{"id":"https://openalex.org/W4376851285","doi":"https://doi.org/10.1109/tpds.2023.3276759","title":"CD-MSA: Cooperative and Deadline-Aware Scheduling for Efficient Multi-Tenancy on DNN Accelerators","display_name":"CD-MSA: Cooperative and Deadline-Aware Scheduling for Efficient Multi-Tenancy on DNN Accelerators","publication_year":2023,"publication_date":"2023-05-16","ids":{"openalex":"https://openalex.org/W4376851285","doi":"https://doi.org/10.1109/tpds.2023.3276759"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3276759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3276759","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5018599297","display_name":"Chunyang Wang","orcid":"https://orcid.org/0000-0001-7861-1061"},"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"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunyang Wang","raw_affiliation_strings":["Sino-German Joint Software Institute, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7861-1061","affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593745","display_name":"Yuebin Bai","orcid":"https://orcid.org/0000-0002-2544-3989"},"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"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuebin Bai","raw_affiliation_strings":["Sino-German Joint Software Institute, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2544-3989","affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102728074","display_name":"Desen Sun","orcid":"https://orcid.org/0000-0001-8630-7959"},"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"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Desen Sun","raw_affiliation_strings":["Sino-German Joint Software Institute, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8630-7959","affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018599297"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.6608,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83727831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"7","first_page":"2091","last_page":"2106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9986000061035156,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8761394023895264},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6308587789535522},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6214390397071838},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5559327602386475},{"id":"https://openalex.org/keywords/preemption","display_name":"Preemption","score":0.5296269059181213},{"id":"https://openalex.org/keywords/multitenancy","display_name":"Multitenancy","score":0.4619358777999878},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4556460976600647},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3931419849395752},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32348594069480896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2943480610847473},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2723578214645386},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.1642395257949829},{"id":"https://openalex.org/keywords/software-as-a-service","display_name":"Software as a service","score":0.13948482275009155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8761394023895264},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6308587789535522},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6214390397071838},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5559327602386475},{"id":"https://openalex.org/C206952183","wikidata":"https://www.wikidata.org/wiki/Q1193100","display_name":"Preemption","level":2,"score":0.5296269059181213},{"id":"https://openalex.org/C69016650","wikidata":"https://www.wikidata.org/wiki/Q1364211","display_name":"Multitenancy","level":5,"score":0.4619358777999878},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4556460976600647},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3931419849395752},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32348594069480896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2943480610847473},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2723578214645386},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.1642395257949829},{"id":"https://openalex.org/C175133352","wikidata":"https://www.wikidata.org/wiki/Q1254596","display_name":"Software as a service","level":4,"score":0.13948482275009155},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2023.3276759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3276759","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6322973505","display_name":null,"funder_award_id":"61732002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7868964886","display_name":null,"funder_award_id":"51877004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8351171912","display_name":null,"funder_award_id":"61572062","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":51,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1968005108","https://openalex.org/W1976700965","https://openalex.org/W2097117768","https://openalex.org/W2127327557","https://openalex.org/W2131107106","https://openalex.org/W2146412113","https://openalex.org/W2151997543","https://openalex.org/W2194775991","https://openalex.org/W2442974303","https://openalex.org/W2525778437","https://openalex.org/W2570030068","https://openalex.org/W2606722458","https://openalex.org/W2883929540","https://openalex.org/W2982050681","https://openalex.org/W3014810041","https://openalex.org/W3016939927","https://openalex.org/W3036878841","https://openalex.org/W3043406639","https://openalex.org/W3043433718","https://openalex.org/W3043571714","https://openalex.org/W3097528158","https://openalex.org/W3097904259","https://openalex.org/W3098068080","https://openalex.org/W3101026687","https://openalex.org/W3114783092","https://openalex.org/W3127736057","https://openalex.org/W3142960365","https://openalex.org/W3157707676","https://openalex.org/W3158233068","https://openalex.org/W3158444059","https://openalex.org/W3159535809","https://openalex.org/W3179122174","https://openalex.org/W3190062760","https://openalex.org/W3206341493","https://openalex.org/W3208777667","https://openalex.org/W3211853974","https://openalex.org/W3215253865","https://openalex.org/W4200028128","https://openalex.org/W4200421900","https://openalex.org/W4200441752","https://openalex.org/W4293584584","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6727690538","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6750227808","https://openalex.org/W6779103662","https://openalex.org/W6798686915"],"related_works":["https://openalex.org/W2160425906","https://openalex.org/W1882733036","https://openalex.org/W2546696010","https://openalex.org/W4318020486","https://openalex.org/W2786808640","https://openalex.org/W4232352653","https://openalex.org/W2099266623","https://openalex.org/W2576563092","https://openalex.org/W2157044008","https://openalex.org/W1992741870"],"abstract_inverted_index":{"With":[0],"DNN":[1,146],"turning":[2],"into":[3,205],"the":[4,12,21,30,47,58,73,81,113,118,137,151,154,187,206,229],"backbone":[5],"of":[6,14,24,38],"AI":[7],"cloud":[8,25,114],"services":[9],"and":[10,35,49,60,67,87,94,104,122,163,235,244],"propelling":[11],"emergence":[13],"INFerence-as-a-Service":[15],"(INFaaS),":[16],"DNN-specific":[17],"accelerators":[18],"have":[19],"become":[20],"indispensable":[22],"components":[23],"inference":[26,115],"systems.":[27],"Due":[28],"to":[29,45,71,125,149,184,241],"conservative":[31],"\u201cone-task-at-a-time\u201d":[32],"working":[33],"mode":[34],"deadline":[36,82],"blindness":[37],"those":[39],"accelerators,":[40],"implementing":[41],"multi-tenancy":[42],"that":[43,116,201],"aims":[44],"improve":[46],"cost-effectiveness":[48],"meet":[50],"SLA":[51,232],"requirements":[52],"is":[53],"intractable.":[54],"Recent":[55],"studies":[56],"including":[57],"temporal":[59],"spatial":[61],"approaches,":[62],"employ":[63],"manifold":[64],"scheduling":[65],"mechanisms":[66],"sophisticated":[68],"architecture":[69,135],"innovations":[70],"address":[72],"challenge.":[74],"However,":[75],"these":[76],"researches":[77,218],"either":[78],"still":[79],"neglect":[80],"awareness":[83],"or":[84],"render":[85],"inevitable":[86],"expensive":[88],"hardware":[89,181],"overheads":[90],"such":[91],"as":[92],"switches":[93],"storage.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99,141,158,190],"present":[100],"<italic":[101,192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[102,193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Cooperative":[103],"Deadline-aware":[105],"Multi-Systolic-Array":[106],"scheduling</i>":[107],"(CD-MSA),":[108],"a":[109,144,160,198],"low-cost":[110],"solution":[111],"for":[112,153,174],"utilizes":[117],"real":[119],"time":[120],"mechanism":[121],"task-level":[123],"parallelism":[124],"enable":[126],"efficient":[127,170],"multi-tenancy.":[128],"Based":[129],"on":[130],"our":[131],"preemptive":[132],"multi-systolic-array":[133],"accelerator":[134],"supporting":[136],"simultaneous":[138],"task":[139,195],"co-location,":[140],"first":[142],"construct":[143],"fine-grained":[145],"execution":[147],"model":[148],"lay":[150],"groundwork":[152],"lightweight":[155],"preemption.":[156],"Second,":[157],"design":[159],"cooperative,":[161],"deadline-":[162],"laxity-aware":[164],"scheduler":[165],"in":[166],"conjunction":[167],"with":[168,215],"an":[169],"schedulability":[171],"test":[172],"method":[173],"better":[175],"QoS":[176],"guarantee":[177],"without":[178],"introducing":[179],"additional":[180],"cost.":[182],"Finally,":[183],"further":[185],"promote":[186],"overall":[188],"throughput,":[189,231],"propose":[191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">dynamic":[194],"fusion</i>":[196],",":[197],"software":[199],"approach":[200],"fuses":[202],"different":[203],"tasks":[204,209],"logically":[207],"\u201cmulti-threading\u201d":[208],"at":[210],"runtime.":[211],"We":[212],"compare":[213],"CD-MSA":[214,227],"several":[216],"state-of-the-art":[217],"across":[219],"three":[220],"multi-DNN":[221],"workloads.":[222],"The":[223],"evaluation":[224],"results":[225],"show":[226],"improves":[228],"latency-bounded":[230],"satisfaction":[233],"rate":[234],"weighted":[236],"system":[237],"throughput":[238],"by":[239],"up":[240],"62%,":[242],"63%":[243],"27%,":[245],"respectively.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
