{"id":"https://openalex.org/W3198711939","doi":"https://doi.org/10.1109/access.2021.3110827","title":"An Efficient im2row-Based Fast Convolution Algorithm for ARM Cortex-M MCUs","display_name":"An Efficient im2row-Based Fast Convolution Algorithm for ARM Cortex-M MCUs","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198711939","doi":"https://doi.org/10.1109/access.2021.3110827","mag":"3198711939"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3110827","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3110827","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09530522.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09530522.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100396074","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-7958-0014"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","SG"],"is_corresponding":true,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China"],"raw_orcid":"https://orcid.org/0000-0002-7958-0014","affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403885","display_name":"Xiaoqin Wang","orcid":"https://orcid.org/0000-0001-5890-8079"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Wang","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103025031","display_name":"Rui Luo","orcid":"https://orcid.org/0000-0002-4230-7372"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Luo","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746048","display_name":"Dingyi Wang","orcid":"https://orcid.org/0009-0006-8145-7476"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingyi Wang","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074562630","display_name":"Mengjie Luo","orcid":"https://orcid.org/0000-0002-9881-6125"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Mengjie Luo","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026870474","display_name":"Shushan Qiao","orcid":"https://orcid.org/0000-0002-9102-2111"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Shushan Qiao","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China"],"raw_orcid":"https://orcid.org/0000-0002-9102-2111","affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006382294","display_name":"Yumei Zhou","orcid":"https://orcid.org/0000-0001-7142-2778"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yumei Zhou","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences, Chaoyang, Beijing 100029, China and University of Chinese Academy of Sciences, Shijingshan, Beijing 100049, China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100396074"],"corresponding_institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210165038"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.291,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56183928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"124384","last_page":"124395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8519638776779175},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8324753642082214},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7506852149963379},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6391549110412598},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5838335156440735},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.566364049911499},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5127483606338501},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5055382251739502},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.48865941166877747},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2242538034915924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13894575834274292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519638776779175},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8324753642082214},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7506852149963379},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6391549110412598},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5838335156440735},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.566364049911499},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5127483606338501},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5055382251739502},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.48865941166877747},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2242538034915924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13894575834274292},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3110827","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3110827","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09530522.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:36c0991e3632448ca916649b4998c449","is_oa":true,"landing_page_url":"https://doaj.org/article/36c0991e3632448ca916649b4998c449","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 124384-124395 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3110827","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3110827","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09530522.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3198711939.pdf","grobid_xml":"https://content.openalex.org/works/W3198711939.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1530262073","https://openalex.org/W1789336918","https://openalex.org/W2172654076","https://openalex.org/W2670151302","https://openalex.org/W2784372305","https://openalex.org/W2883780447","https://openalex.org/W2963887620","https://openalex.org/W3023935494","https://openalex.org/W6631660994","https://openalex.org/W6638020065","https://openalex.org/W6685214006","https://openalex.org/W6740373327","https://openalex.org/W6747876305","https://openalex.org/W6753767121"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W3157543420","https://openalex.org/W2964954556","https://openalex.org/W3019910406"],"abstract_inverted_index":{"With":[0],"the":[1,29,32,50,76,96,132,135,157,162,171,189],"rise":[2],"of":[3,31,78,98,134,168],"IoT":[4],"and":[5,20,103,145,170],"edge":[6,14],"computing,":[7],"deploying":[8],"neural":[9],"networks":[10],"(NNs)":[11],"on":[12,40,53,179],"low-power":[13],"computing":[15,33],"devices":[16],"is":[17,46,82,122,174],"drawing":[18],"more":[19,21],"attention.":[22],"In":[23],"NNs,":[24],"convolutional":[25,51,80,143,150,163],"layers":[26,144,151],"take":[27],"up":[28,161,175,188,193],"majority":[30],"cycles,":[34],"especially":[35],"when":[36],"NNs":[37,181],"are":[38],"implemented":[39],"ARM":[41,54],"processors":[42],"[1].":[43],"Therefore,":[44],"it":[45],"necessary":[47],"to":[48,112,155,176,194],"optimize":[49],"implementation":[52],"Cortex-M":[55],"MCUs.":[56],"This":[57,84,124],"paper":[58],"proposes":[59],"an":[60,166],"efficient":[61],"im2row-based":[62],"fast":[63],"convolution":[64],"algorithm":[65,108,140,159,185],"with":[66],"two":[67],"innovations.":[68],"First,":[69],"a":[70,87,110],"novel":[71],"im2row":[72,89,102],"method":[73,85],"for":[74,91,149],"reusing":[75],"data":[77,92,99,114,120,127],"adjacent":[79],"windows":[81],"presented.":[83],"utilizes":[86],"reusable":[88],"buffer":[90],"reuse,":[93],"significantly":[94],"reducing":[95,131],"amount":[97],"copied":[100],"during":[101],"improving":[104],"efficiency.":[105],"Second,":[106],"in":[107,141],"implementation,":[109],"q7_t":[111],"q15_t":[113],"type":[115],"extension":[116],"technique":[117,125],"that":[118,183],"avoids":[119],"reordering":[121,128],"employed.":[123],"eliminates":[126],"instructions,":[129],"thus":[130],"runtime":[133],"algorithm.":[136],"We":[137],"evaluate":[138],"our":[139,184],"separate":[142],"NNs.":[146],"The":[147],"results":[148],"show":[152],"that,":[153],"compared":[154],"baseline,":[156],"proposed":[158],"speeds":[160],"layer":[164],"by":[165,192],"average":[167],"1.42x,":[169],"maximum":[172],"speedup":[173],"2.9x.":[177],"Experiments":[178],"different":[180],"demonstrate":[182],"can":[186],"speed":[187],"overall":[190],"NN":[191],"2.15x.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}