{"id":"https://openalex.org/W4385731844","doi":"https://doi.org/10.1109/tc.2023.3303988","title":"Improving Cluster Utilization Through Adaptive Resource Management for Deep Neural Network and CPU Jobs Colocation","display_name":"Improving Cluster Utilization Through Adaptive Resource Management for Deep Neural Network and CPU Jobs Colocation","publication_year":2023,"publication_date":"2023-08-10","ids":{"openalex":"https://openalex.org/W4385731844","doi":"https://doi.org/10.1109/tc.2023.3303988"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2023.3303988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3303988","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/A5063596525","display_name":"Han Zhao","orcid":"https://orcid.org/0000-0002-1561-5329"},"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":true,"raw_author_name":"Han Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1561-5329","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008837660","display_name":"Weihao Cui","orcid":"https://orcid.org/0000-0002-6646-5260"},"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":"Weihao Cui","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6646-5260","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"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":"Quan Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5832-0347","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"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":"Jingwen Leng","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5660-5493","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077093242","display_name":"Deze Zeng","orcid":"https://orcid.org/0000-0003-3276-1202"},"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":"Deze Zeng","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3276-1202","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0034-2302","affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063596525"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.1389,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92841271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"72","issue":"12","first_page":"3458","last_page":"3472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9987999796867371,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9945999979972839,"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":0.8417112231254578},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.7774375081062317},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.7529885768890381},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5867261290550232},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5840402245521545},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5740865468978882},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5518454313278198},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.5111175179481506},{"id":"https://openalex.org/keywords/job-queue","display_name":"Job queue","score":0.5064960718154907},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5001909732818604},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4393150806427002},{"id":"https://openalex.org/keywords/allocator","display_name":"Allocator","score":0.4373674690723419},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4225488603115082},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4143449664115906},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3757467269897461},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31678029894828796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30786868929862976},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2253527045249939},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.21312981843948364},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.17821067571640015},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1396157145500183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8417112231254578},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.7774375081062317},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.7529885768890381},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5867261290550232},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5840402245521545},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5740865468978882},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5518454313278198},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.5111175179481506},{"id":"https://openalex.org/C171627638","wikidata":"https://www.wikidata.org/wiki/Q6206744","display_name":"Job queue","level":4,"score":0.5064960718154907},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5001909732818604},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4393150806427002},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.4373674690723419},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4225488603115082},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4143449664115906},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3757467269897461},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31678029894828796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30786868929862976},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2253527045249939},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.21312981843948364},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.17821067571640015},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1396157145500183},{"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":1,"locations":[{"id":"doi:10.1109/tc.2023.3303988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3303988","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":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G2465329715","display_name":null,"funder_award_id":"61832006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5564014484","display_name":null,"funder_award_id":"61872240","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7942366687","display_name":null,"funder_award_id":"62022057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8848817600","display_name":null,"funder_award_id":"62022057, 61832006","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1464363888","https://openalex.org/W1471655812","https://openalex.org/W1686810756","https://openalex.org/W1890643295","https://openalex.org/W1922655562","https://openalex.org/W2055748525","https://openalex.org/W2096125134","https://openalex.org/W2105947650","https://openalex.org/W2141992894","https://openalex.org/W2155893237","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2519091744","https://openalex.org/W2551396370","https://openalex.org/W2618530766","https://openalex.org/W2794670651","https://openalex.org/W2798515322","https://openalex.org/W2899071864","https://openalex.org/W2906973781","https://openalex.org/W2929502194","https://openalex.org/W2953384591","https://openalex.org/W2963403751","https://openalex.org/W2963748441","https://openalex.org/W2982157693","https://openalex.org/W3022548332","https://openalex.org/W3116103263","https://openalex.org/W3131071874","https://openalex.org/W3208777667","https://openalex.org/W4231332361","https://openalex.org/W4235357114","https://openalex.org/W4297808460","https://openalex.org/W4385245566","https://openalex.org/W6628558282","https://openalex.org/W6628701632","https://openalex.org/W6637373629","https://openalex.org/W6639249596","https://openalex.org/W6640090968","https://openalex.org/W6713134421","https://openalex.org/W6729654139","https://openalex.org/W6739901393","https://openalex.org/W6747759466","https://openalex.org/W6756009870","https://openalex.org/W6757417182","https://openalex.org/W6758283263"],"related_works":["https://openalex.org/W2401183800","https://openalex.org/W4391898412","https://openalex.org/W2735859668","https://openalex.org/W2927104664","https://openalex.org/W4385069207","https://openalex.org/W4400936653","https://openalex.org/W2078824716","https://openalex.org/W3201941117","https://openalex.org/W2774282397","https://openalex.org/W4385731844"],"abstract_inverted_index":{"While":[0],"deep":[1,106],"neural":[2],"network":[3],"(DNN)":[4],"models":[5,108],"are":[6],"mainly":[7],"trained":[8],"using":[9],"GPUs,":[10],"many":[11],"companies":[12],"and":[13,29,44,64,83,120,123,157,188],"research":[14],"institutions":[15],"build":[16],"shared":[17],"GPU":[18,40,98,169],"clusters.":[19],"These":[20],"clusters":[21],"host":[22],"DNN":[23,26,36,50,85,185],"training":[24,37,77,118],"jobs,":[25,28,122],"inference":[27,51,86,121,154,186],"CPU":[30,45,63,94,113,146,193],"jobs":[31,38,52,87,119,187],"(jobs":[32],"in":[33,109],"traditional":[34],"areas).":[35],"require":[39],"for":[41,46,116,183],"main":[42],"computation":[43],"auxiliary":[47],"computation.":[48],"Some":[49],"could":[53],"rely":[54],"solely":[55],"on":[56,96,133],"CPU,":[57],"while":[58,176],"others":[59],"must":[60],"utilize":[61],"both":[62],"GPU.":[65],"Our":[66],"investigation":[67],"demonstrates":[68],"that":[69,84,166],"the":[70,92,97,134,178,189],"number":[71],"of":[72,91,111,143,174,180,192],"cores":[73,95],"allocated":[74],"to":[75,127],"a":[76,139,148,152,158],"job":[78,150,155],"significantly":[79],"impacts":[80],"its":[81],"performance,":[82],"can":[88],"make":[89],"use":[90],"limited":[93],"nodes.":[99],"To":[100],"accomplish":[101],"this,":[102],"we":[103,136],"characterize":[104],"representative":[105],"learning":[107],"terms":[110],"their":[112,117,125],"core":[114],"requirements":[115],"investigate":[124],"sensitivity":[126],"other":[128],"CPU-side":[129],"resource":[130],"contention.":[131],"Based":[132],"characterization,":[135],"propose":[137],"SODA,":[138],"scheduling":[140],"system":[141],"comprised":[142],"an":[144,172],"adaptive":[145],"allocator,":[147],"multi-array":[149],"scheduler,":[151],"hardware-aware":[153],"placer,":[156],"real-time":[159],"contention":[160],"eliminator.":[161],"The":[162],"experimental":[163],"results":[164],"indicate":[165],"SODA":[167],"increases":[168],"utilization":[170],"by":[171],"average":[173],"19.9%,":[175],"maintaining":[177],"quality":[179],"service":[181],"target":[182],"all":[184],"queuing":[190],"performance":[191],"jobs.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
