{"id":"https://openalex.org/W4387872851","doi":"https://doi.org/10.1109/icc45041.2023.10279108","title":"microGEMM: An Effective CNN-Based Inference Acceleration for Edge Computing","display_name":"microGEMM: An Effective CNN-Based Inference Acceleration for Edge Computing","publication_year":2023,"publication_date":"2023-05-28","ids":{"openalex":"https://openalex.org/W4387872851","doi":"https://doi.org/10.1109/icc45041.2023.10279108"},"language":"en","primary_location":{"id":"doi:10.1109/icc45041.2023.10279108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45041.2023.10279108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2023 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109438962","display_name":"Zheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344386","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-1233-9023"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064508449","display_name":"Kai Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Qian","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047412399","display_name":"Haodong Lu","orcid":"https://orcid.org/0000-0002-8628-2664"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Lu","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068961034","display_name":"Yinqiu Liu","orcid":"https://orcid.org/0000-0002-6198-3712"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinqiu Liu","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA","Department of Electrical and Computer Engineering, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040264802","display_name":"Siguang Chen","orcid":"https://orcid.org/0000-0002-7375-0393"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siguang Chen","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100366692","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-9099-2781"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA","Department of Electrical and Computer Engineering, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1214,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44092409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2474","last_page":"2479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9954000115394592,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8782994747161865},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.772545576095581},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6116964221000671},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5754361152648926},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5407460331916809},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5233530402183533},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47820353507995605},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.46764063835144043},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.43691015243530273},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4256436824798584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37210649251937866},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3487265706062317},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.34297654032707214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20571362972259521},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.19092294573783875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8782994747161865},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.772545576095581},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6116964221000671},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5754361152648926},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5407460331916809},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5233530402183533},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47820353507995605},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.46764063835144043},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43691015243530273},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4256436824798584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37210649251937866},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3487265706062317},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.34297654032707214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20571362972259521},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.19092294573783875},{"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc45041.2023.10279108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45041.2023.10279108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2023 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2521727659","https://openalex.org/W2605739168","https://openalex.org/W2796337470","https://openalex.org/W2800696118","https://openalex.org/W2971383048","https://openalex.org/W2995763407","https://openalex.org/W3012434840","https://openalex.org/W3034100311","https://openalex.org/W3045635015","https://openalex.org/W3089820912","https://openalex.org/W3093756531","https://openalex.org/W3098316065","https://openalex.org/W3123687588","https://openalex.org/W3128172237","https://openalex.org/W3132745255","https://openalex.org/W3186047385","https://openalex.org/W3188508394","https://openalex.org/W3212505503","https://openalex.org/W4226439885","https://openalex.org/W4293023444","https://openalex.org/W6803869102"],"related_works":["https://openalex.org/W2778498407","https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W3111395152","https://openalex.org/W4313526662","https://openalex.org/W4313463218","https://openalex.org/W4312996489","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs),":[3],"a":[4,112,206],"widely":[5],"recognized":[6],"deep":[7],"learning":[8],"algorithm,":[9,116],"have":[10,43],"been":[11,44],"utilized":[12],"in":[13,59,142,176],"various":[14],"domains":[15],"such":[16],"as":[17,71],"smart":[18],"cities":[19],"and":[20,34,178,186],"healthcare.":[21],"However,":[22],"the":[23,56,63,72,84,91,101,127,132,137,143,148,155,181,187,190],"remarkable":[24],"performance":[25],"of":[26,55,87,104,157,189],"CNNs":[27],"is":[28,62,174],"accompanied":[29],"by":[30,89],"high":[31],"resource":[32],"overhead":[33],"deployment":[35],"complexity.":[36],"To":[37,152],"address":[38],"these":[39],"challenges,":[40],"CNN":[41,60],"compilers":[42],"developed":[45],"to":[46,82,125,213,217],"simplify":[47],"convolutional":[48,123],"operations":[49],"for":[50],"edge":[51,105],"device":[52],"deployment.":[53],"One":[54],"crucial":[57],"components":[58],"models":[61],"General":[64],"Matrix":[65],"Multiply":[66],"(GEMM)":[67],"operation,":[68],"which":[69],"serves":[70],"main":[73],"computational":[74],"kernel.":[75],"In":[76,107],"previous":[77],"studies,":[78],"efforts":[79],"were":[80],"made":[81],"improve":[83],"computation":[85],"speed":[86],"GEMM":[88,133,144,183,188],"modifying":[90],"matrix":[92],"calculation":[93,134,145],"sequence,":[94],"but":[95],"they":[96],"did":[97],"not":[98],"fully":[99],"exploit":[100],"computing":[102],"resources":[103],"devices.":[106],"this":[108],"paper,":[109],"we":[110],"propose":[111],"novel":[113],"GEMM-based":[114],"acceleration":[115],"named":[117],"microGEMM.":[118],"The":[119,171,199],"microGEMM":[120,158,172,204],"algorithm":[121,138,173,184],"divides":[122],"data":[124],"reduce":[126],"memory":[128],"access":[129],"times":[130],"during":[131],"process.":[135],"Moreover,":[136],"employs":[139],"instruction-level":[140],"optimization":[141],"unit,":[146],"decreasing":[147],"cache":[149],"miss":[150],"rate.":[151],"better":[153],"evaluate":[154],"superiority":[156],"on":[159],"resource-constrained":[160],"devices,":[161],"two":[162],"edge-oriented":[163],"metrics":[164],"are":[165],"proposed,":[166],"namely":[167],"CCPS":[168],"&":[169],"CCPoE.":[170],"implemented":[175],"C++":[177],"compared":[179,216],"with":[180],"standard":[182],"(naiveGEMM)":[185],"open-source":[191],"Basic":[192],"Linear":[193],"Algebra":[194],"Subprograms":[195],"(BLAS)":[196],"library":[197],"(openblasGEMM).":[198],"experimental":[200],"results":[201],"demonstrate":[202],"that":[203],"achieves":[205],"significant":[207],"speedup,":[208],"ranging":[209],"from":[210],"5.67":[211],"\u00d7":[212],"14.19":[214],"\u00d7,":[215],"naiveGEMM.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}