{"id":"https://openalex.org/W3152616793","doi":"https://doi.org/10.1109/ipccc50635.2020.9391551","title":"Efficient Architecture Paradigm for Deep Learning Inference as a Service","display_name":"Efficient Architecture Paradigm for Deep Learning Inference as a Service","publication_year":2020,"publication_date":"2020-11-06","ids":{"openalex":"https://openalex.org/W3152616793","doi":"https://doi.org/10.1109/ipccc50635.2020.9391551","mag":"3152616793"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc50635.2020.9391551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc50635.2020.9391551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 39th International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100755394","display_name":"Jin Yu","orcid":"https://orcid.org/0009-0003-5995-2217"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yu","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073700416","display_name":"Xiaopeng Ke","orcid":"https://orcid.org/0009-0006-0039-4013"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Ke","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114549816","display_name":"Fengyuan Xu","orcid":"https://orcid.org/0000-0003-3388-7544"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyuan Xu","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101567031","display_name":"Hao Huang","orcid":"https://orcid.org/0009-0007-7160-0483"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0854,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40738388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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":0.9980999827384949,"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/T12127","display_name":"Software System Performance and Reliability","score":0.996999979019165,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9951000213623047,"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":0.8410993814468384},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7704254388809204},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5671311616897583},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5402163863182068},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5135924816131592},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4512570798397064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4459986388683319},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4444672763347626},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4443759322166443},{"id":"https://openalex.org/keywords/paradigm-shift","display_name":"Paradigm shift","score":0.4146168828010559},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33069175481796265},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32669126987457275},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23464804887771606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410993814468384},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7704254388809204},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5671311616897583},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5402163863182068},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5135924816131592},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4512570798397064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4459986388683319},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4444672763347626},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4443759322166443},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.4146168828010559},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33069175481796265},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32669126987457275},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23464804887771606},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc50635.2020.9391551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc50635.2020.9391551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 39th International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1984541135","https://openalex.org/W1995301561","https://openalex.org/W1996212904","https://openalex.org/W2013461472","https://openalex.org/W2033242260","https://openalex.org/W2067231500","https://openalex.org/W2158899491","https://openalex.org/W2163605009","https://openalex.org/W2401046687","https://openalex.org/W2403946837","https://openalex.org/W2460441129","https://openalex.org/W2583196029","https://openalex.org/W2741593962","https://openalex.org/W2793398195","https://openalex.org/W2804043544","https://openalex.org/W2809414288","https://openalex.org/W2946622848","https://openalex.org/W2952230511","https://openalex.org/W2963026732","https://openalex.org/W3099785009","https://openalex.org/W3100917375","https://openalex.org/W6683738474","https://openalex.org/W6684191040","https://openalex.org/W6712895981","https://openalex.org/W6713203776","https://openalex.org/W6718865826","https://openalex.org/W6742578501","https://openalex.org/W6749255846","https://openalex.org/W6763242850","https://openalex.org/W6785459971"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W4390723067"],"abstract_inverted_index":{"Deep":[0,36],"learning":[1,261],"(DL)":[2],"inference":[3,45,262],"has":[4,49,96],"been":[5],"broadly":[6],"used":[7],"and":[8,21,90,100,126,157,182,223,240],"shown":[9],"excellent":[10],"performance":[11],"in":[12,113,161,243],"many":[13],"intelligent":[14],"applications.":[15],"Unfortunately,":[16],"the":[17,65,78,91,117,124,132,162,167,185,198,213,216,221,228,254,268],"high":[18],"resource":[19],"consumption":[20],"training":[22],"efforts":[23],"of":[24,81,86,94,200,215],"sophisticated":[25],"models":[26],"present":[27],"obstacles":[28],"for":[29,111],"regular":[30],"users":[31],"to":[32,75,97,115,140,144,177,206],"enjoy":[33],"it.":[34,194],"Thus,":[35],"Learning":[37],"Inference":[38],"as":[39,148,150],"a":[40,84,105,135,154,237],"Service":[41],"(DIaaS),":[42],"offering":[43],"online":[44],"services":[46],"on":[47,109,193,272],"cloud,":[48],"earned":[50],"great":[51],"popularity":[52],"among":[53],"cloud":[54,110,155],"tenants":[55],"who":[56],"can":[57],"send":[58],"their":[59],"DIaaS":[60,76,82,95,112,142,160],"inputs":[61,80],"via":[62,187],"RPCs":[63],"across":[64],"internal":[66,88,201],"network.":[67],"However,":[68],"such":[69],"detached":[70,270],"architecture":[71,107,218,252,271],"paradigm":[72,108],"is":[73,170,203],"inappropriate":[74],"because":[77],"high-dimensional":[79],"consume":[83],"lot":[85],"precious":[87],"bandwidth":[89,202],"service":[92],"latency":[93],"be":[98],"low":[99],"stable.":[101],"We":[102,129],"therefore":[103],"propose":[104],"novel":[106],"order":[114],"address":[116],"above":[118],"two":[119],"problems":[120],"without":[121],"giving":[122],"up":[123],"security":[125],"maintenance":[127],"benefits.":[128],"first":[130],"leverage":[131],"SGX":[133],"technology,":[134],"strongly-protected":[136],"user":[137],"space":[138],"enclave,":[139],"bring":[141],"computation":[143,222],"its":[145,158],"input":[146],"source":[147],"close":[149],"possible,":[151],"i.e.":[152],"co-locating":[153],"tenant":[156],"subscribed":[159],"same":[163],"virtual":[164,175],"machine.":[165],"When":[166],"GPU":[168,180,186],"acceleration":[169],"needed,":[171],"we":[172,210,235],"migrate":[173],"this":[174,196],"machine":[176],"any":[178],"available":[179],"host":[181],"transparently":[183],"utilize":[184],"our":[188,250],"backend":[189],"computing":[190],"stack":[191],"installed":[192],"In":[195],"way":[197],"majority":[199],"saved":[204],"compared":[205],"traditional":[207,269],"paradigm.":[208],"Furthermore,":[209],"greatly":[211],"improve":[212],"efficiency":[214],"proposed":[217],"paradigm,":[219],"from":[220],"I/O":[224],"perspectives,":[225],"by":[226],"making":[227],"entire":[229],"data":[230],"flow":[231],"more":[232],"DL-oriented.":[233],"Finally,":[234],"implement":[236],"prototype":[238],"system":[239],"evaluate":[241],"it":[242],"real-world":[244],"scenarios.":[245],"The":[246],"experiments":[247],"show":[248],"that":[249],"locality-aware":[251],"achieves":[253],"average":[255],"single":[256],"CPU":[257],"(GPU)":[258],"based":[259],"deep":[260],"time":[263],"2.84X":[264],"(4.87X)":[265],"less":[266],"than":[267],"average.":[273]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}