{"id":"https://openalex.org/W4321500424","doi":"https://doi.org/10.1145/3579990.3580015","title":"Accelerating Deep Neural Networks on Mobile Multicore NPUs","display_name":"Accelerating Deep Neural Networks on Mobile Multicore NPUs","publication_year":2023,"publication_date":"2023-02-17","ids":{"openalex":"https://openalex.org/W4321500424","doi":"https://doi.org/10.1145/3579990.3580015"},"language":"en","primary_location":{"id":"doi:10.1145/3579990.3580015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579990.3580015","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579990.3580015","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3579990.3580015","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103548947","display_name":"Hanwoong Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4399598381","display_name":"Samsung Advanced Institute of Technology (South Korea)","ror":"https://ror.org/04axnyp10","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598381"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanwoong Jung","raw_affiliation_strings":["Samsung Advanced Institute of Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4399598381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033294107","display_name":"Hexiang Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hexiang Ji","raw_affiliation_strings":["Samsung Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047530385","display_name":"Alexey Pushchin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Pushchin","raw_affiliation_strings":["Samsung Research, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Russia","institution_ids":["https://openalex.org/I4210141363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024703677","display_name":"Maxim Ostapenko","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4399598381","display_name":"Samsung Advanced Institute of Technology (South Korea)","ror":"https://ror.org/04axnyp10","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598381"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Maxim Ostapenko","raw_affiliation_strings":["Samsung Advanced Institute of Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4399598381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006523828","display_name":"Wenlong Niu","orcid":"https://orcid.org/0000-0003-1643-1705"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenlong Niu","raw_affiliation_strings":["Samsung Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062939777","display_name":"Ilya Palachev","orcid":"https://orcid.org/0000-0002-7454-3660"},"institutions":[{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ilya Palachev","raw_affiliation_strings":["Samsung Research, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Russia","institution_ids":["https://openalex.org/I4210141363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090545502","display_name":"Yutian Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutian Qu","raw_affiliation_strings":["Samsung Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102310876","display_name":"\u041f\u0430\u0432\u0435\u043b \u0410\u043d\u0430\u0442\u043e\u043b\u044c\u0435\u0432\u0438\u0447 \u0424\u0435\u0434\u0438\u043d","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pavel Fedin","raw_affiliation_strings":["Samsung Research, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Russia","institution_ids":["https://openalex.org/I4210141363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075746571","display_name":"Y. Gribov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141363","display_name":"Samsung (Russia)","ror":"https://ror.org/051an6p98","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210141363"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yuri Gribov","raw_affiliation_strings":["Samsung Research, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Russia","institution_ids":["https://openalex.org/I4210141363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101129545","display_name":"Heewoo Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4399598381","display_name":"Samsung Advanced Institute of Technology (South Korea)","ror":"https://ror.org/04axnyp10","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598381"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heewoo Nam","raw_affiliation_strings":["Samsung Advanced Institute of Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4399598381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023312041","display_name":"Dongguen Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4399598381","display_name":"Samsung Advanced Institute of Technology (South Korea)","ror":"https://ror.org/04axnyp10","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598381"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongguen Lim","raw_affiliation_strings":["Samsung Advanced Institute of Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4399598381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737622","display_name":"Hyunjun Kim","orcid":"https://orcid.org/0000-0003-3838-4153"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4399598381","display_name":"Samsung Advanced Institute of Technology (South Korea)","ror":"https://ror.org/04axnyp10","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598381"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjun Kim","raw_affiliation_strings":["Samsung Advanced Institute of Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4399598381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113943216","display_name":"Joonho Song","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4399598381","display_name":"Samsung Advanced Institute of Technology (South Korea)","ror":"https://ror.org/04axnyp10","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598381"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonho Song","raw_affiliation_strings":["Samsung Advanced Institute of Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4399598381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375653","display_name":"Seungwon Lee","orcid":"https://orcid.org/0000-0002-0413-0510"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I4399598381","display_name":"Samsung Advanced Institute of Technology (South Korea)","ror":"https://ror.org/04axnyp10","country_code":null,"type":"company","lineage":["https://openalex.org/I4399598381"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungwon Lee","raw_affiliation_strings":["Samsung Advanced Institute of Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4399598381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035561846","display_name":"Hwansoo Han","orcid":"https://orcid.org/0000-0001-7182-8452"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwansoo Han","raw_affiliation_strings":["Sungkyunkwan University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, South Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8481,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8092246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"236","last_page":"248"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9955999851226807,"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":0.8664964437484741},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7593343257904053},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.6671084761619568},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49936580657958984},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4849088788032532},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4518135190010071},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42697620391845703},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.42411500215530396},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.420198529958725},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.41984355449676514},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4080781936645508},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35616472363471985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13766902685165405},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11721909046173096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664964437484741},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7593343257904053},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.6671084761619568},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49936580657958984},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4849088788032532},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4518135190010071},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42697620391845703},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42411500215530396},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.420198529958725},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.41984355449676514},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4080781936645508},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35616472363471985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13766902685165405},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11721909046173096},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579990.3580015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579990.3580015","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579990.3580015","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3579990.3580015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579990.3580015","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579990.3580015","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321500424.pdf","grobid_xml":"https://content.openalex.org/works/W4321500424.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2090593986","https://openalex.org/W2152839228","https://openalex.org/W2183341477","https://openalex.org/W2442974303","https://openalex.org/W2471164860","https://openalex.org/W2798317693","https://openalex.org/W2896180420","https://openalex.org/W2935331687","https://openalex.org/W2961619211","https://openalex.org/W2963163009","https://openalex.org/W2964309882","https://openalex.org/W2973727699","https://openalex.org/W2980856918","https://openalex.org/W2983440318","https://openalex.org/W3010466514","https://openalex.org/W3043571714","https://openalex.org/W3048233142","https://openalex.org/W3119880013","https://openalex.org/W3123054690","https://openalex.org/W3129831491","https://openalex.org/W3130823781","https://openalex.org/W3132107458","https://openalex.org/W3132357455","https://openalex.org/W3133635270","https://openalex.org/W3156643189","https://openalex.org/W3156745629","https://openalex.org/W3163465001","https://openalex.org/W3168643403","https://openalex.org/W3184812671","https://openalex.org/W3204998121","https://openalex.org/W4200342808","https://openalex.org/W4230315356","https://openalex.org/W4240168186","https://openalex.org/W4280562683","https://openalex.org/W4283814737","https://openalex.org/W4288346477"],"related_works":["https://openalex.org/W2359328895","https://openalex.org/W2363535981","https://openalex.org/W2058965144","https://openalex.org/W2007402811","https://openalex.org/W2164382479","https://openalex.org/W2326762630","https://openalex.org/W2391354408","https://openalex.org/W1986103452","https://openalex.org/W2146343568","https://openalex.org/W3012895752"],"abstract_inverted_index":{"Neural":[0],"processing":[1],"units":[2],"(NPUs)":[3],"have":[4,53],"become":[5],"indispensable":[6],"parts":[7],"of":[8,40,47,57,75,116,144,221],"mobile":[9,30,201],"SoCs.":[10],"Furthermore,":[11],"integrating":[12],"multiple":[13,119],"NPU":[14,41],"cores":[15,42],"into":[16,118],"a":[17,21,54,114,131,145,199,219],"single":[18],"chip":[19],"becomes":[20],"promising":[22],"solution":[23],"for":[24,70],"ever-increasing":[25],"computing":[26],"power":[27],"demands":[28],"in":[29,79,85,103,125,158,198],"devices.":[31],"This":[32],"paper":[33],"addresses":[34],"techniques":[35,173,197,213],"to":[36,109,139,207],"maximize":[37],"the":[38,45,94,106,141,162,208],"utilization":[39],"and":[43,73,154,182],"reduce":[44,140],"latency":[46],"on-device":[48],"inference.":[49],"Mobile":[50],"NPUs":[51],"typically":[52],"small":[55],"amount":[56],"local":[58,89],"memory":[59,160,184],"(or":[60],"scratch":[61],"pad":[62],"memory,":[63],"SPM)":[64],"that":[65],"provides":[66],"space":[67],"only":[68],"enough":[69],"input/output":[71],"tensors":[72,157],"weights":[74],"one":[76],"layer":[77,101,115],"operation":[78],"deep":[80],"neural":[81,190],"networks":[82,191],"(DNNs).":[83],"Even":[84],"multicore":[86,128],"NPUs,":[87],"such":[88,97],"memories":[90],"are":[91,161],"distributed":[92],"across":[93],"cores.":[95,205],"In":[96,147],"systems,":[98],"executing":[99],"network":[100],"operations":[102],"parallel":[104,126,152],"is":[105],"primary":[107],"vehicle":[108],"achieve":[110],"performance.":[111],"By":[112],"partitioning":[113,177,210],"DNNs":[117],"sub-layers,":[120],"we":[121,133,169,193],"can":[122,134],"execute":[123],"them":[124],"on":[127],"NPUs.":[129],"Within":[130],"core,":[132],"also":[135],"employ":[136],"pipelined":[137],"execution":[138,142,149,153,179],"time":[143],"sub-layer.":[146],"this":[148],"model,":[150],"synchronizing":[151],"loading/storing":[155],"intermediate":[156],"global":[159,183],"main":[163],"bottlenecks.":[164],"To":[165],"alleviate":[166],"these":[167],"problems,":[168],"propose":[170],"novel":[171],"optimization":[172,196],"which":[174],"carefully":[175],"consider":[176],"direction,":[178],"order,":[180],"synchronization,":[181],"access.":[185],"Using":[186],"six":[187],"popular":[188],"convolutional":[189],"(CNNs),":[192],"evaluate":[194],"our":[195,212],"flagship":[200],"SoC":[202],"with":[203],"three":[204],"Compared":[206],"highest-performing":[209],"approach,":[211],"improve":[214],"performance":[215],"by":[216],"23%,":[217],"achieving":[218],"speedup":[220],"2.1x":[222],"over":[223],"single-core":[224],"systems.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}