{"id":"https://openalex.org/W3134012069","doi":"https://doi.org/10.1109/tvlsi.2021.3060041","title":"SWM: A High-Performance Sparse-Winograd Matrix Multiplication CNN Accelerator","display_name":"SWM: A High-Performance Sparse-Winograd Matrix Multiplication CNN Accelerator","publication_year":2021,"publication_date":"2021-03-09","ids":{"openalex":"https://openalex.org/W3134012069","doi":"https://doi.org/10.1109/tvlsi.2021.3060041","mag":"3134012069"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2021.3060041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2021.3060041","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","raw_type":"journal-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/A5100711647","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-5022-0090"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["State Key Laboratory of Application Specific Integrated Circuit (ASIC) and System, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5022-0090","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Application Specific Integrated Circuit (ASIC) and System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066019284","display_name":"Xitian Fan","orcid":"https://orcid.org/0000-0001-8698-6584"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xitian Fan","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8698-6584","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694034","display_name":"Wei Cao","orcid":"https://orcid.org/0000-0003-0339-7093"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210132426","display_name":"Shanghai Fudan Microelectronics (China)","ror":"https://ror.org/02vfj3j86","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Cao","raw_affiliation_strings":["School of Microelectronics, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0339-7093","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210132426"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002732486","display_name":"Lingli Wang","orcid":"https://orcid.org/0000-0002-0579-3527"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210132426","display_name":"Shanghai Fudan Microelectronics (China)","ror":"https://ror.org/02vfj3j86","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingli Wang","raw_affiliation_strings":["School of Microelectronics, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0579-3527","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210132426"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":2.8744,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.91758958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"29","issue":"5","first_page":"936","last_page":"949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.7520399689674377},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.602956235408783},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5854173898696899},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.570671558380127},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.559614896774292},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5522859692573547},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5340734124183655},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.49782419204711914},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.42829763889312744},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.41457802057266235},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37399953603744507},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3327515423297882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22761785984039307},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1893313229084015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520399689674377},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.602956235408783},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5854173898696899},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.570671558380127},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.559614896774292},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5522859692573547},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5340734124183655},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.49782419204711914},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.42829763889312744},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.41457802057266235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37399953603744507},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3327515423297882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22761785984039307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1893313229084015},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2021.3060041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2021.3060041","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G6990557108","display_name":null,"funder_award_id":"61971143","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2119144962","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2516141709","https://openalex.org/W2565851976","https://openalex.org/W2613119772","https://openalex.org/W2623629680","https://openalex.org/W2625457103","https://openalex.org/W2657126969","https://openalex.org/W2729080111","https://openalex.org/W2768993447","https://openalex.org/W2798487653","https://openalex.org/W2808917878","https://openalex.org/W2808970127","https://openalex.org/W2809121165","https://openalex.org/W2895540242","https://openalex.org/W2899481200","https://openalex.org/W2904331435","https://openalex.org/W2904902077","https://openalex.org/W2908968233","https://openalex.org/W2915106038","https://openalex.org/W2921918777","https://openalex.org/W2940399336","https://openalex.org/W2945146780","https://openalex.org/W2949619037","https://openalex.org/W2953915593","https://openalex.org/W2963416938","https://openalex.org/W2963594949","https://openalex.org/W2964299589","https://openalex.org/W2964525696","https://openalex.org/W3003431487","https://openalex.org/W3015599230","https://openalex.org/W3041223772","https://openalex.org/W3047345547","https://openalex.org/W3093577244","https://openalex.org/W4240168186","https://openalex.org/W4243682116","https://openalex.org/W6637373629","https://openalex.org/W6677580257","https://openalex.org/W6747766405"],"related_works":["https://openalex.org/W3157543420","https://openalex.org/W2293771254","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W2914631005","https://openalex.org/W2123154672","https://openalex.org/W2032786851","https://openalex.org/W2952630098","https://openalex.org/W3132517792"],"abstract_inverted_index":{"Many":[0],"convolutional":[1],"neural":[2],"network":[3],"(CNN)":[4],"accelerators":[5,28],"are":[6,80],"proposed":[7,81],"to":[8,16,62,82,93,105,138],"exploit":[9,30,42],"the":[10,13,18,31,49,63,84,95,107,139,148,151,155,203],"sparsity":[11,32,44,64],"of":[12,20,33,150],"networks":[14],"recently":[15],"enjoy":[17],"benefits":[19],"both":[21,34,43,112,131],"computation":[22],"and":[23,36,75,98,115,129,133,164,175,215],"memory":[24],"reduction.":[25],"However,":[26],"most":[27,169],"cannot":[29,47],"activations":[35],"weights.":[37],"For":[38],"those":[39],"works":[40],"that":[41],"opportunities,":[45],"they":[46],"achieve":[48,145,209],"stable":[50],"load":[51,85,96],"balance":[52,97],"through":[53],"a":[54,69,76],"static":[55],"scheduling":[56,78],"(SS)":[57],"strategy,":[58],"which":[59,110,166],"is":[60,90,160],"vulnerable":[61],"distribution.":[65],"In":[66],"this":[67],"work,":[68],"balanced":[70],"compressed":[71],"sparse":[72,113,116,179],"row":[73],"format":[74],"dynamic":[77],"strategy":[79],"improve":[83],"balance.":[86],"A":[87],"set-associate":[88],"structure":[89],"also":[91],"presented":[92],"tradeoff":[94],"hardware":[99],"resource":[100],"overhead.":[101],"We":[102],"propose":[103],"SWM":[104,121,189],"accelerate":[106],"CNN":[108],"inference,":[109],"supports":[111,130],"convolution":[114,127,174],"fully":[117],"connected":[118],"(FC)":[119],"layers.":[120],"provides":[122],"Winograd":[123],"adaptability":[124],"for":[125,172,178,196],"large":[126],"kernels":[128],"16-bit":[132,152,183,199],"8-bit":[134,142],"quantized":[135],"CNNs.":[136],"Due":[137],"activation":[140],"sharing,":[141],"processing":[143,153],"can":[144,190,208],"theoretically":[146],"twice":[147],"performance":[149],"with":[154,162,182,198,202],"same":[156],"sparsity.":[157],"The":[158],"architecture":[159],"evaluated":[161],"VGG16":[163],"ResNet50,":[165],"achieves:":[167],"at":[168,210],"7.6":[170],"TOP/s":[171,177],"sparse-Winograd":[173],"three":[176],"matrix":[180],"multiplication":[181],"quantization":[184],"on":[185],"Xilinx":[186],"VCU1525":[187],"platform.":[188],"process":[191],"310/725":[192],"images":[193],"per":[194],"second":[195],"VGG16/ResNet50":[197],"quantization.":[200],"Compared":[201],"state-of-the-art":[204],"works,":[205],"our":[206],"design":[207],"least":[211],"1.53":[212],"\u00d7":[213,217],"speedup":[214],"1.8":[216],"energy":[218],"efficiency":[219],"improvement.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}