{"id":"https://openalex.org/W3200967142","doi":"https://doi.org/10.1109/mwscas47672.2021.9531783","title":"WORDA: A Winograd Offline-Runtime Decomposition Algorithm for Faster CNN Inference","display_name":"WORDA: A Winograd Offline-Runtime Decomposition Algorithm for Faster CNN Inference","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3200967142","doi":"https://doi.org/10.1109/mwscas47672.2021.9531783","mag":"3200967142"},"language":"en","primary_location":{"id":"doi:10.1109/mwscas47672.2021.9531783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mwscas47672.2021.9531783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5105085165","display_name":"Jacob Nelson","orcid":null},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Nelson","raw_affiliation_strings":["Tennessee Technological University, Cookeville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tennessee Technological University, Cookeville, TN, USA","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070802892","display_name":"Tolulope A. Odetola","orcid":"https://orcid.org/0000-0002-6199-6249"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tolulope Odetola","raw_affiliation_strings":["Tennessee Technological University, Cookeville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tennessee Technological University, Cookeville, TN, USA","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034599612","display_name":"Syed Rafay Hasan","orcid":"https://orcid.org/0000-0003-0183-8086"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Rafay Hasan","raw_affiliation_strings":["Tennessee Technological University, Cookeville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tennessee Technological University, Cookeville, TN, USA","institution_ids":["https://openalex.org/I63920570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63920570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11200894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9987000226974487,"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":0.9976000189781189,"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":0.8153800964355469},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6456902027130127},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6350151300430298},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6053370833396912},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5933805704116821},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5875734090805054},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5470269322395325},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49046799540519714},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4695254862308502},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3736405670642853},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36141055822372437},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2530103921890259},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1631852090358734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14183953404426575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153800964355469},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6456902027130127},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6350151300430298},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6053370833396912},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5933805704116821},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5875734090805054},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5470269322395325},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49046799540519714},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4695254862308502},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3736405670642853},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36141055822372437},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2530103921890259},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1631852090358734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14183953404426575},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mwscas47672.2021.9531783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mwscas47672.2021.9531783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W2172654076","https://openalex.org/W2325939864","https://openalex.org/W2466675884","https://openalex.org/W2618530766","https://openalex.org/W2625954420","https://openalex.org/W2801550278","https://openalex.org/W2904795057","https://openalex.org/W2913221350","https://openalex.org/W2933543903","https://openalex.org/W2945913827","https://openalex.org/W2951909318","https://openalex.org/W2964525696","https://openalex.org/W2981994035","https://openalex.org/W2982618776","https://openalex.org/W6757703747","https://openalex.org/W6758388311"],"related_works":["https://openalex.org/W4382323155","https://openalex.org/W4315697128","https://openalex.org/W3205506801","https://openalex.org/W2982536526","https://openalex.org/W2995343971","https://openalex.org/W3100944160","https://openalex.org/W2992221004","https://openalex.org/W4383502363","https://openalex.org/W4292794827","https://openalex.org/W4224939635"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4,12],"demonstrated":[5],"impressive":[6],"performance":[7],"in":[8,139,147,151,157],"recent":[9],"times":[10],"and":[11,38,59,124,153,160],"shown":[13],"a":[14,77,136,144,154],"wide":[15],"range":[16],"of":[17,21,41,55,76,168],"applicability.":[18],"The":[19,63,132],"deployment":[20],"CNNs":[22,53],"on":[23,116],"resource-constrained":[24],"edge":[25],"devices":[26],"for":[27,113,118],"inference":[28],"still":[29],"proves":[30],"challenging":[31],"due":[32],"to":[33,51,70,94,98,109],"the":[34,73,83],"computation,":[35],"memory,":[36],"energy,":[37],"band-width":[39],"requirements":[40,75],"CNNs.":[42],"To":[43],"address":[44],"these":[45],"issues,":[46],"FPGAs":[47],"are":[48],"commonly":[49],"used":[50,69,108],"implement":[52],"because":[54],"their":[56],"high":[57],"flexibility":[58],"low":[60,100],"power":[61],"consumption.":[62],"Winograd":[64,84,96],"convolution":[65,78,97,111],"algorithm":[66],"can":[67],"be":[68],"further":[71],"reduce":[72],"computation":[74,101],"operation.":[79],"This":[80],"paper":[81],"proposes":[82],"Offline-Runtime":[85],"Decomposition":[86],"Algorithm":[87],"(WORDA),":[88],"which":[89],"provides":[90],"an":[91],"efficient":[92],"approach":[93],"performing":[95],"achieve":[99],"latency.":[102],"In":[103],"this":[104],"work,":[105],"WORDA":[106],"is":[107],"design":[110],"layers":[112],"CNN":[114,120],"accelerators":[115],"FPGA":[117],"two":[119],"architectures,":[121],"namely":[122],"LeNet":[123],"AlexNet,":[125],"using":[126,166],"Vivado":[127],"HLS":[128],"(High":[129],"Level":[130],"Synthesis).":[131],"state-of-the-art":[133],"comparison":[134],"shows":[135],"58.3%":[137],"decrease":[138],"latency":[140],"while":[141],"only":[142],"incurring":[143],"constant":[145],"increase":[146,156],"BRAMs,":[148],"no":[149],"change":[150],"DSPs,":[152],"122%":[155],"flip-flops":[158],"(FFs)":[159],"lookup":[161],"tables":[162],"(LUTs)":[163],"usage":[164],"when":[165],"filters":[167],"size":[169],"5":[170],"\u00d7":[171],"5.":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}