{"id":"https://openalex.org/W4386707684","doi":"https://doi.org/10.1145/3605573.3605627","title":"SPLIT: QoS-Aware DNN Inference on Shared GPU via Evenly-Sized Model Splitting","display_name":"SPLIT: QoS-Aware DNN Inference on Shared GPU via Evenly-Sized Model Splitting","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386707684","doi":"https://doi.org/10.1145/3605573.3605627"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605627","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605627","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605573.3605627","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3605573.3605627","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026437423","display_name":"Diaohan Luo","orcid":"https://orcid.org/0000-0002-4063-6818"},"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":"Diaohan Luo","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-4063-6818","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101636319","display_name":"Yu Tian","orcid":"https://orcid.org/0009-0000-6623-1491"},"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":"Tian Yu","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0000-6623-1491","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, 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":["Institute of Software, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-1323-2455","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Wu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, China and Chongqing School, University of Chinese Academy of Science, China"],"raw_orcid":"https://orcid.org/0000-0001-7903-5879","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China and Chongqing School, University of Chinese Academy of Science, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687362","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0001-5350-9773"},"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":"Tao Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-5350-9773","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"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/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":["Institute of Software, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, Nanjing, and Nanjing Institute of Software Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-0237-5100","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, Nanjing, and Nanjing Institute of Software Technology, China","institution_ids":["https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6737,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71565753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"605","last_page":"614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.8198062777519226},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8192489743232727},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7819489240646362},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.6743623614311218},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6549509763717651},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6115128993988037},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5507984757423401},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5321632623672485},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5097503066062927},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.46117791533470154},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3813377022743225},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3657143712043762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3422256112098694},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.24228915572166443},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.18915089964866638},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10690030455589294},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.09849914908409119}],"concepts":[{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.8198062777519226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192489743232727},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7819489240646362},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.6743623614311218},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6549509763717651},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6115128993988037},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5507984757423401},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5321632623672485},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5097503066062927},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.46117791533470154},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3813377022743225},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3657143712043762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3422256112098694},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24228915572166443},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.18915089964866638},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10690030455589294},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.09849914908409119},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605573.3605627","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605627","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605573.3605627","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3605573.3605627","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605627","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605573.3605627","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1109687085","display_name":"\u65e0\u670d\u52a1\u5668\u67b6\u6784\u673a\u5668\u5b66\u4e60\u7684\u8ba1\u7b97\u6a21\u578b\u4e0e\u7cfb\u7edf\u6846\u67b6\u7814\u7a76","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386707684.pdf","grobid_xml":"https://content.openalex.org/works/W4386707684.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2144390195","https://openalex.org/W2409233683","https://openalex.org/W2570343428","https://openalex.org/W2623902153","https://openalex.org/W2787114603","https://openalex.org/W2919064223","https://openalex.org/W2931092525","https://openalex.org/W2934853022","https://openalex.org/W2969388332","https://openalex.org/W2982157693","https://openalex.org/W3014367186","https://openalex.org/W3016939927","https://openalex.org/W3096858590","https://openalex.org/W3097411828","https://openalex.org/W3101026687","https://openalex.org/W3113399930","https://openalex.org/W3169411694","https://openalex.org/W3176615255","https://openalex.org/W3186289964","https://openalex.org/W3203452446","https://openalex.org/W3205395194","https://openalex.org/W3217445637","https://openalex.org/W4214597292","https://openalex.org/W4235366964","https://openalex.org/W4283020086","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W1480207378","https://openalex.org/W2052495274","https://openalex.org/W2166100863","https://openalex.org/W2119926828","https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4313526662","https://openalex.org/W3111395152","https://openalex.org/W4312996489","https://openalex.org/W3106131444"],"abstract_inverted_index":{"Improving":[0],"QoS":[1],"by":[2],"simultaneously":[3],"reducing":[4],"the":[5,12,35],"latency":[6],"violation":[7],"rate":[8],"and":[9],"jitter":[10],"in":[11],"presence":[13],"of":[14],"multiple":[15],"deep":[16],"learning":[17],"inference":[18],"(DLI)":[19],"tasks":[20],"sharing":[21],"a":[22,28],"single":[23],"edge":[24],"computing":[25],"processor":[26],"remains":[27],"challenge.":[29],"However,":[30],"existing":[31],"DLI":[32],"systems":[33],"at":[34],"edge,":[36],"designed":[37],"to":[38],"maximize":[39],"throughput,":[40],"face":[41],"performance":[42],"challenges":[43],"when":[44],"confronted":[45],"with":[46,48],"requests":[47],"varying":[49],"QoS.":[50]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
