{"id":"https://openalex.org/W2808739938","doi":"https://doi.org/10.1109/tvlsi.2018.2825145","title":"Accelerating Convolutional Neural Network With FFT on Embedded Hardware","display_name":"Accelerating Convolutional Neural Network With FFT on Embedded Hardware","publication_year":2018,"publication_date":"2018-06-21","ids":{"openalex":"https://openalex.org/W2808739938","doi":"https://doi.org/10.1109/tvlsi.2018.2825145","mag":"2808739938"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2018.2825145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2018.2825145","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11603/15493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089657290","display_name":"Tahmid Abtahi","orcid":"https://orcid.org/0000-0001-9198-943X"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tahmid Abtahi","raw_affiliation_strings":["Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022091861","display_name":"Colin Shea","orcid":"https://orcid.org/0000-0002-3269-5244"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Shea","raw_affiliation_strings":["Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054888852","display_name":"Amey Kulkarni","orcid":"https://orcid.org/0000-0003-3061-8269"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amey Kulkarni","raw_affiliation_strings":["Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084010501","display_name":"Tinoosh Mohsenin","orcid":"https://orcid.org/0000-0001-5551-2124"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tinoosh Mohsenin","raw_affiliation_strings":["Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089657290"],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":6.808,"has_fulltext":true,"cited_by_count":150,"citation_normalized_percentile":{"value":0.9764748,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":"9","first_page":"1737","last_page":"1749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9947999715805054,"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":0.836337685585022},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8029309511184692},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.653348982334137},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5733126401901245},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5644000172615051},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4998478889465332},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4599418342113495},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4304999113082886},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3515671491622925},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.32998502254486084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2752199172973633},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24559569358825684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20161941647529602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836337685585022},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8029309511184692},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.653348982334137},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5733126401901245},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5644000172615051},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4998478889465332},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4599418342113495},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4304999113082886},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3515671491622925},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.32998502254486084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2752199172973633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24559569358825684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20161941647529602},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tvlsi.2018.2825145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2018.2825145","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"},{"id":"pmh:oai:mdsoar.org:11603/15493","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/15493","pdf_url":"http://hdl.handle.net/11603/15493","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Original File Name: Abtahi_umbc_0434M_11710.pdf","raw_type":"Text"},{"id":"doi:10.13016/m2brox-vazm","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2brox-vazm","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mdsoar.org:11603/15493","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/15493","pdf_url":"http://hdl.handle.net/11603/15493","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Original File Name: Abtahi_umbc_0434M_11710.pdf","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G7088958380","display_name":null,"funder_award_id":"1652703","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808739938.pdf","grobid_xml":"https://content.openalex.org/works/W2808739938.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1034159276","https://openalex.org/W1538131130","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1836465849","https://openalex.org/W1922123711","https://openalex.org/W1923002919","https://openalex.org/W2003368250","https://openalex.org/W2014307680","https://openalex.org/W2091708048","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2101251534","https://openalex.org/W2117130368","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2188648459","https://openalex.org/W2194775991","https://openalex.org/W2198342846","https://openalex.org/W2217896605","https://openalex.org/W2255738257","https://openalex.org/W2261806027","https://openalex.org/W2285660444","https://openalex.org/W2286256158","https://openalex.org/W2367563998","https://openalex.org/W2392474488","https://openalex.org/W2419597278","https://openalex.org/W2470394683","https://openalex.org/W2560540238","https://openalex.org/W2565305208","https://openalex.org/W2613215347","https://openalex.org/W2613288670","https://openalex.org/W2614143469","https://openalex.org/W2756829667","https://openalex.org/W2792923869","https://openalex.org/W2795242415","https://openalex.org/W2806076314","https://openalex.org/W2806476189","https://openalex.org/W2949117887","https://openalex.org/W2963340555","https://openalex.org/W2963542991","https://openalex.org/W2963751813","https://openalex.org/W4249932213","https://openalex.org/W6632100814","https://openalex.org/W6637373629","https://openalex.org/W6640442106","https://openalex.org/W6674330103","https://openalex.org/W6674914833","https://openalex.org/W6684191040","https://openalex.org/W6686164453","https://openalex.org/W6687483927","https://openalex.org/W6691901705","https://openalex.org/W6692444220","https://openalex.org/W6717177883","https://openalex.org/W6720898849","https://openalex.org/W6737516148"],"related_works":["https://openalex.org/W2524802307","https://openalex.org/W2466675884","https://openalex.org/W2951390974","https://openalex.org/W2997828269","https://openalex.org/W2907419422","https://openalex.org/W2047588290","https://openalex.org/W3185363859","https://openalex.org/W2440252907","https://openalex.org/W2329139001","https://openalex.org/W3116557650"],"abstract_inverted_index":{"Fueled":[0],"by":[1],"ImageNet":[2],"Large":[3],"Scale":[4],"Visual":[5],"Recognition":[6],"Challenge":[7],"and":[8,25,46,57,98,101,110,154,170,175,188,198,238,242,246,255,265,272,275,282,296,310,314,317,322,326,337],"Common":[9],"Objects":[10],"in":[11,22,105,118,231,269],"Context":[12],"competitions,":[13],"the":[14,39,70,129,166,202,233],"convolutional":[15],"neural":[16,51],"network":[17],"(CNN)":[18],"has":[19],"become":[20],"important":[21],"computer":[23],"vision":[24],"natural":[26],"language":[27],"processing.":[28],"However,":[29],"state-of-the-art":[30],"CNNs":[31],"are":[32,186],"computationally":[33],"memory-intensive,":[34],"thus":[35,68],"energy-efficient":[36,321],"implementation":[37],"on":[38,133,160,207],"embedded":[40,119],"platform":[41],"is":[42,75,288,307],"challenging.":[43],"Recently,":[44],"VGGNet":[45],"ResNet":[47],"showed":[48],"that":[49],"deep":[50],"networks":[52,117],"with":[53,128,190,213,217],"more":[54,294,320],"convolution":[55,73,90,96,103],"layers":[56,62,74],"a":[58,134,218],"few":[59],"fully":[60],"connected":[61],"can":[63],"achieve":[64],"lower":[65],"error":[66],"rates,":[67],"reducing":[69],"complexity":[71,109],"of":[72,76,86,107],"utmost":[77],"importance.":[78],"In":[79,257,284],"this":[80],"paper,":[81],"we":[82],"evaluate":[83],"three":[84,124,203],"variations":[85],"convolutions,":[87],"including":[88],"direct":[89],"(Direct-Conv),":[91],"fast":[92],"Fourier":[93],"transform":[94],"(FFT)based":[95],"(FFT-Conv),":[97],"FFT":[99,229],"overlap":[100],"add":[102],"(FFT-OVA-Conv)":[104],"terms":[106],"computation":[108],"memory":[111],"storage":[112],"requirements":[113],"for":[114,126,201,225],"popular":[115],"CNN":[116],"hardware.":[120],"We":[121],"implemented":[122],"these":[123],"techniques":[125],"ResNet-20":[127],"CIFAR-10":[130],"data":[131],"set":[132],"low-power":[135],"domain-specific":[136,173],"many-core":[137],"architecture":[138],"called":[139],"power-efficient":[140],"nanoclusters":[141],"(PENCs),":[142],"NVIDIA":[143],"Jetson":[144],"TX1":[145,285,338],"graphics":[146],"processing":[147],"unit":[148],"(GPU),":[149],"ARM":[150,258,334],"Cortex":[151],"A53":[152,259,335],"CPU,":[153,260],"SPARse":[155],"Convolutional":[156],"NETwork":[157],"(SPARCNet)":[158],"accelerator":[159],"Zynq":[161,208],"7020":[162],"FPGA":[163,209],"to":[164,192],"explore":[165],"tradeoff":[167],"between":[168],"software":[169],"hardware":[171],"implementation,":[172],"logic":[174],"instructions,":[176],"as":[177,179],"well":[178],"various":[180],"parallelism":[181],"across":[182],"different":[183],"architectures.":[184],"Results":[185],"evaluated":[187],"compared":[189],"respect":[191],"throughput":[193,220,250,279,301,330],"per":[194,221,251,302,331],"layer,":[195],"energy":[196,215],"consumption,":[197],"execution":[199,270],"time":[200,271],"methods.":[204],"SPARCNet":[205],"deployed":[206],"achieved":[210],"42-ms":[211],"runtime":[212],"135-mJ":[214],"consumption":[216],"10.8-MB/s":[219],"layer":[222,303,332],"using":[223],"FFT-Conv":[224,287],"ResNet-20.":[226],"Using":[227],"built-in":[228],"instruction":[230],"PENC,":[232],"FFT-OVA-Conv":[234,261],"performs":[235],"2.9":[236],"\u00d7":[237,240,245,248,264,267,274,277,290,293,299,309,312,316,319,325,328],"1.65":[239],"faster":[241,313],"achieves":[243,262,297,323],"6.8":[244],"2.5":[247],"higher":[249,278,300,329],"watt":[252],"than":[253,280,304,333],"Direct-Conv":[254],"FFT-Conv.":[256,283],"3.36":[263],"1.38":[266],"improvement":[268],"2.72":[273],"1.32":[276],"DirectConv":[281],"GPU,":[286,339],"1.9":[289],"faster,":[291],"2.2":[292],"energy-efficient,":[295],"5.6":[298],"Direct-Conv.":[305],"PENC":[306],"10916":[308],"1.8":[311],"5053":[315],"4.3":[318],"7.5":[324],"1.2":[327],"CPU":[336],"respectively.":[340]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}