{"id":"https://openalex.org/W3164200338","doi":"https://doi.org/10.1145/3412382.3458272","title":"Efficient Execution of Deep Neural Networks on Mobile Devices with NPU","display_name":"Efficient Execution of Deep Neural Networks on Mobile Devices with NPU","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3164200338","doi":"https://doi.org/10.1145/3412382.3458272","mag":"3164200338"},"language":"en","primary_location":{"id":"doi:10.1145/3412382.3458272","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412382.3458272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","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/A5054562944","display_name":"Tianxiang Tan","orcid":"https://orcid.org/0000-0002-9384-7117"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianxiang Tan","raw_affiliation_strings":["The Pennsylvania State University, State College, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102287047","display_name":"Guohong Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guohong Cao","raw_affiliation_strings":["The Pennsylvania State University, State College, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054562944"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":3.1962,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.9331517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9944999814033508,"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":0.839314341545105},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6108071804046631},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5688087940216064},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5471105575561523},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5449385643005371},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5110472440719604},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.43909355998039246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41216179728507996},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3810690939426422},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3364703059196472},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08695754408836365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839314341545105},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6108071804046631},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5688087940216064},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5471105575561523},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5449385643005371},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5110472440719604},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43909355998039246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41216179728507996},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3810690939426422},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3364703059196472},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08695754408836365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3412382.3458272","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412382.3458272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G8755052661","display_name":null,"funder_award_id":"CNS-1815465","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W300523764","https://openalex.org/W854541894","https://openalex.org/W1677182931","https://openalex.org/W1782590233","https://openalex.org/W1935978687","https://openalex.org/W2029016069","https://openalex.org/W2037227137","https://openalex.org/W2101234009","https://openalex.org/W2101788345","https://openalex.org/W2129861682","https://openalex.org/W2155893237","https://openalex.org/W2297325673","https://openalex.org/W2307667287","https://openalex.org/W2325939864","https://openalex.org/W2468875367","https://openalex.org/W2474696196","https://openalex.org/W2546536770","https://openalex.org/W2605258629","https://openalex.org/W2625157458","https://openalex.org/W2626129225","https://openalex.org/W2734927154","https://openalex.org/W2759071281","https://openalex.org/W2767011558","https://openalex.org/W2771329008","https://openalex.org/W2790644963","https://openalex.org/W2792220137","https://openalex.org/W2803025752","https://openalex.org/W2889744664","https://openalex.org/W2892090442","https://openalex.org/W2896542121","https://openalex.org/W2897268228","https://openalex.org/W2898344194","https://openalex.org/W2911185062","https://openalex.org/W2920031528","https://openalex.org/W2963000224","https://openalex.org/W2963037989","https://openalex.org/W2963210849","https://openalex.org/W2963446712","https://openalex.org/W2963674932","https://openalex.org/W2963728985","https://openalex.org/W2964231383","https://openalex.org/W2964299589","https://openalex.org/W2965272715","https://openalex.org/W3047589404","https://openalex.org/W3101962329","https://openalex.org/W3103203826","https://openalex.org/W4245741319","https://openalex.org/W4289305285"],"related_works":["https://openalex.org/W3034529322","https://openalex.org/W2115913271","https://openalex.org/W2113597336","https://openalex.org/W2155505549","https://openalex.org/W2357479218","https://openalex.org/W1819546284","https://openalex.org/W2043253324","https://openalex.org/W2018648706","https://openalex.org/W2114232034","https://openalex.org/W2478692956"],"abstract_inverted_index":{"Many":[0],"Deep":[1],"Neural":[2,53],"Network":[3],"(DNN)":[4],"based":[5,179,211,254,268],"applications":[6],"have":[7,50],"been":[8],"developed":[9,51],"and":[10,35,116,128,152,221,226,256],"run":[11,70,113,121,196],"on":[12,41,95,114,122,125,241,269],"mobile":[13,42,58,96,242],"devices.":[14,43],"Although":[15],"these":[16,46,174],"advanced":[17],"DNN":[18,71,93,109,198],"models":[19,72,94],"can":[20,61,69,258],"provide":[21],"better":[22],"results,":[23],"they":[24],"also":[25,231],"suffer":[26],"from":[27],"high":[28],"computational":[29],"overhead":[30],"which":[31,60,105,117,181,197],"means":[32],"long":[33],"delay":[34,127],"more":[36,218],"energy":[37],"consumption":[38],"when":[39],"running":[40],"To":[44,79,172,201],"address":[45,80,232],"problems,":[47,175],"many":[48,233],"companies":[49],"dedicated":[52],"Processing":[54],"Units":[55],"(NPUs)":[56],"for":[57],"devices,":[59],"process":[62],"AI":[63],"features.":[64],"Compared":[65],"to":[66,88,103,119,144,158,195,236],"CPU,":[67],"NPU":[68],"much":[73],"faster,":[74],"but":[75,184],"with":[76,98,244],"lower":[77],"accuracy.":[78],"this":[81],"issue,":[82],"we":[83,135,176,206],"leverage":[84],"model":[85,110,199,238],"partition":[86,239],"techniques":[87,240],"improve":[89,203,260],"the":[90,108,126,129,133,141,146,155,160,165,204,252,261,265,270],"performance":[91],"of":[92,107,132,190],"devices":[97,243],"NPU.":[99,123,245],"The":[100],"challenge":[101],"is":[102,143,157,167],"determine":[104],"part":[106,118],"should":[111],"be":[112,120],"CPU":[115],"Based":[124],"accuracy":[130,147,166,224,262],"requirements":[131],"applications,":[134],"study":[136],"two":[137],"problems:":[138],"Max-Accuracy":[139],"where":[140,154,194],"goal":[142,156],"maximize":[145],"under":[148],"some":[149],"time":[150,162,228,267],"constraint,":[151],"Min-Time":[153],"minimize":[159],"processing":[161,227,266],"while":[163],"ensuring":[164],"above":[168],"a":[169,187,208],"certain":[170],"threshold.":[171],"solve":[173],"propose":[177,207],"heuristic":[178,253],"algorithms":[180,255],"are":[182],"simple":[183],"only":[185],"search":[186],"small":[188],"number":[189],"layer":[191,219],"combinations":[192,220],"(i.e.,":[193],"layers).":[200],"further":[202],"performance,":[205],"Machine":[209],"Learning":[210],"Model":[212],"Partition":[213],"(MLMP)":[214],"algorithm.":[215],"MLMP":[216,250],"searches":[217],"considers":[222],"both":[223],"loss":[225],"simultaneously.":[229],"We":[230],"implementation":[234],"issues":[235],"support":[237],"Experimental":[246],"results":[247],"show":[248],"that":[249],"outperforms":[251],"it":[257],"significantly":[259],"or":[263],"reduce":[264],"application":[271],"requirements.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}