{"id":"https://openalex.org/W4415707232","doi":"https://doi.org/10.1109/tcc.2025.3626959","title":"Resource Aware Deep Learning Model Partitioning and Allocation for Inference Task in Clusters With Heterogeneous Graphics Processing Units","display_name":"Resource Aware Deep Learning Model Partitioning and Allocation for Inference Task in Clusters With Heterogeneous Graphics Processing Units","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4415707232","doi":"https://doi.org/10.1109/tcc.2025.3626959"},"language":"en","primary_location":{"id":"doi:10.1109/tcc.2025.3626959","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcc.2025.3626959","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cloud Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tcc.2025.3626959","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045799193","display_name":"Akishige Ikoma","orcid":"https://orcid.org/0009-0004-1496-4377"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akishige Ikoma","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Suita, Japan"],"raw_orcid":"https://orcid.org/0009-0004-1496-4377","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, Suita, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076346952","display_name":"Yuichi Ohsita","orcid":"https://orcid.org/0000-0001-9784-627X"},"institutions":[{"id":"https://openalex.org/I158123994","display_name":"Toyo University","ror":"https://ror.org/059d6yn51","country_code":"JP","type":"education","lineage":["https://openalex.org/I158123994"]},{"id":"https://openalex.org/I4210088412","display_name":"Toyonaka Municipal Hospital","ror":"https://ror.org/0056qeq43","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210088412"]},{"id":"https://openalex.org/I4210121970","display_name":"Osaka Prefectural Toyonaka Support School","ror":"https://ror.org/0359zqq03","country_code":"JP","type":"education","lineage":["https://openalex.org/I2800832783","https://openalex.org/I4210111617","https://openalex.org/I4210121970"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichi Ohsita","raw_affiliation_strings":["D3 Center, The University of Osaka, Toyonaka, Japan","Cybermedia Center, Osaka University, Toyonaka, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9784-627X","affiliations":[{"raw_affiliation_string":"D3 Center, The University of Osaka, Toyonaka, Japan","institution_ids":["https://openalex.org/I158123994","https://openalex.org/I4210088412","https://openalex.org/I4210121970"]},{"raw_affiliation_string":"Cybermedia Center, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019839911","display_name":"Masayuki Murata","orcid":"https://orcid.org/0000-0002-4168-2875"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Murata","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Osaka, Suita, Japan","Graduate School of Information Science and Technology, Osaka University, Suita, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4168-2875","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Osaka, Suita, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, Suita, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26718404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"4","first_page":"1105","last_page":"1118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.42260000109672546,"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":0.42260000109672546,"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/T14347","display_name":"Big Data and Digital Economy","score":0.24390000104904175,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.093299999833107,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6557000279426575},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6306999921798706},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5705000162124634},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5533000230789185},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5271999835968018},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5189999938011169},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5026000142097473},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4952999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438000082969666},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6557000279426575},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6146000027656555},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42239999771118164},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30970001220703125},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcc.2025.3626959","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcc.2025.3626959","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cloud Computing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01056:0007242623","is_oa":true,"landing_page_url":"https://hdl.handle.net/11094/103688","pdf_url":"https://ir.library.osaka-u.ac.jp/repo/ouka/all/103688/IEEETransCloudComput_13_4_1105.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Cloud Computing","raw_type":"journal article"},{"id":"pmh:oai:ir.library.osaka-u.ac.jp:11094/103688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TCC.2025.3626959","pdf_url":null,"source":{"id":"https://openalex.org/S4306402540","display_name":"OUKA (Osaka University Knowledge Archive) (Osaka University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98285908","host_organization_name":"The University of Osaka","host_organization_lineage":["https://openalex.org/I98285908"],"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:10.1109/tcc.2025.3626959","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcc.2025.3626959","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cloud Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1580022276","https://openalex.org/W2148869760","https://openalex.org/W2964667342","https://openalex.org/W2969388332","https://openalex.org/W4205916020","https://openalex.org/W4313496563","https://openalex.org/W4385781613","https://openalex.org/W4388041017","https://openalex.org/W4391164389","https://openalex.org/W4396878026"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"models":[3,27],"have":[4,10],"rapidly":[5],"evolved,":[6],"and":[7,30,60,65,80,130],"their":[8],"scales":[9],"become":[11],"larger.":[12],"Pipeline":[13],"parallelism":[14],"is":[15,72],"used":[16],"to":[17,36,41,83,105,141,183,192],"execute":[18,37,42,84],"a":[19,51,57],"large-scale":[20],"DL":[21,26,44,52,86,102,109,162,195],"model.":[22],"In":[23],"pipeline":[24],"parallelism,":[25],"are":[28],"partitioned":[29],"allocated":[31,68,131],"graphics":[32],"processing":[33],"units":[34],"(GPUs)":[35],"each":[38],"partition.":[39],"However,":[40],"numerous":[43],"services":[45,87,163,174],"in":[46,164],"clusters":[47,165],"with":[48,166],"heterogeneous":[49,167],"GPUs,":[50],"model":[53,78,128],"partitioning":[54,79,129],"that":[55,172],"considers":[56],"specific":[58],"type":[59],"number":[61],"of":[62,97,127,155,161],"GPUs":[63,67],"available":[64],"the":[66,70,90,95,114,125,153,159,184],"for":[69,100],"service":[71,103,110,134,148],"required.":[73],"We":[74,112,136,151],"propose":[75],"resource":[76,115,120,143],"aware":[77],"allocation":[81,96,116,144],"(RAMPA)":[82],"more":[85,173],"while":[88,146,178],"satisfying":[89,147,179],"performance":[91,149,180],"requirements.":[92,150],"RAMPA":[93,156,187],"minimizes":[94],"important":[98],"resources":[99,132],"future":[101,108],"execution":[104,160],"avoid":[106],"inhibiting":[107],"execution.":[111],"define":[113,137],"cost":[117],"based":[118],"on":[119,133],"importance.":[121],"Furthermore,":[122],"we":[123],"formulate":[124],"impact":[126],"performance.":[135],"an":[138],"optimization":[139],"problem":[140],"minimize":[142],"costs":[145],"evaluated":[152],"effectiveness":[154],"by":[157],"simulating":[158],"GPUs.":[168],"The":[169],"results":[170],"demonstrate":[171],"can":[175],"be":[176],"executed":[177],"requirements":[181],"compared":[182],"conventional":[185],"method.":[186],"enabled":[188],"efficient":[189],"GPU":[190],"utilization":[191],"deliver":[193],"many":[194],"services.":[196]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-30T00:00:00"}