{"id":"https://openalex.org/W4391183657","doi":"https://doi.org/10.1109/asicon58565.2023.10396574","title":"An Optimized Dataflow Based Accelerator for Sparse Convolutional Neural Networks","display_name":"An Optimized Dataflow Based Accelerator for Sparse Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-10-24","ids":{"openalex":"https://openalex.org/W4391183657","doi":"https://doi.org/10.1109/asicon58565.2023.10396574"},"language":"en","primary_location":{"id":"doi:10.1109/asicon58565.2023.10396574","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asicon58565.2023.10396574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 15th International Conference on ASIC (ASICON)","raw_type":"proceedings-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/A5014283628","display_name":"Xuran Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuran Ding","raw_affiliation_strings":["Central South University,School of Automation,Hunan,China","School of Automation, Central South University, Hunan, China"],"affiliations":[{"raw_affiliation_string":"Central South University,School of Automation,Hunan,China","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"School of Automation, Central South University, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108312957","display_name":"Guowang Su","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guowang Su","raw_affiliation_strings":["Central South University,School of Automation,Hunan,China","School of Automation, Central South University, Hunan, China"],"affiliations":[{"raw_affiliation_string":"Central South University,School of Automation,Hunan,China","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"School of Automation, Central South University, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433265","display_name":"Jun Zhang","orcid":"https://orcid.org/0000-0003-2633-1521"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["Central South University,School of Automation,Hunan,China","School of Automation, Central South University, Hunan, China"],"affiliations":[{"raw_affiliation_string":"Central South University,School of Automation,Hunan,China","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"School of Automation, Central South University, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014283628"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19119382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9991000294685364,"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":0.9990000128746033,"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/dataflow","display_name":"Dataflow","score":0.8738275766372681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817680835723877},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7363855838775635},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7145113348960876},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6216900944709778},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5836145281791687},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4981648921966553},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4940643608570099},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48237767815589905},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.47203078866004944},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.46628662943840027},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.457538366317749},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.39929434657096863},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2772615849971771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22970274090766907},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.09998396039009094}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8738275766372681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817680835723877},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7363855838775635},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7145113348960876},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6216900944709778},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5836145281791687},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4981648921966553},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4940643608570099},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48237767815589905},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.47203078866004944},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.46628662943840027},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.457538366317749},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.39929434657096863},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2772615849971771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22970274090766907},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.09998396039009094},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asicon58565.2023.10396574","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asicon58565.2023.10396574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 15th International Conference on ASIC (ASICON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":10,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2993483871","https://openalex.org/W3038838661","https://openalex.org/W3080842357","https://openalex.org/W3117963962","https://openalex.org/W3118404249","https://openalex.org/W3213578211","https://openalex.org/W4283722322","https://openalex.org/W4293704264","https://openalex.org/W6677580257"],"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/W2187181201","https://openalex.org/W2807127337","https://openalex.org/W3157543420","https://openalex.org/W2532502681"],"abstract_inverted_index":{"Field-programmable":[0],"gate":[1],"arrays":[2],"(FPGAs)":[3],"have":[4],"emerged":[5],"as":[6],"a":[7,46,76,99,124,135,145,152,175],"highly":[8],"promising":[9],"hardware":[10,60],"platform":[11],"for":[12,49,158],"accelerating":[13],"convolutional":[14],"neural":[15],"networks(CNNs)":[16],"inference.":[17],"However,":[18],"most":[19],"existing":[20],"accelerators":[21],"focus":[22],"on":[23,160],"dense":[24,171],"or":[25],"sparse":[26,50,185],"structured":[27],"CNN":[28,172,186],"models":[29],"and":[30,65,94,151,174],"fail":[31],"to":[32,118],"fully":[33],"exploit":[34],"the":[35,81,90,105,113],"inherent":[36],"sparsity":[37,56,91],"in":[38,59,108],"CNNs.":[39,51],"To":[40,70],"address":[41],"this":[42],"limitation,":[43],"we":[44,74,97,122],"propose":[45,75],"reconfigurable":[47,125],"accelerator":[48,143,173],"The":[52],"irregularity":[53],"caused":[54],"by":[55],"presents":[57],"challenges":[58],"implementation,":[61],"including":[62],"load":[63,120],"imbalance":[64],"on-chip":[66],"buffer":[67],"access":[68],"conflicts.":[69],"overcome":[71],"these":[72],"challenges,":[73],"convolution-decomposition":[77],"dataflow":[78],"that":[79,103,141],"transforms":[80],"spatial":[82],"convolution":[83],"into":[84],"matrix-vector":[85],"multiplication,":[86],"thus":[87],"effectively":[88],"leveraging":[89],"of":[92,148,155,179],"activations":[93],"weights.":[95],"Then":[96],"introduce":[98],"bitmap-nonzero":[100],"encoding":[101],"scheme":[102],"matches":[104],"dataflow,":[106],"resulting":[107],"lower":[109],"decoding":[110],"overhead":[111],"during":[112],"nonzero":[114],"detection":[115],"process.":[116],"Moreover,":[117],"mitigate":[119],"imbalance,":[121],"designed":[123],"processing":[126],"element(PE)":[127],"array":[128],"where":[129],"each":[130],"PE":[131,137],"operates":[132],"independently,":[133],"ensuring":[134],"high":[136,146],"utilization.":[138],"Experiments":[139],"demonstrate":[140],"our":[142],"achieves":[144],"performance":[147],"202.68":[149],"GOPs":[150],"DSP":[153,176],"efficiency":[154,177],"1.583":[156],"GOPs/DSP":[157],"VGG-16":[159],"Intel":[161],"Arria10":[162],"SX660":[163],"platform,":[164],"which":[165],"provides":[166],"an":[167],"8.79\u00d7":[168],"speedup":[169],"over":[170,183],"improvement":[178],"1.39\u00d7":[180],"~":[181],"2.24\u00d7":[182],"previous":[184],"accelerators.":[187]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}