{"id":"https://openalex.org/W2553762784","doi":"https://doi.org/10.1109/iccd.2016.7753296","title":"CNN-MERP: An FPGA-based memory-efficient reconfigurable processor for forward and backward propagation of convolutional neural networks","display_name":"CNN-MERP: An FPGA-based memory-efficient reconfigurable processor for forward and backward propagation of convolutional neural networks","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2553762784","doi":"https://doi.org/10.1109/iccd.2016.7753296","mag":"2553762784"},"language":"en","primary_location":{"id":"doi:10.1109/iccd.2016.7753296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2016.7753296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 34th International Conference on Computer Design (ICCD)","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/A5036250749","display_name":"Xushen Han","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xushen Han","raw_affiliation_strings":["Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110827563","display_name":"Dajiang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dajiang Zhou","raw_affiliation_strings":["Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707116","display_name":"Shihao Wang","orcid":"https://orcid.org/0000-0002-8688-1034"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shihao Wang","raw_affiliation_strings":["Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101598322","display_name":"Shinji Kimura","orcid":"https://orcid.org/0000-0002-9475-6858"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Kimura","raw_affiliation_strings":["Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":2.704,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93772731,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"320","last_page":"327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9987999796867371,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8197191953659058},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7224639058113098},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.6533712148666382},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6363211274147034},{"id":"https://openalex.org/keywords/reconfigurability","display_name":"Reconfigurability","score":0.6310713291168213},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6029370427131653},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5732542872428894},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.5185047388076782},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4697829782962799},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.46873554587364197},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43004006147384644},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.430037260055542},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3362029194831848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18360108137130737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197191953659058},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7224639058113098},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.6533712148666382},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6363211274147034},{"id":"https://openalex.org/C2780149590","wikidata":"https://www.wikidata.org/wiki/Q7302742","display_name":"Reconfigurability","level":2,"score":0.6310713291168213},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6029370427131653},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5732542872428894},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.5185047388076782},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4697829782962799},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.46873554587364197},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43004006147384644},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.430037260055542},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3362029194831848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18360108137130737},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd.2016.7753296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2016.7753296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 34th International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1665214252","https://openalex.org/W1990315422","https://openalex.org/W2009832130","https://openalex.org/W2019459561","https://openalex.org/W2044535169","https://openalex.org/W2048266589","https://openalex.org/W2051825853","https://openalex.org/W2070167224","https://openalex.org/W2094756095","https://openalex.org/W2117696986","https://openalex.org/W2125203716","https://openalex.org/W2144354855","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2289252105","https://openalex.org/W2290132443","https://openalex.org/W3004171485","https://openalex.org/W6622239757","https://openalex.org/W6637242042","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2152623100","https://openalex.org/W2096417281","https://openalex.org/W25204318","https://openalex.org/W2077035242","https://openalex.org/W2138895528","https://openalex.org/W3042643149","https://openalex.org/W1999203047","https://openalex.org/W3201977823","https://openalex.org/W2362203107","https://openalex.org/W2084703527"],"abstract_inverted_index":{"Large-scale":[0],"deep":[1],"convolutional":[2],"neural":[3],"networks":[4],"(CNNs)":[5],"are":[6,30,68],"widely":[7],"used":[8],"in":[9],"machine":[10],"learning":[11],"applications.":[12],"While":[13],"CNNs":[14],"involve":[15],"huge":[16],"complexity,":[17],"VLSI":[18,59,66],"(ASIC":[19],"and":[20,116,128,138],"FPGA)":[21],"chips":[22],"that":[23,100],"deliver":[24],"high-density":[25],"integration":[26],"of":[27,42,57,74,84,142,152,170],"computational":[28,43],"resources":[29],"regarded":[31,70],"as":[32,71],"a":[33,72,145,167],"promising":[34],"platform":[35],"for":[36,80],"CNN's":[37],"implementation.":[38],"At":[39],"massive":[40],"parallelism":[41],"units,":[44],"however,":[45],"the":[46,54,58,62,75,81,103,135,139,175,185],"external":[47,148],"memory":[48,98,149],"bandwidth,":[49,166],"which":[50,131,156,179],"is":[51,123,132,154,157,172,180],"constrained":[52],"by":[53],"pin":[55],"count":[56],"chip,":[60],"becomes":[61],"system":[63,168],"bottleneck.":[64],"Moreover,":[65],"solutions":[67],"usually":[69],"lack":[73],"flexibility":[76],"to":[77,90,125],"be":[78],"reconfigured":[79],"various":[82],"parameters":[83],"CNNs.":[85],"This":[86],"paper":[87],"presents":[88],"CNN-MERP":[89,94],"address":[91],"these":[92],"issues.":[93],"incorporates":[95],"an":[96,147],"efficient":[97,129],"hierarchy":[99],"significantly":[101],"reduces":[102],"bandwidth":[104,150],"requirements":[105],"from":[106],"multiple":[107],"optimizations":[108],"including":[109],"on/off-chip":[110],"data":[111,113,117],"allocation,":[112],"flow":[114],"optimization":[115],"reuse.":[118],"The":[119],"proposed":[120],"2-level":[121],"reconfigurability":[122],"utilized":[124],"enable":[126],"fast":[127],"reconfiguration,":[130],"based":[133],"on":[134],"control":[136],"logic":[137],"multiboot":[140],"feature":[141],"FPGA.":[143],"As":[144],"result,":[146],"requirement":[151],"1.94MB/GFlop":[153],"achieved,":[155],"55%":[158],"lower":[159],"than":[160,184],"prior":[161],"arts.":[162],"Under":[163],"limited":[164],"DRAM":[165],"throughput":[169],"1244GFlop/s":[171],"achieved":[173],"at":[174],"Vertex":[176],"UltraScale":[177],"platform,":[178],"5.48":[181],"times":[182],"higher":[183],"state-of-the-art":[186],"FPGA":[187],"implementations.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}