{"id":"https://openalex.org/W3208777667","doi":"https://doi.org/10.1145/3458817.3476143","title":"Enable simultaneous DNN services based on deterministic operator overlap and precise latency prediction","display_name":"Enable simultaneous DNN services based on deterministic operator overlap and precise latency prediction","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3208777667","doi":"https://doi.org/10.1145/3458817.3476143","mag":"3208777667"},"language":"en","primary_location":{"id":"doi:10.1145/3458817.3476143","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-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/A5008837660","display_name":"Weihao Cui","orcid":"https://orcid.org/0000-0002-6646-5260"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weihao Cui","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063596525","display_name":"Han Zhao","orcid":"https://orcid.org/0000-0002-1561-5329"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018118687","display_name":"Ningxin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningxin Zheng","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047571832","display_name":"Jieru Zhao","orcid":"https://orcid.org/0000-0001-8211-2812"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieru Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055733274","display_name":"Zhuo Song","orcid":"https://orcid.org/0009-0003-3244-5186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Song","raw_affiliation_strings":["Alibaba Cloud"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103896366","display_name":"Tao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Ma","raw_affiliation_strings":["Alibaba Cloud"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051050779","display_name":"Yong Yang","orcid":"https://orcid.org/0000-0002-4943-5625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Yang","raw_affiliation_strings":["Alibaba Cloud"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388741","display_name":"Chao Li","orcid":"https://orcid.org/0000-0003-1932-7698"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5008837660"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":6.8835,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.97082808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.996399998664856,"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/abacus","display_name":"Abacus (architecture)","score":0.8309861421585083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8089762926101685},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7947146892547607},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.6574743986129761},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.656294584274292},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.5073229670524597},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.42344406247138977},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40711402893066406},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2580910921096802},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08516153693199158},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07681387662887573}],"concepts":[{"id":"https://openalex.org/C205724471","wikidata":"https://www.wikidata.org/wiki/Q208454","display_name":"Abacus (architecture)","level":2,"score":0.8309861421585083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089762926101685},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7947146892547607},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.6574743986129761},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.656294584274292},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.5073229670524597},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42344406247138977},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40711402893066406},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2580910921096802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08516153693199158},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07681387662887573},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458817.3476143","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6378516902","display_name":null,"funder_award_id":"62022057, 61832006, 61632017, 61872240","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2153635508","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2323909431","https://openalex.org/W2442974303","https://openalex.org/W2528800812","https://openalex.org/W2734941459","https://openalex.org/W2790601347","https://openalex.org/W2792839191","https://openalex.org/W2811206245","https://openalex.org/W2904487346","https://openalex.org/W2950683227","https://openalex.org/W2963516811","https://openalex.org/W2971710145","https://openalex.org/W2982157693","https://openalex.org/W2982899198","https://openalex.org/W2986864338","https://openalex.org/W3005664618","https://openalex.org/W3011377185","https://openalex.org/W3014817752","https://openalex.org/W3017091196","https://openalex.org/W3033527233","https://openalex.org/W3043406639","https://openalex.org/W3047875636","https://openalex.org/W3089332930","https://openalex.org/W3096484587","https://openalex.org/W3098087397","https://openalex.org/W3116103263","https://openalex.org/W3131071874","https://openalex.org/W3156127671","https://openalex.org/W3214476430","https://openalex.org/W4288113322","https://openalex.org/W4401785208"],"related_works":["https://openalex.org/W2726467123","https://openalex.org/W2064726690","https://openalex.org/W4252678288","https://openalex.org/W4254065731","https://openalex.org/W221518970","https://openalex.org/W2404584980","https://openalex.org/W3093483503","https://openalex.org/W1607297154","https://openalex.org/W4210820789","https://openalex.org/W4205975583"],"abstract_inverted_index":{"While":[0],"user-facing":[1],"services":[2,8,16,62],"experience":[3],"diurnal":[4],"load":[5],"patterns,":[6],"co-locating":[7,15],"improve":[9],"hardware":[10],"utilization.":[11],"Prior":[12],"work":[13],"on":[14,17,143],"GPUs":[18],"run":[19,115],"queries":[20,27],"sequentially,":[21],"as":[22,118],"the":[23,26,40,49,91,94,101,106,111,116,122,134,139],"latencies":[24,92],"of":[25,48,75,93,109,133],"are":[28,44],"neither":[29],"stable":[30],"nor":[31],"predictable":[32],"when":[33],"running":[34],"simultaneously.":[35,63],"The":[36,88,98,113],"input":[37],"sensitiveness":[38],"and":[39,84,137],"non-deterministic":[41],"operator":[42,67,96,103,124],"overlap":[43,68,104],"two":[45],"primary":[46],"factors":[47],"latency":[50,71,78],"unpredictability.":[51],"Hence,":[52],"We":[53],"propose":[54],"Abacus,":[55],"a":[56,80],"runtime":[57],"system":[58],"that":[59,129],"runs":[60],"multiple":[61],"Abacus":[64,73,130],"enables":[65],"deterministic":[66,95,123],"to":[69,120],"enforce":[70],"predictability.":[72],"composes":[74],"an":[76],"overlap-aware":[77],"predictor,":[79],"headroom-based":[81],"query":[82],"controller,":[83],"segmental":[85],"model":[86],"executors.":[87],"predictor":[89],"predicts":[90],"overlap.":[97,125],"controller":[99],"determines":[100],"appropriate":[102],"for":[105],"QoS":[107,135],"guarantee":[108],"all":[110],"services.":[112],"executors":[114],"operators":[117],"needed":[119],"support":[121],"Our":[126],"evaluation":[127],"shows":[128],"reduces":[131],"51.3%":[132],"violation":[136],"improves":[138],"throughput":[140],"by":[141],"29.8%":[142],"average":[144],"compared":[145],"with":[146],"state-of-the-art":[147],"solutions.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":11}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}
