{"id":"https://openalex.org/W3184376546","doi":"https://doi.org/10.1145/3460776","title":"Configurable Multi-directional Systolic Array Architecture for Convolutional Neural Networks","display_name":"Configurable Multi-directional Systolic Array Architecture for Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-07-17","ids":{"openalex":"https://openalex.org/W3184376546","doi":"https://doi.org/10.1145/3460776","mag":"3184376546"},"language":"en","primary_location":{"id":"doi:10.1145/3460776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3460776","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3460776","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3460776","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/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":true,"raw_author_name":"Rui Xu","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"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":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","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/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":"Yaohua Wang","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029556003","display_name":"Xinhai Chen","orcid":"https://orcid.org/0000-0002-2931-4893"},"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":"Xinhai Chen","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","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":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101888900"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":3.0108,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.92842721,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"18","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9984999895095825,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9878000020980835,"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/systolic-array","display_name":"Systolic array","score":0.9608581066131592},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8479733467102051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7570540904998779},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7097933292388916},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.585869550704956},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5281194448471069},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5237424373626709},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4768589437007904},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4283333420753479},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41188639402389526},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3432890772819519},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33219999074935913},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.28617510199546814},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2731718420982361},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22865569591522217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11847710609436035}],"concepts":[{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.9608581066131592},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8479733467102051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570540904998779},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7097933292388916},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.585869550704956},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5281194448471069},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5237424373626709},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4768589437007904},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4283333420753479},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41188639402389526},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3432890772819519},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.28617510199546814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2731718420982361},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22865569591522217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11847710609436035},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3460776","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3460776","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3460776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3460776","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3460776","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G2187338242","display_name":null,"funder_award_id":"61672526","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3996695050","display_name":null,"funder_award_id":"2018YFB0204301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6809183074","display_name":null,"funder_award_id":"Project No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"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/W3184376546.pdf","grobid_xml":"https://content.openalex.org/works/W3184376546.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2019459561","https://openalex.org/W2067523571","https://openalex.org/W2108598243","https://openalex.org/W2147800946","https://openalex.org/W2152839228","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2531409750","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2618530766","https://openalex.org/W2625954420","https://openalex.org/W2790925711","https://openalex.org/W2900228909","https://openalex.org/W2945146780","https://openalex.org/W2946948417","https://openalex.org/W2949660525","https://openalex.org/W2949870694","https://openalex.org/W2972054167","https://openalex.org/W2980104813","https://openalex.org/W2980200167","https://openalex.org/W3012178976","https://openalex.org/W3016542674","https://openalex.org/W3047390932","https://openalex.org/W3091512799","https://openalex.org/W3094406919","https://openalex.org/W3097528158","https://openalex.org/W3118608800","https://openalex.org/W4249970585"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W2807127337","https://openalex.org/W2964954556","https://openalex.org/W3019910406"],"abstract_inverted_index":{"The":[0,17,85],"systolic":[1,22,41,58,99,109,124,132,197,216,242,276],"array":[2,23,42,82,110,133,153,172,198,243],"architecture":[3,24,92],"is":[4,25,88],"one":[5],"of":[6,20,64,80,97,141,169,178,249],"the":[7,21,40,57,68,74,81,90,95,98,123,131,139,147,152,167,170,176,195,229,240,246,260,269,274],"most":[8],"popular":[9],"choices":[10],"for":[11],"convolutional":[12],"neural":[13],"network":[14],"hardware":[15,37,203],"accelerators.":[16],"biggest":[18],"advantage":[19,51],"its":[26],"simple":[27,91],"and":[28,35,159,192,205,273,282],"efficient":[29],"design":[30,93,105],"principle.":[31],"Without":[32],"complicated":[33],"control":[34],"dataflow,":[36],"accelerators":[38],"with":[39],"can":[43,206,227,258],"calculate":[44],"traditional":[45,275],"convolution":[46,70,254],"very":[47],"efficiently.":[48],"However,":[49],"this":[50,102],"also":[52],"brings":[53],"new":[54],"challenges":[55],"to":[56,112,122,129,136,165,173,194,235,239,265],"array.":[59,100,125],"When":[60,251],"computing":[61],"special":[62],"types":[63],"convolution,":[65,73],"such":[66,218],"as":[67,219],"small-scale":[69,142],"or":[71],"depthwise":[72,179,253],"processing":[75],"element":[76],"(PE)":[77],"utilization":[78,231,261],"rate":[79,232,262],"decreases":[83],"sharply.":[84],"main":[86],"reason":[87],"that":[89,151,213],"limits":[94],"flexibility":[96],"In":[101,181],"article,":[103],"we":[104,117,145,186],"a":[106,119,189],"configurable":[107],"multi-directional":[108],"(CMSA)":[111],"address":[113],"these":[114],"issues.":[115],"First,":[116],"added":[118],"data":[120,156],"path":[121],"It":[126,200],"allows":[127,163],"users":[128,164],"split":[130],"through":[134],"configuration":[135],"speed":[137,174],"up":[138,175,234,264],"calculation":[140,177],"convolution.":[143,180],"Second,":[144],"redesigned":[146],"PE":[148,171,230],"unit":[149],"so":[150],"has":[154],"multiple":[155],"transmission":[157],"modes":[158],"dataflow":[160,168],"strategies.":[161],"This":[162],"switch":[166],"addition,":[182],"unlike":[183],"other":[184],"works,":[185],"only":[187],"make":[188],"few":[190],"changes":[191],"modifications":[193],"existing":[196],"architecture.":[199],"avoids":[201],"additional":[202],"overheads":[204],"be":[207],"easily":[208],"deployed":[209],"in":[210,255,280],"application":[211],"scenarios":[212],"require":[214],"small":[215],"arrays":[217,277],"mobile":[220],"terminals.":[221],"Based":[222],"on":[223],"our":[224],"evaluation,":[225],"CMSA":[226,257,272],"increase":[228,259],"by":[233,263],"1.6":[236],"times":[237],"compared":[238],"typical":[241],"when":[244],"running":[245,252],"last":[247],"layers":[248],"ResNet-18.":[250],"MobileNet,":[256],"14.8":[266],"times.":[267],"At":[268],"same":[270],"time,":[271],"are":[278],"similar":[279],"area":[281],"energy":[283],"consumption.":[284]},"counts_by_year":[{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}