{"id":"https://openalex.org/W4409282409","doi":"https://doi.org/10.1145/3676536.3676718","title":"GACER: Granularity-Aware ConcurrEncy Regulation for Multi-Tenant Deep Learning","display_name":"GACER: Granularity-Aware ConcurrEncy Regulation for Multi-Tenant Deep Learning","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409282409","doi":"https://doi.org/10.1145/3676536.3676718"},"language":"en","primary_location":{"id":"doi:10.1145/3676536.3676718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676718","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676718","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 43rd IEEE/ACM International Conference on Computer-Aided Design","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/10.1145/3676536.3676718","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101011040","display_name":"Yongbo Yu","orcid":"https://orcid.org/0009-0004-7314-001X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongbo Yu","raw_affiliation_strings":["George Mason University, Fairfax, United States"],"raw_orcid":"https://orcid.org/0009-0004-7314-001X","affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, United States","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103085687","display_name":"Fuxun Yu","orcid":"https://orcid.org/0000-0002-4880-6658"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuxun Yu","raw_affiliation_strings":["Microsoft, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-4880-6658","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073942971","display_name":"Zhi Tian","orcid":"https://orcid.org/0000-0002-2738-6826"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Tian","raw_affiliation_strings":["George Mason University, Fairfax, USA"],"raw_orcid":"https://orcid.org/0000-0002-2738-6826","affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441957","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0003-2790-976X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2790-976X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56328559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"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":0.9972000122070312,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9675999879837036,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7526403665542603},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.6789199113845825},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6235962510108948},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3766394555568695},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3354218602180481},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.210270494222641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526403665542603},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.6789199113845825},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6235962510108948},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3766394555568695},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3354218602180481},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.210270494222641}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676536.3676718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676718","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676718","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 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3676536.3676718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676536.3676718","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3676536.3676718","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 43rd IEEE/ACM International Conference on Computer-Aided Design","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409282409.pdf","grobid_xml":"https://content.openalex.org/works/W4409282409.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2024122052","https://openalex.org/W2723293840","https://openalex.org/W2754493004","https://openalex.org/W2804032941","https://openalex.org/W2901299405","https://openalex.org/W2924515500","https://openalex.org/W2941870244","https://openalex.org/W2944851425","https://openalex.org/W2953901595","https://openalex.org/W2994850640","https://openalex.org/W3014807190","https://openalex.org/W3037749908","https://openalex.org/W3097411828","https://openalex.org/W3158444059","https://openalex.org/W3217445637","https://openalex.org/W4211092666","https://openalex.org/W4232902075","https://openalex.org/W4243035950","https://openalex.org/W4250981202","https://openalex.org/W4280489237","https://openalex.org/W4300850425","https://openalex.org/W4360831842","https://openalex.org/W4372271902"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746"],"abstract_inverted_index":{"As":[0],"deep":[1,111],"learning":[2,112],"continues":[3],"to":[4,9,29,48,106,155],"advance":[5,91],"and":[6,36,54,64,75,101,114,132,149,160],"is":[7,33],"applied":[8],"increasingly":[10],"complex":[11],"scenarios,":[12],"the":[13,41,51,92,99,145],"demand":[14],"for":[15,110],"concurrent":[16,57],"deployment":[17],"of":[18,61,87,94],"multiple":[19],"neural":[20],"network":[21],"models":[22,58],"has":[23],"arisen.":[24],"This":[25],"demand,":[26],"commonly":[27],"referred":[28],"as":[30,121],"multi-tenant":[31,134],"computing,":[32],"becoming":[34],"more":[35,37],"important.":[38],"However,":[39],"even":[40],"most":[42],"mature":[43],"GPU-based":[44],"computing":[45,95,135,158],"systems":[46],"struggle":[47],"adequately":[49],"address":[50],"significant":[52],"heterogeneity":[53],"complexity":[55],"among":[56],"in":[59,71],"terms":[60],"resource":[62,73,147],"allocation":[63],"runtime":[65],"scheduling.":[66],"And":[67,137],"this":[68,82],"usually":[69],"results":[70],"considerable":[72],"utilization":[74,148],"throughput":[76],"issues.":[77],"To":[78],"tackle":[79],"these":[80],"issues,":[81],"work":[83],"proposes":[84],"a":[85],"set":[86],"optimization":[88,126,163],"techniques":[89,117],"that":[90,128,141],"granularity":[93],"management":[96],"from":[97],"both":[98],"spatial":[100],"temporal":[102],"perspectives,":[103],"specifically":[104],"tailored":[105],"heterogeneous":[107],"model":[108],"compositions":[109],"inference":[113],"training.":[115],"These":[116],"are":[118],"further":[119],"integrated":[120],"GACER":[122,142],"---":[123],"an":[124],"automated":[125],"framework":[127],"provides":[129],"high-utilization,":[130],"high-throughput,":[131],"low-latency":[133],"support.":[136],"our":[138],"experiments":[139],"demonstrate":[140],"significantly":[143],"improves":[144],"overall":[146],"consistently":[150],"achieves":[151],"outstanding":[152],"speedups":[153],"compared":[154],"native":[156],"GPU":[157],"frameworks":[159],"existing":[161],"state-of-the-art":[162],"works.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}