{"id":"https://openalex.org/W3185424780","doi":"https://doi.org/10.23919/date51398.2021.9474215","title":"Hardware-Software Codesign of Weight Reshaping and Systolic Array Multiplexing for Efficient CNNs","display_name":"Hardware-Software Codesign of Weight Reshaping and Systolic Array Multiplexing for Efficient CNNs","publication_year":2021,"publication_date":"2021-02-01","ids":{"openalex":"https://openalex.org/W3185424780","doi":"https://doi.org/10.23919/date51398.2021.9474215","mag":"3185424780"},"language":"en","primary_location":{"id":"doi:10.23919/date51398.2021.9474215","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date51398.2021.9474215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5102009115","display_name":"Jingyao Zhang","orcid":"https://orcid.org/0000-0003-3202-6427"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyao Zhang","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049448415","display_name":"Huaxi Gu","orcid":"https://orcid.org/0000-0002-6409-2229"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxi Gu","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070194930","display_name":"Grace Li Zhang","orcid":"https://orcid.org/0000-0002-8289-9288"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Grace Li Zhang","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451269","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-5055-8921"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017567485","display_name":"Ulf Schlichtmann","orcid":"https://orcid.org/0000-0003-4431-7619"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Schlichtmann","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"667","last_page":"672"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983000159263611,"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/T10320","display_name":"Neural Networks and Applications","score":0.9957000017166138,"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/pruning","display_name":"Pruning","score":0.8048611879348755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701507806777954},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.704279899597168},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.5945724248886108},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5692381858825684},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5599297881126404},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5235954523086548},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5209178328514099},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5151259303092957},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5096685886383057},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.457367479801178},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.40338531136512756},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.38405001163482666},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36397355794906616},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3249968886375427},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.31974542140960693},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.2819623351097107},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.245501309633255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23120254278182983},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10167309641838074}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8048611879348755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701507806777954},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.704279899597168},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.5945724248886108},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5692381858825684},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5599297881126404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5235954523086548},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5209178328514099},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5151259303092957},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5096685886383057},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.457367479801178},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40338531136512756},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.38405001163482666},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36397355794906616},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3249968886375427},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31974542140960693},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.2819623351097107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.245501309633255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23120254278182983},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10167309641838074},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date51398.2021.9474215","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date51398.2021.9474215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W2119144962","https://openalex.org/W2606722458","https://openalex.org/W2657126969","https://openalex.org/W2900228909","https://openalex.org/W2944853256","https://openalex.org/W2945296148","https://openalex.org/W2952294252","https://openalex.org/W2962780877","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2964299589","https://openalex.org/W2970971581","https://openalex.org/W3034729708","https://openalex.org/W4295312788","https://openalex.org/W4302296459","https://openalex.org/W6725543821","https://openalex.org/W6765111094","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W1992586242","https://openalex.org/W4287865796","https://openalex.org/W2979429416","https://openalex.org/W3008796096","https://openalex.org/W2132165562","https://openalex.org/W2351404747","https://openalex.org/W4309228605","https://openalex.org/W2070391474","https://openalex.org/W3185424780","https://openalex.org/W2780340867"],"abstract_inverted_index":{"The":[0,40,158],"last":[1],"decade":[2],"has":[3],"witnessed":[4],"the":[5,19,24,95,131,136,149,163],"breakthrough":[6],"of":[7,22,26,90,139,165],"deep":[8],"neural":[9,54],"networks":[10,55],"(DNNs)":[11],"in":[12,37,87,99],"various":[13,125,156],"fields,":[14],"e.g.,":[15,80],"image/speech":[16],"recognition.":[17],"With":[18],"increasing":[20],"depth":[21],"DNNs,":[23],"number":[25],"multiply-accumulate":[27],"operations":[28,68],"(MAC)":[29],"with":[30,69,77],"weights":[31,59,114],"explodes":[32],"significantly,":[33],"preventing":[34],"their":[35],"applications":[36],"resource-constrained":[38],"platforms.":[39],"existing":[41],"weight":[42,72],"pruning":[43,61,117],"method":[44,51],"is":[45,153],"considered":[46],"to":[47,52,129],"be":[48,169],"an":[49,88],"effective":[50],"compress":[53],"for":[56,108,155],"acceleration.":[57],"However,":[58],"after":[60,115],"usually":[62],"exhibit":[63],"irregular":[64,71],"patterns.":[65],"Implementing":[66],"MAC":[67],"such":[70,140],"patterns":[73],"on":[74,110,142],"hardware":[75,91,96],"platforms":[76],"regular":[78],"designs,":[79],"GPUs":[81],"and":[82,148],"systolic":[83,111,143,151],"arrays,":[84,144],"might":[85],"result":[86],"underutilization":[89],"resources.":[92],"To":[93,134],"utilize":[94],"resource":[97],"efficiently,":[98],"this":[100],"paper,":[101],"we":[102],"propose":[103],"a":[104,121,145],"hardware-software":[105],"codesign":[106],"framework":[107],"acceleration":[109],"arrays.":[112],"First,":[113],"unstructured":[116],"are":[118,127],"reorganized":[119],"into":[120],"dense":[122],"cluster.":[123],"Second,":[124],"blocks":[126,141],"selected":[128],"cover":[130],"cluster":[132],"seamlessly.":[133],"support":[135],"concurrent":[137],"computations":[138],"multiplexing":[146],"technique":[147],"corresponding":[150],"architecture":[152],"developed":[154],"CNNs.":[157],"experimental":[159],"results":[160],"demonstrate":[161],"that":[162],"performance":[164],"CNN":[166],"inferences":[167],"can":[168],"improved":[170],"significantly":[171],"without":[172],"accuracy":[173],"loss.":[174]},"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":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}