3096583839","https://openalex.org/W3116115872","https://openalex.org/W3135013702","https://openalex.org/W3181228931","https://openalex.org/W3197312007","https://openalex.org/W3197816522","https://openalex.org/W3209503812","https://openalex.org/W3212545986","https://openalex.org/W4288289123","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6685352114","https://openalex.org/W6687566353","https://openalex.org/W6697698479","https://openalex.org/W6727576777","https://openalex.org/W6739901393","https://openalex.org/W6753359477","https://openalex.org/W6756009870","https://openalex.org/W6759814162","https://openalex.org/W6769424276","https://openalex.org/W6782839094","https://openalex.org/W6791067469","https://openalex.org/W6798473733","https://openalex.org/W7067822191"],"related_works":["https://openalex.org/W2128040437","https://openalex.org/W2011810134","https://openalex.org/W2093732113","https://openalex.org/W2381253015","https://openalex.org/W2141305934","https://openalex.org/W2268219566","https://openalex.org/W2050497389","https://openalex.org/W3097192092","https://openalex.org/W3029619930","https://openalex.org/W2061005265"],"abstract_inverted_index":{"With":[0],"the":[1,44,59,84,87,96,100,105,117,145,155],"rapid":[2],"proliferation":[3],"of":[4,46,103,107,121,138,157],"deep":[5],"learning":[6],"(DL)":[7],"jobs":[8,15,48,60,123],"running":[9],"on":[10,65,130,160],"heterogeneous":[11,66,131],"GPUs,":[12],"scheduling":[13,19,47,81],"DL":[14,122],"to":[16,49,78,124,143],"meet":[17,50],"various":[18,62,136],"requirements,":[20],"such":[21],"as":[22,176,178],"meeting":[23],"deadlines":[24],"and":[25,36,141],"reducing":[26,54,173],"job":[27,126,139],"completion":[28],"time":[29,102],"(JCT),":[30],"is":[31],"critical.":[32],"Unfortunately,":[33],"existing":[34],"efficiency-oriented":[35],"deadline-aware":[37],"efforts":[38],"are":[39],"still":[40],"rudimentary.":[41],"They":[42],"lack":[43],"capability":[45],"deadline":[51],"requirements":[52],"while":[53,172],"total":[55,88,97,168,174],"JCT,":[56],"especially":[57],"when":[58],"have":[61],"execution":[63,127],"times":[64,128],"GPUs.":[67,132],"Therefore,":[68],"we":[69],"present":[70],"Hydra,":[71],"a":[72,91,112],"novel":[73],"quantitative":[74],"cost":[75,85,147],"comparison":[76],"approach,":[77],"address":[79],"this":[80],"issue.":[82],"Here,":[83],"represents":[86],"JCT":[89,175],"plus":[90],"dynamic":[92],"penalty":[93],"calculated":[94],"from":[95],"tardiness":[98,169],"(i.e.,":[99],"delay":[101],"exceeding":[104],"deadline)":[106],"all":[108],"jobs.":[109],"Hydra":[110,134,165],"adopts":[111],"sampling":[113],"approach":[114],"that":[115,164],"exploits":[116],"inherent":[118],"iterative":[119],"periodicity":[120],"estimate":[125],"accurately":[129],"Then,":[133],"considers":[135],"combinations":[137],"sequences":[140],"GPUs":[142],"obtain":[144],"minimized":[146],"by":[148,170],"leveraging":[149],"an":[150],"efficient":[151],"branch-and-bound":[152],"algorithm.":[153],"Finally,":[154],"results":[156],"evaluation":[158],"experiments":[159],"Alibaba":[161],"traces":[162],"show":[163],"can":[166],"reduce":[167],"85.8%":[171],"much":[177],"possible,":[179],"compared":[180],"with":[181],"state-of-the-art":[182],"efforts.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
