{"id":"https://openalex.org/W3016917092","doi":"https://doi.org/10.1109/hpca47549.2020.00051","title":"Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design","display_name":"Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3016917092","doi":"https://doi.org/10.1109/hpca47549.2020.00051","mag":"3016917092"},"language":"en","primary_location":{"id":"doi:10.1109/hpca47549.2020.00051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca47549.2020.00051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5010481801","display_name":"Xingyao Zhang","orcid":"https://orcid.org/0000-0002-8874-9520"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xingyao Zhang","raw_affiliation_strings":["ECOMS Lab, ECE Department, University of Houston, Houston, USA"],"affiliations":[{"raw_affiliation_string":"ECOMS Lab, ECE Department, University of Houston, Houston, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Future System Architecture (FSA) Lab, University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Future System Architecture (FSA) Lab, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024508481","display_name":"Chenhao Xie","orcid":"https://orcid.org/0000-0002-1399-0352"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenhao Xie","raw_affiliation_strings":["Pacific Northwest National Lab (PNNL), Richland, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab (PNNL), Richland, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378697","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0003-3653-7013"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["College of Information Engineering, Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101447392","display_name":"Weigong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigong Zhang","raw_affiliation_strings":["Beijing Advanced Innovation Center for Imaging Theory and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Imaging Theory and Technology, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016298390","display_name":"Xin Fu","orcid":"https://orcid.org/0000-0002-9458-4769"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Fu","raw_affiliation_strings":["ECOMS Lab, ECE Department, University of Houston, Houston, USA"],"affiliations":[{"raw_affiliation_string":"ECOMS Lab, ECE Department, University of Houston, Houston, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010481801"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":1.8563,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87685689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"542","last_page":"555"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8607743382453918},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5409906506538391},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5393974184989929},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5166340470314026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49319690465927124},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44950827956199646},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.43374839425086975},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.41269081830978394},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3647322654724121},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32596397399902344},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.27205079793930054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607743382453918},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5409906506538391},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5393974184989929},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5166340470314026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49319690465927124},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44950827956199646},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.43374839425086975},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.41269081830978394},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3647322654724121},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32596397399902344},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27205079793930054}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca47549.2020.00051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca47549.2020.00051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W603908379","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1975237352","https://openalex.org/W1977655452","https://openalex.org/W1981220134","https://openalex.org/W1981943579","https://openalex.org/W2000965124","https://openalex.org/W2048266589","https://openalex.org/W2083780116","https://openalex.org/W2084336274","https://openalex.org/W2086112773","https://openalex.org/W2097117768","https://openalex.org/W2102995204","https://openalex.org/W2107583051","https://openalex.org/W2112796928","https://openalex.org/W2126407742","https://openalex.org/W2128414660","https://openalex.org/W2130454051","https://openalex.org/W2194775991","https://openalex.org/W2204310803","https://openalex.org/W2279098554","https://openalex.org/W2335728318","https://openalex.org/W2342408547","https://openalex.org/W2345611555","https://openalex.org/W2508602506","https://openalex.org/W2510697685","https://openalex.org/W2517869808","https://openalex.org/W2518281301","https://openalex.org/W2518511512","https://openalex.org/W2588978745","https://openalex.org/W2590796488","https://openalex.org/W2605347906","https://openalex.org/W2611106620","https://openalex.org/W2613168994","https://openalex.org/W2613718673","https://openalex.org/W2760393804","https://openalex.org/W2775143585","https://openalex.org/W2785994986","https://openalex.org/W2799350897","https://openalex.org/W2800818619","https://openalex.org/W2802189604","https://openalex.org/W2805939409","https://openalex.org/W2809361304","https://openalex.org/W2885577113","https://openalex.org/W2899771611","https://openalex.org/W2901722832","https://openalex.org/W2904295992","https://openalex.org/W2904436509","https://openalex.org/W2904902077","https://openalex.org/W2905104204","https://openalex.org/W2905209374","https://openalex.org/W2906782360","https://openalex.org/W2907019248","https://openalex.org/W2911936770","https://openalex.org/W2913763165","https://openalex.org/W2914039041","https://openalex.org/W2917234738","https://openalex.org/W2945497771","https://openalex.org/W2951810231","https://openalex.org/W2953106684","https://openalex.org/W2963703618","https://openalex.org/W2970450854","https://openalex.org/W3005783121","https://openalex.org/W3101197104","https://openalex.org/W3118608800","https://openalex.org/W3149681544","https://openalex.org/W4232753305","https://openalex.org/W4239722617","https://openalex.org/W4288601955","https://openalex.org/W4297805688","https://openalex.org/W4302296459","https://openalex.org/W6600115225","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6633029124","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6703116779","https://openalex.org/W6733793881","https://openalex.org/W6743446608","https://openalex.org/W6747050675","https://openalex.org/W6748053814","https://openalex.org/W6750715008","https://openalex.org/W6751339499","https://openalex.org/W6752296312","https://openalex.org/W6756040250","https://openalex.org/W6756880974","https://openalex.org/W6757921179","https://openalex.org/W6758137187","https://openalex.org/W6758143911","https://openalex.org/W6787972765","https://openalex.org/W6884914804"],"related_works":["https://openalex.org/W2110265185","https://openalex.org/W2046863313","https://openalex.org/W2154356865","https://openalex.org/W2001585562","https://openalex.org/W4205541923","https://openalex.org/W2154560316","https://openalex.org/W2112804590","https://openalex.org/W2077105843","https://openalex.org/W2140286994","https://openalex.org/W3175523456"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,10,37,52,77,133,203,270],"CNNs":[4],"have":[5,99],"achieved":[6],"great":[7],"successes":[8],"in":[9,185,234,268],"image":[11,15,33,81],"processing":[12,233],"tasks,":[13],"e.g.,":[14],"recognition":[16],"and":[17,48,83,136,148,230,250],"object":[18,84],"detection.":[19,85],"Unfortunately,":[20],"traditional":[21],"CNN's":[22],"classification":[23],"is":[24],"found":[25],"to":[26,36,44,74,87,132,155],"be":[27],"easily":[28],"misled":[29],"by":[30,201],"increasingly":[31],"complex":[32],"features":[34,138],"due":[35,131],"usage":[38],"of":[39,51,90,95,139,183,206],"pooling":[40],"operations,":[41,97],"hence":[42],"unable":[43],"preserve":[45],"accurate":[46],"position":[47],"pose":[49],"information":[50],"objects.":[53],"To":[54,160],"address":[55,161],"this":[56],"challenge,":[57],"a":[58,92,166],"novel":[59],"neural":[60],"network":[61,275],"structure":[62],"called":[63],"Capsule":[64],"Network":[65],"has":[66],"been":[67,100],"proposed,":[68],"which":[69,151],"introduces":[70],"equivariance":[71],"through":[72,226],"capsules":[73],"significantly":[75],"enhance":[76],"learning":[78,116],"ability":[79],"for":[80,113,179,253],"segmentation":[82],"Due":[86],"its":[88],"requirement":[89],"performing":[91],"high":[93],"volume":[94],"matrix":[96],"CapsNets":[98,127],"generally":[101],"accelerated":[102],"on":[103,120,124,222,247],"modern":[104,125],"GPU":[105],"platforms":[106],"that":[107,195,239],"provide":[108],"highly":[109],"optimized":[110],"software":[111,158],"library":[112],"common":[114],"deep":[115],"tasks.":[117],"However,":[118],"based":[119],"our":[121,217,240],"performance":[122,249,266],"characterization":[123],"GPUs,":[126],"exhibit":[128],"low":[129],"efficiency":[130,225],"special":[134],"program":[135],"execution":[137],"their":[140],"routing":[141,198,212,271],"procedure,":[142],"including":[143],"massive":[144],"unshareable":[145],"intermediate":[146],"variables":[147],"intensive":[149],"synchronizations,":[150],"are":[152],"very":[153],"difficult":[154],"optimize":[156],"at":[157],"level.":[159],"these":[162],"challenges,":[163],"we":[164],"propose":[165],"hybrid":[167],"computing":[168,177],"architecture":[169],"design":[170,218,242],"named":[171],"PIM-CapsNet.":[172],"It":[173],"preserves":[174],"GPU's":[175],"on-chip":[176],"capability":[178,205],"accelerating":[180],"CNN":[181],"types":[182],"layers":[184],"CapsNet,":[186],"while":[187],"pipelining":[188],"with":[189,256,273],"an":[190],"off-chip":[191],"in-memory":[192],"acceleration":[193],"solution":[194],"effectively":[196],"tackles":[197],"procedure's":[199,213],"inefficiency":[200],"leveraging":[202],"processing-in-memory":[204],"today's":[207],"3D":[208],"stacked":[209],"memory.":[210,235],"Using":[211],"inherent":[214],"parallellization":[215],"feature,":[216],"enables":[219],"hierarchical":[220],"improvements":[221],"CapsNet":[223,254],"inference":[224],"minimizing":[227],"data":[228],"movement":[229],"maximizing":[231],"parallel":[232],"Evaluation":[236],"results":[237,262],"demonstrate":[238],"proposed":[241],"can":[243],"achieve":[244],"substantial":[245],"improvement":[246],"both":[248],"energy":[251],"savings":[252],"inference,":[255],"almost":[257],"zero":[258],"accuracy":[259],"loss.":[260],"The":[261],"also":[263],"suggest":[264],"good":[265],"scalability":[267],"optimizing":[269],"procedure":[272],"increasing":[274],"size.":[276]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}