{"id":"https://openalex.org/W2795961274","doi":"https://doi.org/10.1109/tcad.2018.2824280","title":"Double MAC on a DSP: Boosting the Performance of Convolutional Neural Networks on FPGAs","display_name":"Double MAC on a DSP: Boosting the Performance of Convolutional Neural Networks on FPGAs","publication_year":2018,"publication_date":"2018-04-06","ids":{"openalex":"https://openalex.org/W2795961274","doi":"https://doi.org/10.1109/tcad.2018.2824280","mag":"2795961274"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2018.2824280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2018.2824280","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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/A5030318115","display_name":"Sugil Lee","orcid":"https://orcid.org/0000-0003-3092-6501"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sugil Lee","raw_affiliation_strings":["Neural Processing Research Center, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Neural Processing Research Center, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038577249","display_name":"Dae Woo Kim","orcid":"https://orcid.org/0000-0001-6533-8086"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daewoo Kim","raw_affiliation_strings":["School of ECE, Ulsan National Institute of Science and Technology, Ulsan, South Korea"],"affiliations":[{"raw_affiliation_string":"School of ECE, Ulsan National Institute of Science and Technology, Ulsan, South Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101637741","display_name":"Dong Thanh Nguyen","orcid":"https://orcid.org/0000-0001-5011-1313"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong Nguyen","raw_affiliation_strings":["School of ECE, Ulsan National Institute of Science and Technology, Ulsan, South Korea"],"affiliations":[{"raw_affiliation_string":"School of ECE, Ulsan National Institute of Science and Technology, Ulsan, South Korea","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100780257","display_name":"Jongeun Lee","orcid":"https://orcid.org/0000-0003-1523-2974"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongeun Lee","raw_affiliation_strings":["Neural Processing Research Center, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Neural Processing Research Center, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030318115"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.8262,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.85891467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"38","issue":"5","first_page":"888","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.998199999332428,"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":0.8427730798721313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8399081230163574},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7872812747955322},{"id":"https://openalex.org/keywords/verilog","display_name":"Verilog","score":0.6865454912185669},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.548326313495636},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5245828032493591},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5219746828079224},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.506166398525238},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.468201220035553},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.45829448103904724},{"id":"https://openalex.org/keywords/adder","display_name":"Adder","score":0.4523582458496094},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4162072539329529},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4071018099784851},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39375853538513184},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38877665996551514},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35676896572113037},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33352017402648926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2937505841255188},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23300701379776},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.09554654359817505}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8427730798721313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399081230163574},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7872812747955322},{"id":"https://openalex.org/C2779030575","wikidata":"https://www.wikidata.org/wiki/Q827773","display_name":"Verilog","level":3,"score":0.6865454912185669},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.548326313495636},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5245828032493591},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5219746828079224},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.506166398525238},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.468201220035553},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.45829448103904724},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.4523582458496094},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4162072539329529},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4071018099784851},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39375853538513184},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38877665996551514},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35676896572113037},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33352017402648926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2937505841255188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23300701379776},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09554654359817505},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcad.2018.2824280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2018.2824280","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.unist.ac.kr:201301/24220","is_oa":false,"landing_page_url":"https://scholarworks.unist.ac.kr/handle/201301/24220","pdf_url":null,"source":{"id":"https://openalex.org/S4306401118","display_name":"Scholarworks@UNIST (Ulsan National Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48566637","host_organization_name":"Ulsan National Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I48566637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"ARTICLE"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G7611891132","display_name":null,"funder_award_id":"2016M3A7B4909668","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G8840038583","display_name":null,"funder_award_id":"2E27810-18-P034","funder_id":"https://openalex.org/F4320322091","funder_display_name":"Korea Institute of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322091","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1841592590","https://openalex.org/W1902934009","https://openalex.org/W1974078116","https://openalex.org/W1990315422","https://openalex.org/W1991716621","https://openalex.org/W1998917233","https://openalex.org/W2048266589","https://openalex.org/W2053968820","https://openalex.org/W2068395868","https://openalex.org/W2094756095","https://openalex.org/W2097262165","https://openalex.org/W2117696986","https://openalex.org/W2138913040","https://openalex.org/W2155893237","https://openalex.org/W2162973524","https://openalex.org/W2163605009","https://openalex.org/W2276486856","https://openalex.org/W2285660444","https://openalex.org/W2286365479","https://openalex.org/W2289252105","https://openalex.org/W2289254158","https://openalex.org/W2294282016","https://openalex.org/W2341783944","https://openalex.org/W2368124317","https://openalex.org/W2402098947","https://openalex.org/W2546081786","https://openalex.org/W2593882908","https://openalex.org/W2612090114","https://openalex.org/W2613938013","https://openalex.org/W2625226188","https://openalex.org/W2963114950","https://openalex.org/W2963374099","https://openalex.org/W3024621361","https://openalex.org/W4236363946","https://openalex.org/W6637373629","https://openalex.org/W6638783484","https://openalex.org/W6639703010","https://openalex.org/W6674479107","https://openalex.org/W6674638574","https://openalex.org/W6683688612","https://openalex.org/W6684191040","https://openalex.org/W6696004547","https://openalex.org/W6696152683"],"related_works":["https://openalex.org/W4390550886","https://openalex.org/W3217463396","https://openalex.org/W2790557758","https://openalex.org/W2516396101","https://openalex.org/W3204929712","https://openalex.org/W4295102875","https://openalex.org/W2300671402","https://openalex.org/W2126882773","https://openalex.org/W2169963286","https://openalex.org/W3094476157"],"abstract_inverted_index":{"Deep":[0],"learning":[1,24],"workloads,":[2],"such":[3],"as":[4],"convolutional":[5],"neural":[6],"networks":[7],"(CNNs)":[8],"are":[9],"important":[10],"due":[11],"to":[12,32,54,113,154],"increasingly":[13],"demanding":[14],"high-performance":[15],"hardware":[16],"acceleration.":[17],"One":[18],"distinguishing":[19],"feature":[20],"of":[21,60,74,89,128],"a":[22,47,129,159],"deep":[23],"workload":[25],"is":[26,29],"that":[27],"it":[28,112],"inherently":[30],"resilient":[31],"small":[33],"numerical":[34],"errors":[35],"and":[36,103,106,149],"thus":[37],"works":[38],"very":[39],"well":[40],"with":[41],"low":[42],"precision":[43],"hardware.":[44],"We":[45,80,95],"propose":[46],"novel":[48],"method":[49,99,109],"called":[50],"double":[51,56,119,124],"multiply-and-accumulate":[52],"(MAC)":[53],"theoretically":[55],"the":[57,87,92,114,125,133,140,146,167],"computation":[58,126],"rate":[59],"CNN":[61,93,116,130,147],"accelerators":[62],"by":[63,85,110],"packing":[64],"two":[65],"MAC":[66,120],"operations":[67],"into":[68],"one":[69],"digital":[70],"signal":[71],"processing":[72],"block":[73],"off-the-shelf":[75],"field-programmable":[76],"gate":[77],"arrays":[78],"(FPGAs).":[79],"overcame":[81],"several":[82],"technical":[83],"challenges":[84],"exploiting":[86],"mode":[88],"operation":[90],"in":[91],"accelerator.":[94,117],"have":[96],"validated":[97],"our":[98,108],"through":[100],"FPGA":[101,150],"synthesis":[102],"Verilog":[104],"simulation,":[105],"evaluated":[107],"applying":[111],"state-of-the-art":[115,162],"The":[118],"approach":[121],"used":[122],"can":[123],"throughput":[127],"layer.":[131],"On":[132],"network":[134],"level":[135],"(all":[136],"convolution":[137],"layers":[138],"combined),":[139],"performance":[141],"improvement":[142],"varies":[143],"depending":[144],"on":[145],"application":[148],"size,":[151],"from":[152],"14%":[153],"more":[155],"than":[156],"80%":[157],"over":[158],"highly":[160],"optimized":[161],"accelerator":[163],"solution,":[164],"without":[165],"sacrificing":[166],"output":[168],"quality":[169],"significantly.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}