{"id":"https://openalex.org/W4402351697","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651211","title":"Low-Latency Deep Learning Inference Schedule on Multi-Core MCU","display_name":"Low-Latency Deep Learning Inference Schedule on Multi-Core MCU","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351697","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651211"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5028110218","display_name":"Chaonong Xu","orcid":"https://orcid.org/0000-0003-1897-4797"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaonong Xu","raw_affiliation_strings":["China University of Petroleum (Beijing),Beijing Key Lab of Petroleum Data Mining,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing),Beijing Key Lab of Petroleum Data Mining,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101069682","display_name":"Min Liu","orcid":"https://orcid.org/0009-0007-7231-0787"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Liu","raw_affiliation_strings":["China University of Petroleum (Beijing),Beijing Key Lab of Petroleum Data Mining,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing),Beijing Key Lab of Petroleum Data Mining,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323217","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-6304-8824"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Institute of Intelligent Computing,Zhejiang Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Computing,Zhejiang Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029313886","display_name":"Weiming Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Kong","raw_affiliation_strings":["China University of Petroleum (Beijing),Beijing Key Lab of Petroleum Data Mining,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing),Beijing Key Lab of Petroleum Data Mining,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49973205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"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":0.9972000122070312,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9789999723434448,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9602000117301941,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6965466141700745},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6757992506027222},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5886796712875366},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5597488284111023},{"id":"https://openalex.org/keywords/microcontroller","display_name":"Microcontroller","score":0.5279197692871094},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5240136384963989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5015711784362793},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.49235284328460693},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41747117042541504},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38894301652908325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33690714836120605},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3129233717918396},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19222214818000793},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07820290327072144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965466141700745},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6757992506027222},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5886796712875366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5597488284111023},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.5279197692871094},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5240136384963989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5015711784362793},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.49235284328460693},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41747117042541504},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38894301652908325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33690714836120605},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3129233717918396},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19222214818000793},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07820290327072144}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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":24,"referenced_works":["https://openalex.org/W2760063890","https://openalex.org/W2784372305","https://openalex.org/W2786771851","https://openalex.org/W2804032941","https://openalex.org/W2915364523","https://openalex.org/W2931092525","https://openalex.org/W2938868270","https://openalex.org/W2963918968","https://openalex.org/W2964259004","https://openalex.org/W2981758446","https://openalex.org/W3013186616","https://openalex.org/W3044604993","https://openalex.org/W3048107166","https://openalex.org/W3103638723","https://openalex.org/W3165698711","https://openalex.org/W4282970339","https://openalex.org/W4287639545","https://openalex.org/W4316252352","https://openalex.org/W6747876305","https://openalex.org/W6748224102","https://openalex.org/W6756887525","https://openalex.org/W6780827055","https://openalex.org/W6781736146","https://openalex.org/W6784225549"],"related_works":["https://openalex.org/W4316095964","https://openalex.org/W2383001583","https://openalex.org/W2771395446","https://openalex.org/W2131084560","https://openalex.org/W3112038843","https://openalex.org/W3209836052","https://openalex.org/W2088310429","https://openalex.org/W2161641032","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Emerging":[0],"Artificial":[1],"Internet-of-Things":[2],"(AIoT)":[3],"services":[4,21],"based":[5,130],"on":[6,23,124,131,146],"Microcontroller":[7],"Units":[8],"(MCU)":[9],"heavily":[10],"harness":[11],"Deep":[12],"Learning":[13],"(DL)":[14],"to":[15,36,76,159,170],"improve":[16],"user":[17],"experiences.":[18],"Such":[19],"DL-assisted":[20],"depend":[22],"fast":[24],"Neural":[25],"Network":[26],"(NN)":[27],"execution":[28,40,139,211],"for":[29,58,66,85,120,180,197],"high":[30],"responsiveness,":[31],"demanding":[32],"tiny":[33],"IoT":[34],"devices":[35],"minimize":[37],"the":[38,93,128,138,171,208],"NN":[39],"latency":[41,134,140],"by":[42,97],"efficiently":[43],"utilizing":[44],"their":[45],"underlying":[46],"hardware":[47],"resources.":[48],"However,":[49],"existing":[50],"inference":[51,123,202],"frameworks":[52],"cannot":[53],"achieve":[54,192],"satisfied":[55],"real-time":[56],"performance":[57],"Multi-core":[59],"MCU":[60],"(MMCU),":[61],"now":[62],"a":[63,109,132,147,193,199,217],"mainstream":[64],"platform":[65],"AIoT.":[67],"We":[68,126],"mention":[69],"that":[70,187],"two":[71],"improvements":[72],"can":[73,191],"be":[74],"made":[75],"speed":[77],"up":[78],"inference:":[79],"1)":[80],"select":[81],"appropriate":[82],"data":[83,114],"layout":[84,115],"each":[86,100,142],"operator":[87,101,143],"in":[88],"NNs,":[89],"and":[90,116,167,177],"2)":[91],"exploit":[92],"capability":[94],"of":[95,112,141,174,195,219],"MMCU":[96],"properly":[98],"partitioning":[99],"into":[102],"multiple":[103],"cores.In":[104],"this":[105],"paper,":[106],"we":[107],"propose":[108],"novel":[110],"idea":[111],"joint":[113],"Intra-Operator":[117],"Parallelism":[118],"(IOP)":[119],"low-latency":[121],"DL":[122],"MMCU.":[125,149],"formulate":[127],"problem":[129],"self-built":[133],"predictor,":[135],"which":[136],"predicts":[137],"within":[144],"NNs":[145],"given":[148],"An":[150],"algorithm":[151],"with":[152,207],"time":[153],"complexity":[154],"being":[155],"${\\mathcal{O}}\\left({|E|M{N^3}}\\right)$":[156],"is":[157],"proposed":[158],"find":[160],"an":[161,181],"optimal":[162],"scheduling":[163,189,214],"plan,":[164],"where":[165],"N":[166],"M":[168],"refer":[169],"maximum":[172],"number":[173],"possible":[175],"layouts":[176],"IOP":[178,210],"strategies":[179],"operator.":[182],"Our":[183],"experimental":[184],"evaluation":[185],"demonstrates":[186],"our":[188,213],"plan":[190,215],"speedup":[194,218],"1.52\u00d7\u22123.37\u00d7":[196],"CMSIS-NN,":[198],"state-of-the-art":[200,209],"edge":[201],"software":[203],"stack.":[204],"Besides,":[205],"compared":[206],"system,":[212],"achieves":[216],"approximately":[220],"1.67\u00d7.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}