{"id":"https://openalex.org/W3022173611","doi":"https://doi.org/10.1109/tcsi.2020.2986350","title":"O\u2074-DNN: A Hybrid DSP-LUT-Based Processing Unit With Operation Packing and Out-of-Order Execution for Efficient Realization of Convolutional Neural Networks on FPGA Devices","display_name":"O\u2074-DNN: A Hybrid DSP-LUT-Based Processing Unit With Operation Packing and Out-of-Order Execution for Efficient Realization of Convolutional Neural Networks on FPGA Devices","publication_year":2020,"publication_date":"2020-04-29","ids":{"openalex":"https://openalex.org/W3022173611","doi":"https://doi.org/10.1109/tcsi.2020.2986350","mag":"3022173611"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2020.2986350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2020.2986350","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","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/A5067209238","display_name":"Pouya Haghi","orcid":"https://orcid.org/0000-0003-2893-9194"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Pouya Haghi","raw_affiliation_strings":["School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042809860","display_name":"Mehdi Kamal","orcid":"https://orcid.org/0000-0001-7098-6440"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]},{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mehdi Kamal","raw_affiliation_strings":["School of Computer Science, Institute for Research in Fundamental Sciences, Tehran, Iran","School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0001-7098-6440","affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute for Research in Fundamental Sciences, Tehran, Iran","institution_ids":["https://openalex.org/I4210146419"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074063358","display_name":"Ali Afzali\u2010Kusha","orcid":"https://orcid.org/0000-0001-8614-2007"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ali Afzali-Kusha","raw_affiliation_strings":["School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0001-8614-2007","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044650311","display_name":"Massoud Pedram","orcid":"https://orcid.org/0000-0002-2677-7307"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Massoud Pedram","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-2677-7307","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1917,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.47123966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"67","issue":"9","first_page":"3056","last_page":"3069"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9990000128746033,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9970999956130981,"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/lookup-table","display_name":"Lookup table","score":0.7573508620262146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472648620605469},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6589676737785339},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.6363762617111206},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6252367496490479},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5211606025695801},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5198115110397339},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.47891390323638916},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44328904151916504},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3998798429965973},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34445101022720337},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3428512215614319},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3244885206222534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1702404022216797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09370660781860352}],"concepts":[{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.7573508620262146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472648620605469},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6589676737785339},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.6363762617111206},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6252367496490479},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5211606025695801},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5198115110397339},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.47891390323638916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44328904151916504},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3998798429965973},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34445101022720337},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3428512215614319},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3244885206222534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1702404022216797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09370660781860352},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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:10.1109/tcsi.2020.2986350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2020.2986350","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1825672851","https://openalex.org/W1934410531","https://openalex.org/W2002555321","https://openalex.org/W2117539524","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2177838837","https://openalex.org/W2194775991","https://openalex.org/W2337344472","https://openalex.org/W2583383421","https://openalex.org/W2604319603","https://openalex.org/W2606722458","https://openalex.org/W2625954420","https://openalex.org/W2725615981","https://openalex.org/W2762374354","https://openalex.org/W2794365619","https://openalex.org/W2795915628","https://openalex.org/W2795961274","https://openalex.org/W2810498815","https://openalex.org/W2890947558","https://openalex.org/W2903688003","https://openalex.org/W2903735800","https://openalex.org/W2949275038","https://openalex.org/W2951537853","https://openalex.org/W2962728029","https://openalex.org/W2963594949","https://openalex.org/W2963831937","https://openalex.org/W2964299589","https://openalex.org/W4230481654","https://openalex.org/W4294371482","https://openalex.org/W6637373629","https://openalex.org/W6638839971","https://openalex.org/W6684191040","https://openalex.org/W6685682220","https://openalex.org/W6703414193","https://openalex.org/W6749562289","https://openalex.org/W6754656709"],"related_works":["https://openalex.org/W2040548413","https://openalex.org/W2352017551","https://openalex.org/W4308216800","https://openalex.org/W2350861609","https://openalex.org/W2363310833","https://openalex.org/W2129894819","https://openalex.org/W2143940934","https://openalex.org/W2339728242","https://openalex.org/W4213033874","https://openalex.org/W2524802307"],"abstract_inverted_index":{"In":[0,53,132,242],"this":[1,54,225],"paper,":[2],"we":[3,144],"propose":[4],"O":[5,258],"<sup":[6,259],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[7,260],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">4</sup>":[8,261],"-DNN,":[9],"a":[10,42,66,72,172,239],"high-performance":[11],"FPGA-based":[12],"architecture":[13,38,209,226],"for":[14,28,153,197],"convolutional":[15,108],"neural":[16,154,219],"network":[17,155],"(CNN)":[18],"accelerators":[19],"relying":[20],"on":[21,110,177,229,244],"operation":[22],"packing":[23],"and":[24,90,122],"out-of-order":[25,202],"(OoO)":[26],"execution":[27],"DSP":[29,67,82,100],"blocks":[30,83],"augmented":[31],"with":[32],"LUT-based":[33],"glue":[34],"logic.":[35],"The":[36,102,205],"high-level":[37],"is":[39,62,118,181,203,210,253],"comprised":[40],"of":[41,45,59,75,81,116,139,149,168,188,207],"systolic":[43],"array":[44],"processing":[46],"elements":[47],"(PEs),":[48],"supporting":[49],"output":[50],"stationary":[51],"dataflow.":[52],"architecture,":[55],"the":[56,78,86,123,136,140,150,159,166,169,178,186,189,199,208,257,265],"computational":[57,95,104,142,170,191],"unit":[58,105,151,192],"each":[60,99],"PE":[61],"realized":[63],"by":[64,255],"using":[65,212],"block":[68,89],"as":[69,71,162,164],"well":[70,163],"small":[73],"number":[74,80],"LUTs.":[76],"Given":[77],"limited":[79],"in":[84],"FPGAs,":[85],"combination":[87],"(DSP":[88],"some":[91],"LUTs)":[92],"provides":[93],"more":[94],"power":[96],"obtainable":[97],"through":[98],"block.":[101],"proposed":[103,141,190],"performs":[106],"eight":[107],"operations":[109],"five":[111],"input":[112,128],"operands":[113],"where":[114],"one":[115],"them":[117],"an":[119,146,194],"8-bit":[120,127],"weight":[121,179],"others":[124],"are":[125],"four":[126,217],"feature":[129],"(IF)":[130],"maps.":[131],"addition,":[133,243],"to":[134,238,264],"improve":[135,185],"energy":[137,250],"efficiency":[138,251],"unit,":[143],"present":[145],"approximate":[147],"form":[148],"suitable":[152],"applications.":[156],"To":[157,184],"reduce":[158],"memory":[160],"bandwidth":[161],"increase":[165],"utilization":[167],"units,":[171],"data":[173],"reusing":[174],"technique":[175],"based":[176],"sharing":[180],"also":[182],"presented.":[183],"performance":[187],"further,":[193],"addressing":[195],"approach":[196],"computing":[198],"partial":[200],"sums":[201],"proposed.":[204],"efficacy":[206],"assessed":[211],"two":[213],"FPGA":[214],"devices":[215],"executing":[216],"state-of-the-art":[218],"networks.":[220],"Experimental":[221],"results":[222],"show":[223],"that":[224],"leads":[227],"to,":[228],"average":[230,245],"(up":[231],"to),":[232],"2.5\u00d7":[233],"(3.44\u00d7)":[234],"higher":[235],"throughput":[236],"compared":[237,263],"baseline":[240,266],"structure.":[241,267],"(maximum":[246],"of),":[247],"12%":[248],"(40%)":[249],"improvement":[252],"achievable":[254],"employing":[256],"-DNN":[262]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}