{"id":"https://openalex.org/W4410893427","doi":"https://doi.org/10.1145/3737462","title":"SPDFA: A Novel Dataflow Fusion Sparse Deep Neural Network Accelerator","display_name":"SPDFA: A Novel Dataflow Fusion Sparse Deep Neural Network Accelerator","publication_year":2025,"publication_date":"2025-05-30","ids":{"openalex":"https://openalex.org/W4410893427","doi":"https://doi.org/10.1145/3737462"},"language":"en","primary_location":{"id":"doi:10.1145/3737462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3737462","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and 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/A5088703563","display_name":"Jinwei Xu","orcid":"https://orcid.org/0000-0003-1242-4217"},"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":"Jinwei Xu","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China"],"raw_orcid":"https://orcid.org/0000-0003-1242-4217","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069310600","display_name":"Jingfei Jiang","orcid":"https://orcid.org/0000-0002-7103-8650"},"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":"Jingfei Jiang","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China"],"raw_orcid":"https://orcid.org/0000-0002-7103-8650","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Gao","orcid":"https://orcid.org/0000-0003-1700-705X"},"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":"Lei Gao","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China"],"raw_orcid":"https://orcid.org/0000-0003-1700-705X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108450320","display_name":"Xifu Qian","orcid":null},"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":"Xifu Qian","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China"],"raw_orcid":"https://orcid.org/0000-0001-6691-660X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"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":"Yong Dou","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China"],"raw_orcid":"https://orcid.org/0000-0002-1256-8934","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09127625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9904999732971191,"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/dataflow","display_name":"Dataflow","score":0.930211067199707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.875366747379303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5417073965072632},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49761202931404114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47372809052467346},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.44889241456985474},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44830620288848877}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.930211067199707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875366747379303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5417073965072632},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49761202931404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47372809052467346},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.44889241456985474},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44830620288848877},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3737462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3737462","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1702756715","display_name":null,"funder_award_id":"2022YFB4501400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2585720638","https://openalex.org/W2618530766","https://openalex.org/W2915106038","https://openalex.org/W2962820060","https://openalex.org/W3016832937","https://openalex.org/W3038838661","https://openalex.org/W3155922894","https://openalex.org/W4213153339","https://openalex.org/W4233429846","https://openalex.org/W4312678586","https://openalex.org/W4318540786","https://openalex.org/W4320712936","https://openalex.org/W4387969481"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640"],"abstract_inverted_index":{"Unstructured":[0],"sparse":[1,21,58,173,183],"pruning":[2],"significantly":[3],"reduces":[4],"the":[5,16,34,46,101,118,137,165],"computational":[6,42,80,144,161],"and":[7,26,74,86,103],"parametric":[8],"complexities":[9],"of":[10,20,36,120,190],"deep":[11,59,174],"neural":[12,60,175,184],"network":[13,176,185],"models.":[14,177],"Nevertheless,":[15],"highly":[17],"irregular":[18],"nature":[19],"models":[22],"limits":[23],"their":[24],"performance":[25,180],"efficiency":[27,81,162,204],"on":[28],"traditional":[29],"computing":[30],"platforms,":[31],"thereby":[32,141],"prompting":[33],"development":[35],"specialized":[37,53],"hardware":[38],"solutions.":[39],"To":[40],"improve":[41],"efficiency,":[43],"we":[44,63,93,123,135],"introduce":[45],"Sparse":[47],"Dataflow":[48],"Fusion":[49],"Accelerator":[50],"(SPDFA),":[51],"a":[52,65,95,131,188,202],"architecture":[54],"meticulously":[55],"designed":[56],"for":[57],"networks.":[61],"Firstly,":[62],"present":[64],"non-blocking":[66],"data":[67],"distribution-computing":[68],"engine":[69,78],"that":[70,109,150],"integrates":[71],"inner":[72],"product":[73],"column":[75],"product.":[76],"This":[77],"boosts":[79],"by":[82,187],"decomposing":[83],"matrix":[84],"multiplication":[85],"convolution":[87],"into":[88],"rectangular":[89],"matrix-vector":[90],"multiplications.":[91],"Secondly,":[92],"implement":[94],"computation":[96],"array":[97],"to":[98,116,164,171],"further":[99,142],"exploit":[100],"parallelism,":[102],"design":[104],"an":[105,125,153],"on-chip":[106],"buffer":[107],"structure":[108],"supports":[110],"multi-line":[111],"memory":[112],"access":[113],"mode.":[114],"Lastly,":[115],"bolster":[117],"adaptability":[119],"our":[121],"accelerator,":[122],"propose":[124],"innovative":[126],"macroinstruction":[127,138],"set":[128],"coupled":[129],"with":[130,201],"micro-kernel":[132],"scheme.":[133],"Furthermore,":[134,178],"refine":[136],"issue":[139],"strategy,":[140],"enhancing":[143],"efficiency.":[145],"Our":[146],"evaluation":[147],"results":[148],"demonstrate":[149],"SPDFA":[151,197],"achieves":[152],"average":[154],"1.29":[155],"\\(\\times\\)":[156,158,192,194],"\u20132.38":[157],"improvement":[159],"in":[160],"compared":[163],"state-of-the-art":[166],"SpMM":[167],"accelerators":[168,186],"when":[169],"applied":[170],"unstructured":[172],"its":[179],"outperforms":[181],"existing":[182],"factor":[189],"1.03":[191],"\u20131.83":[193],".":[195],"Additionally,":[196],"exhibits":[198],"excellent":[199],"scalability":[200],"scaling":[203],"exceeding":[205],"80%.":[206]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}