{"id":"https://openalex.org/W2982157693","doi":"https://doi.org/10.1145/3341301.3359658","title":"Nexus","display_name":"Nexus","publication_year":2019,"publication_date":"2019-10-21","ids":{"openalex":"https://openalex.org/W2982157693","doi":"https://doi.org/10.1145/3341301.3359658","mag":"2982157693"},"language":"en","primary_location":{"id":"doi:10.1145/3341301.3359658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341301.3359658","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341301.3359658","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM Symposium on Operating Systems Principles","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/10.1145/3341301.3359658","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036308058","display_name":"Haichen Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haichen Shen","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021778628","display_name":"Lequn Chen","orcid":"https://orcid.org/0000-0003-0113-8397"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lequn Chen","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067667405","display_name":"Yuchen Jin","orcid":"https://orcid.org/0000-0003-4518-8660"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchen Jin","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102796536","display_name":"Liangyu Zhao","orcid":"https://orcid.org/0000-0001-5033-4867"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangyu Zhao","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066291927","display_name":"Bingyu Kong","orcid":null},"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":"Bingyu Kong","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030096283","display_name":"Matthai Philipose","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthai Philipose","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497042","display_name":"Arvind Krishnamurthy","orcid":"https://orcid.org/0000-0002-9505-9528"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Krishnamurthy","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103159653","display_name":"Ravi Sundaram","orcid":"https://orcid.org/0000-0001-5657-4298"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ravi Sundaram","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5036308058"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":7.6546,"has_fulltext":true,"cited_by_count":222,"citation_normalized_percentile":{"value":0.97874519,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"322","last_page":"337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9965999722480774,"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":0.8361625671386719},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6973086595535278},{"id":"https://openalex.org/keywords/nexus","display_name":"Nexus (standard)","score":0.6886528730392456},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6879144310951233},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6569469571113586},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5280319452285767},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5126597285270691},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5059110522270203},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.41133856773376465},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36683207750320435},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35288316011428833},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3257354497909546},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28624409437179565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22839507460594177},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.2008538544178009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361625671386719},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6973086595535278},{"id":"https://openalex.org/C148609458","wikidata":"https://www.wikidata.org/wiki/Q7021281","display_name":"Nexus (standard)","level":2,"score":0.6886528730392456},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6879144310951233},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6569469571113586},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5280319452285767},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5126597285270691},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5059110522270203},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.41133856773376465},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36683207750320435},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35288316011428833},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3257354497909546},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28624409437179565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22839507460594177},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2008538544178009},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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:10.1145/3341301.3359658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341301.3359658","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341301.3359658","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM Symposium on Operating Systems Principles","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3341301.3359658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341301.3359658","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341301.3359658","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5734622975","display_name":null,"funder_award_id":"CNS-1614717","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7667601692","display_name":"CSR: Small: Enabling Deep Neural Networks for Mobile-Cloud Applications","funder_award_id":"1614717","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/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982157693.pdf","grobid_xml":"https://content.openalex.org/works/W2982157693.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1557310162","https://openalex.org/W1958236864","https://openalex.org/W2011039300","https://openalex.org/W2062118960","https://openalex.org/W2102849319","https://openalex.org/W2112796928","https://openalex.org/W2112984492","https://openalex.org/W2120422789","https://openalex.org/W2148620466","https://openalex.org/W2149933564","https://openalex.org/W2155541015","https://openalex.org/W2155893237","https://openalex.org/W2161381512","https://openalex.org/W2163961697","https://openalex.org/W2194775991","https://openalex.org/W2300242332","https://openalex.org/W2325939864","https://openalex.org/W2402144811","https://openalex.org/W2412782625","https://openalex.org/W2468875367","https://openalex.org/W2530841038","https://openalex.org/W2550742086","https://openalex.org/W2563513434","https://openalex.org/W2599379624","https://openalex.org/W2734941459","https://openalex.org/W2752236330","https://openalex.org/W2798515322","https://openalex.org/W2885829265","https://openalex.org/W2899071864","https://openalex.org/W2919594608","https://openalex.org/W2952186347","https://openalex.org/W2963510045","https://openalex.org/W2964108773","https://openalex.org/W4230110863"],"related_works":["https://openalex.org/W3126909309","https://openalex.org/W4256360871","https://openalex.org/W2747100754","https://openalex.org/W3117832639","https://openalex.org/W2885513359","https://openalex.org/W2802787844","https://openalex.org/W1578170453","https://openalex.org/W2965101536","https://openalex.org/W2891178753","https://openalex.org/W3121214617"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,20,68,106,119],"problem":[3],"of":[4,14,22,52,57,76,105,118,130,143],"serving":[5],"Deep":[6],"Neural":[7],"Networks":[8],"(DNNs)":[9],"efficiently":[10],"from":[11,67],"a":[12,80,135],"cluster":[13],"GPUs.":[15],"In":[16,88],"order":[17],"to":[18,35,62,73,97],"realize":[19],"promise":[21],"very":[23],"low-cost":[24],"processing":[25],"made":[26],"by":[27],"accelerators":[28],"such":[29],"as":[30],"GPUs,":[31,53,94],"it":[32],"is":[33,79],"essential":[34],"run":[36],"them":[37],"at":[38,102,112],"sustained":[39],"high":[40],"utilization.":[41],"Doing":[42],"so":[43],"requires":[44],"cluster-scale":[45],"resource":[46],"management":[47],"that":[48,60,84],"performs":[49],"detailed":[50],"scheduling":[51],"reasoning":[54],"about":[55],"groups":[56],"DNN":[58],"invocations":[59],"need":[61],"be":[63],"co-scheduled,":[64],"and":[65],"moving":[66],"conventional":[69],"whole-DNN":[70],"execution":[71],"model":[72],"executing":[74],"fragments":[75],"DNNs.":[77],"Nexus":[78,108],"fully":[81],"implemented":[82],"system":[83],"includes":[85],"these":[86],"innovations.":[87],"large-scale":[89],"case":[90],"studies":[91],"on":[92,134,141],"16":[93],"when":[95],"required":[96],"stay":[98],"within":[99,128],"latency":[100,139],"constraints":[101],"least":[103],"99%":[104],"time,":[107],"can":[109],"process":[110],"requests":[111],"rates":[113],"1.8-12.7X":[114],"higher":[115],"than":[116],"state":[117],"art":[120],"systems":[121],"can.":[122],"A":[123],"long-running":[124],"multi-application":[125],"deployment":[126],"stays":[127],"84%":[129],"optimal":[131],"utilization":[132],"and,":[133],"100-GPU":[136],"cluster,":[137],"violates":[138],"SLOs":[140],"0.27%":[142],"requests.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2019-11-01T00:00:00"}