{"id":"https://openalex.org/W2798317693","doi":"https://doi.org/10.23919/date.2018.8342033","title":"SmartShuttle: Optimizing off-chip memory accesses for deep learning accelerators","display_name":"SmartShuttle: Optimizing off-chip memory accesses for deep learning accelerators","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2798317693","doi":"https://doi.org/10.23919/date.2018.8342033","mag":"2798317693"},"language":"en","primary_location":{"id":"doi:10.23919/date.2018.8342033","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2018.8342033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5100352041","display_name":"Jiajun Li","orcid":"https://orcid.org/0000-0002-7208-9345"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajun Li","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108793944","display_name":"Guihai Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guihai Yan","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102393841","display_name":"Wenyan L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyan Lu","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034121567","display_name":"Shuhao Jiang","orcid":"https://orcid.org/0000-0002-7706-063X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhao Jiang","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101372514","display_name":"Shijun Gong","orcid":"https://orcid.org/0000-0002-0887-316X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijun Gong","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018329525","display_name":"Jingya Wu","orcid":"https://orcid.org/0000-0003-4938-5899"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingya Wu","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023380073","display_name":"Xiaowei Li","orcid":"https://orcid.org/0000-0002-0874-814X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Li","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100352041"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":5.8496,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.97178288,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976999759674072,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.8723929524421692},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6929275393486023},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6735697984695435},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6329149603843689},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46581554412841797},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.46558892726898193},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.41241204738616943},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3540962338447571},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3505023717880249},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.33335357904434204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15792638063430786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8723929524421692},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6929275393486023},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6735697984695435},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6329149603843689},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46581554412841797},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.46558892726898193},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.41241204738616943},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3540962338447571},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3505023717880249},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33335357904434204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15792638063430786},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date.2018.8342033","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2018.8342033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2119144962","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2276486856","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2565305208","https://openalex.org/W2565851976","https://openalex.org/W2612076670","https://openalex.org/W2625457103","https://openalex.org/W2964299589","https://openalex.org/W4240168186","https://openalex.org/W4249932213","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W3120961607","https://openalex.org/W2098207691","https://openalex.org/W3148568549","https://openalex.org/W1648516568","https://openalex.org/W361036515","https://openalex.org/W4211178602","https://openalex.org/W2269474412","https://openalex.org/W4386903460","https://openalex.org/W2537599394","https://openalex.org/W2433923775"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Network":[2],"(CNN)":[3],"accelerators":[4,32],"are":[5],"rapidly":[6],"growing":[7],"in":[8,89],"popularity":[9],"as":[10,76],"a":[11,94],"promising":[12],"solution":[13],"for":[14,125,182,192],"deep":[15],"learning":[16],"based":[17],"applications.":[18],"Though":[19],"optimizations":[20],"on":[21,160],"computation":[22],"have":[23],"been":[24],"intensively":[25],"studied,":[26],"the":[27,56,70,83,98,106,138,153,161,172,200],"energy":[28,41,61],"efficiency":[29],"of":[30,72,86,96,100,155],"such":[31],"remains":[33],"limited":[34],"by":[35,204],"off-chip":[36,50,122],"memory":[37,51,123,162],"accesses":[38,71,99,124],"since":[39],"their":[40],"cost":[42],"is":[43,55],"magnitudes":[44],"higher":[45],"than":[46],"other":[47],"operations.":[48],"Minimizing":[49],"access":[52,163,181,191],"volume,":[53],"therefore,":[54],"key":[57],"to":[58,68,120,143],"further":[59],"improving":[60],"efficiency.":[62],"However,":[63],"we":[64],"observed":[65],"that":[66,169],"sticking":[67],"minimizing":[69,97],"one":[73],"data":[74,102,134,156],"type":[75],"many":[77],"prior":[78],"work":[79],"did":[80],"cannot":[81],"fit":[82],"varying":[84],"shapes":[85],"convolutional":[87,147,173],"layers":[88,174],"CNNs.":[90],"Hence,":[91],"there":[92],"exists":[93],"dilemma":[95],"which":[101,198],"type.":[103],"To":[104],"overcome":[105],"problem,":[107],"this":[108],"paper":[109],"proposed":[110],"an":[111],"adaptive":[112],"layer":[113],"partitioning":[114],"and":[115,137,158,178,188,206],"scheduling":[116],"scheme,":[117],"called":[118],"SmartShuttle,":[119],"minimize":[121],"CNN":[126],"accelerators.":[127],"Smartshuttle":[128],"can":[129],"adaptively":[130],"switch":[131],"among":[132],"different":[133,146],"reuse":[135],"schemes":[136],"corresponding":[139],"tiling":[140],"factor":[141],"settings":[142],"dynamically":[144],"match":[145],"layers.":[148],"Moreover,":[149],"SmartShuttle":[150,170],"thoroughly":[151],"investigates":[152],"impact":[154],"reusability":[157],"sparsity":[159],"volume.":[164],"The":[165],"experimental":[166],"results":[167],"show":[168],"processes":[171],"at":[175],"434.8":[176],"multiply":[177],"accumulations":[179],"(MACs)/DRAM":[180],"VGG16":[183],"(batch":[184,194],"size":[185,195],"=":[186,196],"3),":[187],"526.3":[189],"MACs/DRAM":[190],"AlexNet":[193],"4),":[197],"outperforms":[199],"state-of-the-art":[201],"approach":[202],"(Eyeriss)":[203],"52.2%":[205],"52.6%,":[207],"respectively.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}