{"id":"https://openalex.org/W3084718578","doi":"https://doi.org/10.1109/nvmsa51238.2020.9188176","title":"A Kernel Unfolding Approach to Trade Data Movement with Computation Power for CNN Acceleration","display_name":"A Kernel Unfolding Approach to Trade Data Movement with Computation Power for CNN Acceleration","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3084718578","doi":"https://doi.org/10.1109/nvmsa51238.2020.9188176","mag":"3084718578"},"language":"en","primary_location":{"id":"doi:10.1109/nvmsa51238.2020.9188176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nvmsa51238.2020.9188176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 9th Non-Volatile Memory Systems and Applications Symposium (NVMSA)","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/A5033438572","display_name":"Yueh-Han Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yueh-Han Wu","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020602495","display_name":"Tse-Yuan Wang","orcid":"https://orcid.org/0000-0003-0919-7252"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tse-Yuan Wang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073534245","display_name":"Yuan-Hao Chang","orcid":"https://orcid.org/0000-0002-1282-2111"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Hao Chang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056407308","display_name":"Tei\u2010Wei Kuo","orcid":"https://orcid.org/0000-0003-1974-0394"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tei-Wei Kuo","raw_affiliation_strings":["Hong Kong Institute for Advanced Study, City University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong Institute for Advanced Study, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104059482","display_name":"Hung-Sheng Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086683","display_name":"Macronix International (China)","ror":"https://ror.org/00yec5b88","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210086683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hung-Sheng Chang","raw_affiliation_strings":["Macronix Emerging System Lab, Macronix International Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Macronix Emerging System Lab, Macronix International Co., Ltd","institution_ids":["https://openalex.org/I4210086683"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033438572"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08327009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9987000226974487,"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":0.8344267010688782},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6646755337715149},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5904591083526611},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5642799735069275},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5507404208183289},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5506189465522766},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4882202446460724},{"id":"https://openalex.org/keywords/high-memory","display_name":"High memory","score":0.4730341136455536},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4544513523578644},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44712644815444946},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.4365122616291046},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3741114139556885},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36181211471557617},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3583250045776367},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3053155541419983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25546935200691223},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17640206217765808},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12617403268814087},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.10744839906692505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8344267010688782},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6646755337715149},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5904591083526611},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5642799735069275},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5507404208183289},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5506189465522766},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4882202446460724},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.4730341136455536},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4544513523578644},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44712644815444946},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.4365122616291046},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3741114139556885},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36181211471557617},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3583250045776367},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3053155541419983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25546935200691223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17640206217765808},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12617403268814087},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.10744839906692505},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nvmsa51238.2020.9188176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nvmsa51238.2020.9188176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 9th Non-Volatile Memory Systems and Applications Symposium (NVMSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1979804960","https://openalex.org/W2048266589","https://openalex.org/W2117696986","https://openalex.org/W2119144962","https://openalex.org/W2442974303","https://openalex.org/W2508602506","https://openalex.org/W2518281301","https://openalex.org/W2613989746","https://openalex.org/W2618530766","https://openalex.org/W2899084534","https://openalex.org/W2904260223","https://openalex.org/W2905557681","https://openalex.org/W2911491685","https://openalex.org/W2964299589"],"related_works":["https://openalex.org/W2547220881","https://openalex.org/W1603816627","https://openalex.org/W2532617734","https://openalex.org/W2543262377","https://openalex.org/W2056138949","https://openalex.org/W347959834","https://openalex.org/W3089341786","https://openalex.org/W2386943538","https://openalex.org/W2132401245","https://openalex.org/W3022440123"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNN)":[3],"achieves":[4],"human-level":[5],"accuracy":[6],"on":[7,20,29,51,78,125],"the":[8,17,21,30,40,44,52,66,106,122,144,152,164],"image":[9],"classification":[10],"applications.":[11],"However,":[12,75],"its":[13],"complicated":[14],"structure":[15],"brings":[16],"large":[18],"requirement":[19],"MAC":[22],"operations":[23],"and":[24,47,129,151],"result":[25],"in":[26,58,108,133],"huge":[27],"cost":[28,69,77],"data":[31,67],"movement.":[32],"In":[33],"addition,":[34],"this":[35],"situation":[36],"becomes":[37],"worse":[38],"when":[39],"asymmetric":[41],"growth":[42],"of":[43],"computing":[45,141],"power":[46],"memory":[48,59,131,145],"speed":[49],"happens":[50],"von":[53],"Neumann-based":[54],"architecture.":[55],"Recently,":[56],"processing":[57],"(PIM)":[60],"design":[61,166],"is":[62,83,118],"adopted":[63],"to":[64,104,110,120,138,170,175],"reduce":[65],"communication":[68],"by":[70],"storing":[71],"parameters":[72],"into":[73],"memory.":[74],"significant":[76],"feeding":[79,124],"input":[80,126],"feature":[81,127],"map":[82],"a":[84],"big":[85],"challenge,":[86],"especially":[87],"for":[88],"high":[89],"bandwidth":[90,146],"but":[91],"long":[92],"access":[93],"latency":[94],"PIM":[95,109,134,177],"devices.":[96],"Thus,":[97,143],"we":[98],"explore":[99],"an":[100],"idea":[101],"that":[102,163],"how":[103],"trade":[105],"space":[107],"eliminate":[111,121],"such":[112],"cost.":[113],"A":[114],"kernel":[115],"unfolding":[116],"technique":[117],"proposed":[119,165],"duplicated":[123],"map,":[128],"meanwhile,":[130],"cells":[132],"are":[135],"highly":[136],"utilized":[137,149],"achieve":[139,168],"peak":[140],"throughput.":[142],"could":[147,156,167],"be":[148,157],"efficiently":[150],"corresponding":[153],"execution":[154],"time":[155],"reduced":[158],"significantly.":[159],"The":[160],"results":[161],"show":[162],"up":[169],"16.2\u00d7":[171],"cycle":[172],"improvement":[173],"compared":[174],"traditional":[176],"designs.":[178]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}