{"id":"https://openalex.org/W2789246071","doi":"https://doi.org/10.1145/3174243.3174257","title":"Towards a Uniform Template-based Architecture for Accelerating 2D and 3D CNNs on FPGA","display_name":"Towards a Uniform Template-based Architecture for Accelerating 2D and 3D CNNs on FPGA","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2789246071","doi":"https://doi.org/10.1145/3174243.3174257","mag":"2789246071"},"language":"en","primary_location":{"id":"doi:10.1145/3174243.3174257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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/A5037428152","display_name":"Junzhong Shen","orcid":"https://orcid.org/0000-0001-6233-6800"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junzhong Shen","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101058401","display_name":"You Huang","orcid":"https://orcid.org/0000-0002-9006-1522"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Huang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034746334","display_name":"Zelong Wang","orcid":"https://orcid.org/0000-0001-8517-6862"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zelong Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102984199","display_name":"Yuran Qiao","orcid":"https://orcid.org/0000-0002-5488-3545"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuran Qiao","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710936","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-0944-2708"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyuan Zhang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037428152"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":6.6853,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.97580085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8364819288253784},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8096194267272949},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.802579402923584},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5698402523994446},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.5637180805206299},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5608364343643188},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4929008483886719},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4734867513179779},{"id":"https://openalex.org/keywords/cellular-neural-network","display_name":"Cellular neural network","score":0.41155123710632324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41045671701431274},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3792104721069336},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3755651116371155},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3632766604423523},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3623039722442627},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3547084927558899},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28434520959854126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27672240138053894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364819288253784},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8096194267272949},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.802579402923584},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5698402523994446},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5637180805206299},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5608364343643188},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4929008483886719},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4734867513179779},{"id":"https://openalex.org/C812465","wikidata":"https://www.wikidata.org/wiki/Q5058375","display_name":"Cellular neural network","level":3,"score":0.41155123710632324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41045671701431274},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3792104721069336},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3755651116371155},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3632766604423523},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3623039722442627},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3547084927558899},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28434520959854126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27672240138053894},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3174243.3174257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2090210354","https://openalex.org/W2094756095","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2261808795","https://openalex.org/W2276486856","https://openalex.org/W2294282016","https://openalex.org/W2301358467","https://openalex.org/W2341234201","https://openalex.org/W2520083297","https://openalex.org/W2525740295","https://openalex.org/W2565305208","https://openalex.org/W2574797063","https://openalex.org/W2584311934","https://openalex.org/W2584616277","https://openalex.org/W2585774018","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2625954420","https://openalex.org/W2626616508","https://openalex.org/W2767899175","https://openalex.org/W4249932213"],"related_works":["https://openalex.org/W1530050325","https://openalex.org/W206608699","https://openalex.org/W2024633643","https://openalex.org/W2489260869","https://openalex.org/W2000135173","https://openalex.org/W3133116121","https://openalex.org/W2625058759","https://openalex.org/W3195471267","https://openalex.org/W2971009090","https://openalex.org/W4295935044"],"abstract_inverted_index":{"Three-dimensional":[0],"convolutional":[1],"neural":[2],"networks":[3],"(3D":[4],"CNNs)":[5],"are":[6,71],"used":[7],"efficiently":[8],"in":[9,17,91,218],"many":[10],"computer":[11],"vision":[12],"applications.":[13],"Most":[14],"previous":[15],"work":[16],"this":[18,89],"area":[19],"has":[20],"concentrated":[21],"only":[22],"on":[23,39,46,113,148,172],"designing":[24],"and":[25,57,68,96,123,143,166,170,185,194,201,216,220,227],"optimizing":[26],"accelerators":[27,146,162],"for":[28,77,84,163,192],"2D":[29,67,79,95,122,142,165],"CNN,":[30],"with":[31,199],"few":[32],"attempts":[33],"made":[34],"to":[35,48,52,93,117,135,182,214,223],"accelerate":[36,94],"3D":[37,44,69,85,97,124,144,167],"CNN":[38,86,125,145],"FPGA.":[40],"We":[41],"find":[42],"accelerating":[43,78],"CNNs":[45,70,80,98,168],"FPGA":[47,174],"be":[49,82],"challenge":[50],"due":[51],"their":[53],"high":[54],"computational":[55],"complexity":[56],"storage":[58],"demands.":[59],"More":[60],"importantly,":[61],"although":[62],"the":[63,73,114,154,157],"computation":[64],"patterns":[65],"of":[66,121,141,156,208,212],"analogous,":[72],"conventional":[74],"approaches":[75],"adopted":[76],"may":[81],"unfit":[83],"acceleration.":[87],"In":[88],"paper,":[90],"order":[92],"using":[99],"a":[100,105,131,224,228,234],"uniform":[101,106,132],"framework,":[102],"we":[103,128,152,179],"propose":[104],"template-based":[107,158],"architecture":[108,159],"that":[109,205],"uses":[110],"templates":[111],"based":[112,147],"Winograd":[115],"algorithm":[116],"ensure":[118],"fast":[119],"development":[120],"accelerators.":[126],"Furthermore,":[127],"also":[129],"develop":[130],"analytical":[133],"model":[134],"facilitate":[136],"efficient":[137],"design":[138],"space":[139],"explorations":[140],"our":[149,206],"architecture.":[150],"Finally,":[151],"demonstrate":[153,204],"effectiveness":[155],"by":[160],"implementing":[161],"real-life":[164],"(VGG16":[169],"C3D)":[171],"multiple":[173],"platforms.":[175],"On":[176],"S2C":[177],"VUS440,":[178],"achieve":[180],"up":[181,213],"1.13":[183],"TOPS":[184,187],"1.11":[186],"under":[188],"low":[189],"resource":[190],"utilization":[191],"VGG16":[193],"C3D,":[195],"respectively.":[196],"End-to-end":[197],"comparisons":[198],"CPU":[200,225],"GPU":[202,235],"solutions":[203],"implementation":[207],"C3D":[209],"achieves":[210],"gains":[211],"13x":[215],"60x":[217],"performance":[219],"energy":[221,230],"relative":[222],"solution,":[226],"6.4x":[229],"efficiency":[231],"gain":[232],"over":[233],"solution.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}