{"id":"https://openalex.org/W4396506382","doi":"https://doi.org/10.1109/jiot.2024.3395335","title":"Optimizing Convolutions for Deep Learning Inference on ARM Cortex-M Processors","display_name":"Optimizing Convolutions for Deep Learning Inference on ARM Cortex-M Processors","publication_year":2024,"publication_date":"2024-04-30","ids":{"openalex":"https://openalex.org/W4396506382","doi":"https://doi.org/10.1109/jiot.2024.3395335"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2024.3395335","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3395335","pdf_url":"https://ieeexplore.ieee.org/ielx7/6488907/6702522/10513367.pdf","source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6488907/6702522/10513367.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055946528","display_name":"Antonio Maci\u00e1-Lillo","orcid":"https://orcid.org/0000-0001-8356-7616"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Antonio Maci\u00e1-Lillo","raw_affiliation_strings":["Department of Technology Information and Computation, Universitat d&#x2019;Alacant, San Vicente del Raspeig, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8356-7616","affiliations":[{"raw_affiliation_string":"Department of Technology Information and Computation, Universitat d&#x2019;Alacant, San Vicente del Raspeig, Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090675958","display_name":"Sergio Barrachina","orcid":"https://orcid.org/0000-0003-4642-7467"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergio Barrachina","raw_affiliation_strings":["Department Computer Science and Engineering, Universitat Jaume I, Castell&#x00F3; de la Plana, Spain"],"raw_orcid":"https://orcid.org/0000-0003-4642-7467","affiliations":[{"raw_affiliation_string":"Department Computer Science and Engineering, Universitat Jaume I, Castell&#x00F3; de la Plana, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001637665","display_name":"Germ\u00e1n Fabregat","orcid":"https://orcid.org/0000-0002-0452-3058"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Germ\u00e1n Fabregat","raw_affiliation_strings":["Department Computer Science and Engineering, Universitat Jaume I, Castell&#x00F3; de la Plana, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0452-3058","affiliations":[{"raw_affiliation_string":"Department Computer Science and Engineering, Universitat Jaume I, Castell&#x00F3; de la Plana, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054862021","display_name":"Manuel F. Dolz","orcid":"https://orcid.org/0000-0001-9466-3398"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel F. Dolz","raw_affiliation_strings":["Department Computer Science and Engineering, Universitat Jaume I, Castell&#x00F3; de la Plana, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9466-3398","affiliations":[{"raw_affiliation_string":"Department Computer Science and Engineering, Universitat Jaume I, Castell&#x00F3; de la Plana, Spain","institution_ids":["https://openalex.org/I10902133"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055946528"],"corresponding_institution_ids":["https://openalex.org/I130194489"],"apc_list":null,"apc_paid":null,"fwci":1.9531,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86062334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"11","issue":"15","first_page":"26203","last_page":"26219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","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"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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/T10320","display_name":"Neural Networks and Applications","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811347484588623},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7647385597229004},{"id":"https://openalex.org/keywords/microcontroller","display_name":"Microcontroller","score":0.6162359714508057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5308191776275635},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5099159479141235},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49947571754455566},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.499103307723999},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49169331789016724},{"id":"https://openalex.org/keywords/arduino","display_name":"Arduino","score":0.47143736481666565},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46438348293304443},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4545728862285614},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39820966124534607},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3696945905685425},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3612573742866516},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35227927565574646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33771955966949463},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3252737522125244},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07858514785766602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811347484588623},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7647385597229004},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.6162359714508057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5308191776275635},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5099159479141235},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49947571754455566},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.499103307723999},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49169331789016724},{"id":"https://openalex.org/C136501162","wikidata":"https://www.wikidata.org/wiki/Q175957","display_name":"Arduino","level":2,"score":0.47143736481666565},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46438348293304443},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4545728862285614},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39820966124534607},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3696945905685425},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3612573742866516},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35227927565574646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33771955966949463},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3252737522125244},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07858514785766602},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jiot.2024.3395335","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3395335","pdf_url":"https://ieeexplore.ieee.org/ielx7/6488907/6702522/10513367.pdf","source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"},{"id":"pmh:oai:repositori.uji.es:10234/207311","is_oa":true,"landing_page_url":"http://hdl.handle.net/10234/207311","pdf_url":null,"source":{"id":"https://openalex.org/S4306400303","display_name":"Repositori UJI (Universitat Jaume I)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I10902133","host_organization_name":"Universitat Jaume I","host_organization_lineage":["https://openalex.org/I10902133"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:rua.ua.es:10045/142602","is_oa":true,"landing_page_url":"http://hdl.handle.net/10045/142602","pdf_url":null,"source":{"id":"https://openalex.org/S4306400416","display_name":"Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130194489","host_organization_name":"University of Alicante","host_organization_lineage":["https://openalex.org/I130194489"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/jiot.2024.3395335","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3395335","pdf_url":"https://ieeexplore.ieee.org/ielx7/6488907/6702522/10513367.pdf","source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2573851405","display_name":null,"funder_award_id":"CIDEXG/2022/13","funder_id":"https://openalex.org/F4320336489","funder_display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G4916508278","display_name":null,"funder_award_id":"PRE2021-099284","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7535663061","display_name":null,"funder_award_id":"AEI/10.","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8269684946","display_name":null,"funder_award_id":"TED2021-129334B-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null},{"id":"https://openalex.org/F4320336489","display_name":"Conselleria de Innovaci\u00f3n, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396506382.pdf","grobid_xml":"https://content.openalex.org/works/W4396506382.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2194775991","https://openalex.org/W2604319603","https://openalex.org/W2618530766","https://openalex.org/W2784372305","https://openalex.org/W2900071409","https://openalex.org/W2950027350","https://openalex.org/W2963037989","https://openalex.org/W2969920946","https://openalex.org/W2985361718","https://openalex.org/W3004034302","https://openalex.org/W3049613586","https://openalex.org/W3198711939","https://openalex.org/W4212823851","https://openalex.org/W4224278821","https://openalex.org/W4281687509","https://openalex.org/W4288095610","https://openalex.org/W4297775537","https://openalex.org/W4311486595","https://openalex.org/W4311543031","https://openalex.org/W4381303840","https://openalex.org/W4388543812","https://openalex.org/W6631660994","https://openalex.org/W6637373629","https://openalex.org/W6737664043","https://openalex.org/W6740373327","https://openalex.org/W6747876305","https://openalex.org/W6763749723","https://openalex.org/W6769561780","https://openalex.org/W6776385562"],"related_works":["https://openalex.org/W4293241760","https://openalex.org/W2747703758","https://openalex.org/W2770439812","https://openalex.org/W2315986283","https://openalex.org/W2318293530","https://openalex.org/W2592512903","https://openalex.org/W2799932818","https://openalex.org/W2768783059","https://openalex.org/W4229074545","https://openalex.org/W4385574901"],"abstract_inverted_index":{"We":[0,69],"perform":[1],"a":[2,85,123],"series":[3],"of":[4,19,73,93,108],"optimisations":[5],"on":[6,23,77],"the":[7,11,17,44,49,53,57,75,78,88,118],"convolution":[8,50,89],"operator":[9,51],"within":[10],"ARM":[12,29],"CMSIS-NN":[13],"library":[14],"to":[15,65,128],"improve":[16],"performance":[18],"deep":[20],"learning":[21],"tasks":[22],"Arduino":[24,79],"development":[25],"boards":[26,80],"equipped":[27],"with":[28],"Cortex-M4":[30],"and":[31,56,60,112],"M7":[32],"microcontrollers.":[33],"To":[34],"this":[35],"end,":[36],"we":[37,61],"develop":[38],"custom":[39],"microkernels":[40],"that":[41],"efficiently":[42],"handle":[43],"internal":[45],"computations":[46],"required":[47],"by":[48,81,100,122],"via":[52],"lowering":[54],"approach":[55],"direct":[58],"method,":[59],"design":[62],"two":[63],"techniques":[64,95],"avoid":[66],"register":[67],"spilling.":[68],"also":[70],"take":[71],"advantage":[72],"all":[74],"RAM":[76],"reusing":[82],"it":[83],"as":[84],"scratchpad":[86],"for":[87,103,105],"filters.":[90],"The":[91],"integration":[92],"these":[94],"into":[96],"CMSIS-NN,":[97],"when":[98],"invoked":[99],"TensorFlow":[101],"Lite":[102],"microcontrollers":[104],"quantised":[106],"versions":[107],"VGG,":[109],"SqueezeNet,":[110],"ResNet,":[111],"MobileNet-like":[113],"convolutional":[114],"neural":[115],"networks":[116],"enhances":[117],"overall":[119],"inference":[120],"speed":[121],"factor":[124],"ranging":[125],"from":[126],"1.13\u00d7":[127],"1.50\u00d7.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2024-05-01T00:00:00"}
