{"id":"https://openalex.org/W3217357178","doi":"https://doi.org/10.1109/tpds.2021.3129647","title":"Heterogeneous Systolic Array Architecture for Compact CNNs Hardware Accelerators","display_name":"Heterogeneous Systolic Array Architecture for Compact CNNs Hardware Accelerators","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3217357178","doi":"https://doi.org/10.1109/tpds.2021.3129647","mag":"3217357178"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3129647","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3129647","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/4359390/09623517.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/71/4359390/09623517.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101888900","display_name":"Rui Xu","orcid":"https://orcid.org/0000-0003-4220-9569"},"institutions":[{"id":"https://openalex.org/I55124834","display_name":"ICFAI University, Dehradun","ror":"https://ror.org/02ecg3h97","country_code":"IN","type":"education","lineage":["https://openalex.org/I55124834"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":["School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: nudtxurui@gmail.com)","[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: nudtxurui@gmail.com)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: nudtxurui@gmail.com)","institution_ids":["https://openalex.org/I55124834"]},{"raw_affiliation_string":"[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: nudtxurui@gmail.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760813","display_name":"Sheng Ma","orcid":"https://orcid.org/0000-0003-1710-4060"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Ma","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, Hunan, China, (e-mail: masheng@nudt.edu.cn)","[School of Computer, National University of Defense Technology, Changsha, Hunan, China, (e-mail: masheng@nudt.edu.cn)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, Hunan, China, (e-mail: masheng@nudt.edu.cn)","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"[School of Computer, National University of Defense Technology, Changsha, Hunan, China, (e-mail: masheng@nudt.edu.cn)]","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070012760","display_name":"Yaohua Wang","orcid":"https://orcid.org/0009-0005-6211-6388"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohua Wang","raw_affiliation_strings":["School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: yaowangeth@gmail.com)","[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: yaowangeth@gmail.com)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: yaowangeth@gmail.com)","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: yaowangeth@gmail.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720832","display_name":"Yang Guo","orcid":"https://orcid.org/0000-0001-9050-0866"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Guo","raw_affiliation_strings":["College of Computer, National University of Defense Technology, 58294 Changsha, Hunan, China, (e-mail: guoyang@nudt.edu.cn)","[College of Computer, National University of Defense Technology, 58294 Changsha, Hunan, China, (e-mail: guoyang@nudt.edu.cn)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, 58294 Changsha, Hunan, China, (e-mail: guoyang@nudt.edu.cn)","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"[College of Computer, National University of Defense Technology, 58294 Changsha, Hunan, China, (e-mail: guoyang@nudt.edu.cn)]","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I4210111018","display_name":"Hunan Haili Chemical Industry (China)","ror":"https://ror.org/026h9r553","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210111018"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: dsli@nudt.edu.cn)","[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: dsli@nudt.edu.cn)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: dsli@nudt.edu.cn)","institution_ids":["https://openalex.org/I4210111018"]},{"raw_affiliation_string":"[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: dsli@nudt.edu.cn)]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102984199","display_name":"Yuran Qiao","orcid":"https://orcid.org/0000-0002-5488-3545"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuran Qiao","raw_affiliation_strings":["School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: qiaoyuran@nudt.edu.cn)","[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: qiaoyuran@nudt.edu.cn)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: qiaoyuran@nudt.edu.cn)","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"[School of Computer, NUDT, 58294 Changsha, Hunan, China, (e-mail: qiaoyuran@nudt.edu.cn)]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9887,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.87530543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8403512239456177},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6654183864593506},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6447387933731079},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.5831322073936462},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5719646215438843},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5445442795753479},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.44117286801338196},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4394626021385193},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4167194664478302},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3746548295021057},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3304857611656189},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32527434825897217},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2802013158798218},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14520114660263062},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.11268773674964905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11108449101448059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403512239456177},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6654183864593506},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6447387933731079},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.5831322073936462},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5719646215438843},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5445442795753479},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.44117286801338196},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4394626021385193},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4167194664478302},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3746548295021057},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3304857611656189},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32527434825897217},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2802013158798218},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14520114660263062},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.11268773674964905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11108449101448059},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3129647","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3129647","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/4359390/09623517.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tpds.2021.3129647","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3129647","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/4359390/09623517.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G3240443966","display_name":null,"funder_award_id":"61802420","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3606055544","display_name":null,"funder_award_id":"62025208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8613193636","display_name":null,"funder_award_id":"62172430","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3217357178.pdf","grobid_xml":"https://content.openalex.org/works/W3217357178.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2019459561","https://openalex.org/W2067523571","https://openalex.org/W2155893237","https://openalex.org/W2162385899","https://openalex.org/W2163605009","https://openalex.org/W2289252105","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2791673912","https://openalex.org/W2900228909","https://openalex.org/W2909419460","https://openalex.org/W2945146780","https://openalex.org/W2955425717","https://openalex.org/W2962752334","https://openalex.org/W2962970995","https://openalex.org/W2963037463","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W2982196009","https://openalex.org/W2989762710","https://openalex.org/W2990661479","https://openalex.org/W3007459273","https://openalex.org/W3012561096","https://openalex.org/W3035421056","https://openalex.org/W3040024858","https://openalex.org/W3047390932","https://openalex.org/W3097528158","https://openalex.org/W3101543398","https://openalex.org/W3107562138","https://openalex.org/W3114929349","https://openalex.org/W3127131099","https://openalex.org/W3184698997","https://openalex.org/W4287811529","https://openalex.org/W4297775537","https://openalex.org/W6684191040","https://openalex.org/W6737664043","https://openalex.org/W6762718338","https://openalex.org/W6766029800","https://openalex.org/W6770165107","https://openalex.org/W6777291753"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W2187181201"],"abstract_inverted_index":{"Compact":[0],"convolutional":[1,30,44,76,174],"neural":[2,34,45],"networks":[3],"have":[4],"become":[5],"a":[6,140],"hot":[7],"research":[8],"topic.":[9],"However,":[10],"we":[11,47,117],"find":[12],"that":[13,60],"the":[14,33,49,70,81,86,92,99,101,104,112,119,124,127,136,162,165,169,190,196,200,204,211,215,220,229,238,241,248],"systolic":[15,38,51,88,192],"array":[16,52,129,142,193,198],"accelerators":[17],"are":[18],"extremely":[19],"inefficient":[20],"in":[21,32,98,172,234],"dealing":[22],"with":[23,144,159],"compact":[24,43],"models,":[25],"especially":[26],"when":[27],"processing":[28,58,96,147],"depthwise":[29,75,173],"layers":[31,77,175],"networks.":[35],"To":[36],"make":[37],"arrays":[39],"more":[40],"efficient":[41],"for":[42,123],"networks,":[46],"propose":[48],"heterogeneous":[50,57],"(HeSA)":[53],"architecture.":[54,194],"It":[55],"introduces":[56],"elements":[59,97,148],"support":[61],"multiple":[62],"modes":[63],"of":[64,74,85,95,168,240],"dataflow,":[65],"which":[66],"can":[67,138,202],"further":[68],"exploit":[69],"reuse":[71,223],"data":[72,205,222,227],"chance":[73,224],"and":[78,107,130,151,180,225],"without":[79],"changing":[80],"scale":[82],"or":[83],"structure":[84,122],"nave":[87],"array.":[89],"By":[90,218],"increasing":[91],"utilization":[93,149,166],"rate":[94,150,167],"array,":[100],"HeSA":[102,137,163,201,230,242],"improves":[103,164],"performance,":[105],"throughput,":[106],"energy":[108,235],"efficiency":[109],"compared":[110,188,246],"to":[111,189,247,251],"standard":[113,191],"baseline.":[114],"In":[115,195],"addition,":[116],"design":[118,143],"flexible":[120,134],"buffer":[121],"communication":[125,153],"between":[126],"computing":[128,170],"external":[131],"buffer.":[132],"Through":[133],"routing,":[135],"achieve":[139],"large-scale":[141,197],"maintaining":[145,210],"high":[146],"low":[152],"costs.":[154],"Based":[155],"on":[156],"our":[157],"evaluation":[158],"typical":[160],"workloads,":[161],"resource":[171],"by":[176,207],"4.5":[177],"-":[178,183],"11.2":[179],"acquires":[181],"1.6":[182],"3.1":[184],"total":[185],"performance":[186,213],"speedup":[187],"design,":[199],"reduce":[203],"traffic":[206],"40%":[208],"while":[209],"same":[212],"as":[214],"scaling-out":[216],"method.":[217],"improving":[219],"on-chip":[221],"reducing":[226],"traffic,":[228],"saves":[231],"over":[232],"20%":[233],"consumption.":[236],"Meanwhile,":[237],"area":[239],"is":[243],"basically":[244],"unchanged":[245],"baseline":[249],"due":[250],"its":[252],"simple":[253],"design.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}