{"id":"https://openalex.org/W2918845477","doi":"https://doi.org/10.23919/date.2019.8715272","title":"Towards Design Space Exploration and Optimization of Fast Algorithms for Convolutional Neural Networks (CNNs) on FPGAs","display_name":"Towards Design Space Exploration and Optimization of Fast Algorithms for Convolutional Neural Networks (CNNs) on FPGAs","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2918845477","doi":"https://doi.org/10.23919/date.2019.8715272","mag":"2918845477"},"language":"en","primary_location":{"id":"doi:10.23919/date.2019.8715272","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8715272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5060826708","display_name":"Afzal Ahmad","orcid":"https://orcid.org/0000-0003-4491-5440"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Afzal Ahmad","raw_affiliation_strings":["Department of Electrical Engineering, Lahore University of Management Sciences (LUMS), Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Lahore University of Management Sciences (LUMS), Lahore, Pakistan","institution_ids":["https://openalex.org/I207789805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069432255","display_name":"Muhammad Adeel Pasha","orcid":"https://orcid.org/0000-0001-9892-5201"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Adeel Pasha","raw_affiliation_strings":["Department of Electrical Engineering, Lahore University of Management Sciences (LUMS), Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Lahore University of Management Sciences (LUMS), Lahore, Pakistan","institution_ids":["https://openalex.org/I207789805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I207789805"],"apc_list":null,"apc_paid":null,"fwci":1.1174,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.81833785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1106","last_page":"1111"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9969000220298767,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7987991571426392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7862882614135742},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.7249181866645813},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.7247356176376343},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6888127326965332},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6314529180526733},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5658697485923767},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5223701596260071},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4839975833892822},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4648647904396057},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.431282639503479},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.4227650463581085},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3560919165611267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3164893388748169},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3153786063194275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28291016817092896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08321818709373474}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7987991571426392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862882614135742},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7249181866645813},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.7247356176376343},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6888127326965332},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6314529180526733},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5658697485923767},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5223701596260071},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4839975833892822},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4648647904396057},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.431282639503479},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.4227650463581085},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3560919165611267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3164893388748169},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3153786063194275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28291016817092896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08321818709373474},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date.2019.8715272","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8715272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W1487564550","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W2113929681","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2276486856","https://openalex.org/W2368124317","https://openalex.org/W2525740295","https://openalex.org/W2618530766","https://openalex.org/W2742152118","https://openalex.org/W6637373629","https://openalex.org/W6638020065","https://openalex.org/W6676968756","https://openalex.org/W6685214006","https://openalex.org/W6727759651"],"related_works":["https://openalex.org/W4282568311","https://openalex.org/W4313484792","https://openalex.org/W1995613452","https://openalex.org/W4388893884","https://openalex.org/W2951473296","https://openalex.org/W2883928845","https://openalex.org/W4288420200","https://openalex.org/W4285346947","https://openalex.org/W3145095675","https://openalex.org/W4365793791"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"gained":[5],"widespread":[6],"popularity":[7],"in":[8,90,130,135,155],"the":[9,68,84,107,113,117,138,160],"field":[10],"of":[11,22,71,74,86,116,151],"computer":[12],"vision":[13],"and":[14,93,100,109,127,132],"image":[15],"processing.":[16],"Due":[17],"to":[18,30,47,66,82,125,137,153],"huge":[19],"computational":[20,114],"requirements":[21],"CNNs,":[23],"dedicated":[24],"hardware-based":[25],"implementations":[26],"are":[27,43],"being":[28,45],"explored":[29],"improve":[31],"their":[32],"performance.":[33],"Hardware":[34],"platforms":[35],"such":[36],"as":[37],"Field":[38],"Programmable":[39],"Gate":[40],"Arrays":[41],"(FPGAs)":[42],"widely":[44],"used":[46],"design":[48,80,97,140],"parallel":[49,101],"architectures":[50],"for":[51],"this":[52,55],"purpose.":[53],"In":[54],"paper,":[56],"we":[57,148],"analyze":[58],"Winograd":[59,102],"minimal":[60],"filtering":[61],"or":[62],"fast":[63],"convolution":[64,103],"algorithms":[65],"reduce":[67],"arithmetic":[69],"complexity":[70,115],"convolutional":[72],"layers":[73],"CNNs.":[75],"We":[76,95],"explore":[77],"a":[78,98],"complex":[79],"space":[81],"find":[83],"sets":[85],"parameters":[87],"that":[88,105],"result":[89],"improved":[91],"throughput":[92,108,131],"power-efficiency.":[94],"also":[96],"pipelined":[99],"engine":[104],"improves":[106],"power-efficiency":[110],"while":[111,141],"reducing":[112],"overall":[118],"system.":[119],"Our":[120],"proposed":[121],"designs":[122],"show":[123],"up":[124,152],"4.75\u00d7":[126],"1.44\u00d7":[128],"improvements":[129],"power-efficiency,":[133],"respectively,":[134],"comparison":[136],"state-of-the-art":[139,161],"using":[142],"approximately":[143],"2.67\u00d7":[144],"more":[145],"multipliers.":[146],"Furthermore,":[147],"obtain":[149],"savings":[150],"53.6%":[154],"logic":[156],"resources":[157],"compared":[158],"with":[159],"implementation.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}