{"id":"https://openalex.org/W6884607144","doi":"https://doi.org/10.1109/tvlsi.2025.3584657","title":"A High-Performance SCNN Accelerator Using Parallel Sparsity Detection and Index-Oriented Computation Workflow","display_name":"A High-Performance SCNN Accelerator Using Parallel Sparsity Detection and Index-Oriented Computation Workflow","publication_year":2025,"publication_date":"2025-07-10","ids":{"openalex":"https://openalex.org/W6884607144","doi":"https://doi.org/10.1109/tvlsi.2025.3584657"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2025.3584657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2025.3584657","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":null,"display_name":"Yishuo Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yishuo Meng","raw_affiliation_strings":["School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianfei Wang","orcid":"https://orcid.org/0009-0004-0132-3319"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfei Wang","raw_affiliation_strings":["School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-0132-3319","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiang Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Hou","raw_affiliation_strings":["School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siwei Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Xiang","raw_affiliation_strings":["School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ge Li","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chen Yang","orcid":"https://orcid.org/0000-0002-8221-7670"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":["School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-8221-7670","affiliations":[{"raw_affiliation_string":"School of Microelectronics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38437264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"9","first_page":"2449","last_page":"2461"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.545199990272522,"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":0.545199990272522,"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/T12676","display_name":"Machine Learning and ELM","score":0.04650000110268593,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.029100000858306885,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/workflow","display_name":"Workflow","score":0.7057999968528748},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7050999999046326},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5200999975204468},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.478300005197525},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.439300000667572},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3824999928474426},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.3702999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8513000011444092},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7057999968528748},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7050999999046326},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5041999816894531},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.478300005197525},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4390000104904175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2025.3584657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2025.3584657","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":[],"awards":[{"id":"https://openalex.org/G963865091","display_name":null,"funder_award_id":"62176206","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2798170643","https://openalex.org/W2913221350","https://openalex.org/W2964233199","https://openalex.org/W2964525696","https://openalex.org/W2979439447","https://openalex.org/W2987129023","https://openalex.org/W3038838661","https://openalex.org/W3085447111","https://openalex.org/W3090600872","https://openalex.org/W3114479342","https://openalex.org/W3118404249","https://openalex.org/W3132745255","https://openalex.org/W3159322265","https://openalex.org/W3164217046","https://openalex.org/W3185702163","https://openalex.org/W3187481008","https://openalex.org/W3216450673","https://openalex.org/W4205884968","https://openalex.org/W4206719179","https://openalex.org/W4236868170","https://openalex.org/W4285250061","https://openalex.org/W4286571907","https://openalex.org/W4291653242","https://openalex.org/W4291910419","https://openalex.org/W4297094636","https://openalex.org/W4312247188","https://openalex.org/W4320712936","https://openalex.org/W4360606209","https://openalex.org/W4360831992","https://openalex.org/W4385627125","https://openalex.org/W4386902741","https://openalex.org/W4388739202","https://openalex.org/W4390771525","https://openalex.org/W4391326529","https://openalex.org/W4391387876","https://openalex.org/W4394773664","https://openalex.org/W4394841879","https://openalex.org/W4409248508","https://openalex.org/W4409248726"],"related_works":[],"abstract_inverted_index":{"The":[0,146],"customization":[1],"of":[2,19,61,116,143],"accelerators":[3],"for":[4,97],"sparse":[5,99,111],"convolutional":[6],"neural":[7],"networks":[8],"(SCNNs)":[9],"has":[10],"been":[11],"shown":[12],"to":[13,56,83,104,162,183,204,218],"significantly":[14],"enhance":[15],"the":[16,24,59,86,106,114,117,135,163,215],"computational":[17],"efficiency":[18,194],"CNNs.":[20],"However,":[21],"while":[22,158],"processing":[23],"widely":[25],"existing":[26],"irregularly":[27],"distributed":[28],"sparsity":[29,36,62,75,119,220],"in":[30,47,68],"filters":[31],"and":[32,40,81,89,122,132,191],"feature":[33],"maps,":[34],"serial":[35],"detection":[37,76,120],"(SSD)":[38],"methods":[39],"small-capacity":[41],"computation":[42,95,123],"arrays":[43],"are":[44],"always":[45],"applied":[46],"current":[48],"works.":[49],"As":[50],"a":[51,72,125,140,171,192],"result,":[52],"it":[53],"is":[54,79,101,130],"difficult":[55],"fully":[57],"translate":[58,219],"exploitation":[60,221],"into":[63,222],"hardware":[64],"performance":[65,157,172,223],"improvement.":[66],"Therefore,":[67],"this":[69,151,167],"article,":[70],"first,":[71],"novel":[73],"parallel":[74,98],"(PSD)":[77],"scheme":[78,121],"proposed":[80,103],"hardware-implemented":[82],"efficiently":[84],"extract":[85],"valid":[87],"weights":[88],"activations.":[90],"In":[91],"addition,":[92],"an":[93],"index-oriented":[94],"workflow":[96],"convolution":[100],"also":[102],"eliminate":[105],"output":[107],"index":[108],"diversity":[109],"during":[110],"convolutions.":[112],"With":[113],"assistance":[115],"above":[118],"workflow,":[124],"large-scale":[126],"two-side":[127],"SCNN":[128],"accelerator":[129],"designed":[131],"implemented":[133],"on":[134],"Xilinx":[136],"VCU118":[137],"platform,":[138],"achieving":[139],"runtime":[141],"frequency":[142],"300":[144],"MHz.":[145],"evaluation":[147],"results":[148,213],"indicate":[149],"that":[150],"work":[152,168],"can":[153,169],"achieve":[154,170],"1284.43/1105.31":[155],"GOPS":[156],"deploying":[159],"VGG16/ResNet-50.":[160],"Compared":[161],"previous":[164],"dense-/sparse-based":[165],"works,":[166],"enhancement":[173],"ranging":[174],"from":[175,196],"<inline-formula":[176,184,197,205],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[177,185,198,206],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[178,186,199,207],"<tex-math":[179,187,200,208],"notation=\"LaTeX\">$1.284\\times":[180],"$</tex-math>":[181,189,202,210],"</inline-formula>":[182,190,203],"notation=\"LaTeX\">$12.266\\times":[188],"DSP":[193],"improvement":[195],"notation=\"LaTeX\">$1.718\\times":[201],"notation=\"LaTeX\">$6.131\\times":[209],"</inline-formula>.":[211],"These":[212],"highlight":[214],"superior":[216],"ability":[217],"gains.":[224]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}