{"id":"https://openalex.org/W4360831984","doi":"https://doi.org/10.1109/hpca56546.2023.10071035","title":"MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networks","display_name":"MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networks","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4360831984","doi":"https://doi.org/10.1109/hpca56546.2023.10071035"},"language":"en","primary_location":{"id":"doi:10.1109/hpca56546.2023.10071035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.05843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027053870","display_name":"Seah Kim","orcid":"https://orcid.org/0000-0002-9581-1222"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seah Kim","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015017700","display_name":"Hasan Genc","orcid":"https://orcid.org/0000-0001-8596-6135"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasan Genc","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011397869","display_name":"Vadim Vadimovich Nikiforov","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vadim Vadimovich Nikiforov","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035134864","display_name":"Krste Asanovi\u0107","orcid":"https://orcid.org/0000-0003-0754-3975"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krste Asanovi\u0107","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041784384","display_name":"Borivoje Nikoli\u0107","orcid":"https://orcid.org/0000-0003-2324-1715"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Borivoje Nikoli\u0107","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008683881","display_name":"Yakun Sophia Shao","orcid":"https://orcid.org/0000-0003-1811-5407"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yakun Sophia Shao","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027053870"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":3.6727,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94597839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"828","last_page":"841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8294293880462646},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7803627252578735},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.6830419898033142},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5677571296691895},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4508504569530487},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42850640416145325},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.42423027753829956},{"id":"https://openalex.org/keywords/service-level-agreement","display_name":"Service-level agreement","score":0.42332231998443604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33144912123680115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07997003197669983},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07174292206764221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294293880462646},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7803627252578735},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.6830419898033142},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5677571296691895},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4508504569530487},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42850640416145325},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.42423027753829956},{"id":"https://openalex.org/C2778160497","wikidata":"https://www.wikidata.org/wiki/Q869830","display_name":"Service-level agreement","level":3,"score":0.42332231998443604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33144912123680115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07997003197669983},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07174292206764221},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca56546.2023.10071035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.05843","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05843","pdf_url":"https://arxiv.org/pdf/2305.05843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.05843","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05843","pdf_url":"https://arxiv.org/pdf/2305.05843","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6831451530","display_name":null,"funder_award_id":"1955450","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4360831984.pdf"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1983394510","https://openalex.org/W2022832305","https://openalex.org/W2029102646","https://openalex.org/W2060032722","https://openalex.org/W2094833706","https://openalex.org/W2097117768","https://openalex.org/W2102709380","https://openalex.org/W2109707174","https://openalex.org/W2112878711","https://openalex.org/W2126570805","https://openalex.org/W2129381159","https://openalex.org/W2132269953","https://openalex.org/W2143773524","https://openalex.org/W2150181997","https://openalex.org/W2156077332","https://openalex.org/W2160121678","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2323909431","https://openalex.org/W2545380179","https://openalex.org/W2570343428","https://openalex.org/W2605330055","https://openalex.org/W2606722458","https://openalex.org/W2884267664","https://openalex.org/W2889289513","https://openalex.org/W2893813411","https://openalex.org/W2896457183","https://openalex.org/W2899733099","https://openalex.org/W2929502194","https://openalex.org/W2931743911","https://openalex.org/W2940862705","https://openalex.org/W2953212265","https://openalex.org/W2962970995","https://openalex.org/W2964187693","https://openalex.org/W2964248288","https://openalex.org/W2979245724","https://openalex.org/W3006129853","https://openalex.org/W3015395436","https://openalex.org/W3016939927","https://openalex.org/W3029192705","https://openalex.org/W3043406639","https://openalex.org/W3043571714","https://openalex.org/W3101026687","https://openalex.org/W3147312088","https://openalex.org/W3158233068","https://openalex.org/W3159535809","https://openalex.org/W3213528054","https://openalex.org/W4214512541","https://openalex.org/W4229703929","https://openalex.org/W4236382111","https://openalex.org/W4240407149","https://openalex.org/W4241970061","https://openalex.org/W4244814458","https://openalex.org/W4244995015","https://openalex.org/W4253773507","https://openalex.org/W4280489237","https://openalex.org/W4297577098","https://openalex.org/W4300273322","https://openalex.org/W6695314431","https://openalex.org/W6755207826","https://openalex.org/W6759886010","https://openalex.org/W6769062451","https://openalex.org/W6775855348"],"related_works":["https://openalex.org/W3161249280","https://openalex.org/W2267059662","https://openalex.org/W2323516465","https://openalex.org/W2364268683","https://openalex.org/W4238615239","https://openalex.org/W4388411807","https://openalex.org/W1519906715","https://openalex.org/W2478803962","https://openalex.org/W3169430512","https://openalex.org/W2063960996"],"abstract_inverted_index":{"Driven":[0],"by":[1,160,166],"the":[2,23,31,39,103,130,144,148],"wide":[3],"adoption":[4],"of":[5,34,92,147],"deep":[6],"neural":[7],"networks":[8],"(DNNs)":[9],"across":[10],"different":[11,35],"application":[12],"domains,":[13],"multi-tenancy":[14,44,72],"execution,":[15],"where":[16],"multiple":[17],"DNNs":[18],"are":[19],"deployed":[20],"simultaneously":[21],"on":[22,82,118],"same":[24],"hardware,":[25],"has":[26],"been":[27],"proposed":[28],"to":[29,48,95,111,154,171],"satisfy":[30],"latency":[32,120],"requirements":[33],"applications":[36,94,128],"while":[37],"improving":[38],"overall":[40],"system":[41,73,158],"utilization.":[42],"However,":[43],"execution":[45],"could":[46],"lead":[47],"undesired":[49],"system-level":[50],"resource":[51,84],"contention,":[52],"causing":[53],"quality-of-service":[54],"(QoS)":[55],"degradation":[56],"for":[57,74],"latency-critical":[58],"applications.To":[59],"address":[60],"this":[61],"challenge,":[62],"we":[63],"propose":[64],"MoCA":[65,86,101,142],"<sup":[66],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[67],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[68],",":[69],"an":[70],"adaptive":[71],"DNN":[75,107],"accelerators.":[76],"Unlike":[77],"existing":[78],"solutions":[79],"that":[80,126,141],"focus":[81],"compute":[83],"partition,":[85],"dynamically":[87,112],"manages":[88],"shared":[89],"memory":[90,114],"resources":[91,131],"co-located":[93,127],"meet":[96],"their":[97,119,137],"QoS":[98],"targets.":[99],"Specifically,":[100],"leverages":[102],"regularities":[104],"in":[105],"both":[106],"operators":[108],"and":[109,122,164],"accelerators":[110],"modulate":[113],"access":[115],"rates":[116],"based":[117],"targets":[121],"user-defined":[123],"priorities":[124],"so":[125],"get":[129],"they":[132],"demand":[133],"without":[134],"significantly":[135],"starving":[136],"co-runners.":[138],"We":[139],"demonstrate":[140],"improves":[143],"satisfaction":[145],"rate":[146],"service":[149],"level":[150],"agreement":[151],"(SLA)":[152],"up":[153],"3.9\u00d7":[155],"(1.8\u00d7":[156],"average),":[157,163,169],"throughput":[159],"2.3\u00d7":[161],"(1.7\u00d7":[162],"fairness":[165],"1.3\u00d7":[167],"(1.2\u00d7":[168],"compared":[170],"prior":[172],"work.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}