{"id":"https://openalex.org/W4405518161","doi":"https://doi.org/10.1109/tvlsi.2024.3515217","title":"An Efficient Sparse CNN Inference Accelerator With Balanced Intra- and Inter-PE Workload","display_name":"An Efficient Sparse CNN Inference Accelerator With Balanced Intra- and Inter-PE Workload","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4405518161","doi":"https://doi.org/10.1109/tvlsi.2024.3515217"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2024.3515217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3515217","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/A5034974345","display_name":"Jianbo Guo","orcid":"https://orcid.org/0000-0002-2762-7423"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianbo Guo","raw_affiliation_strings":["School of Microelectronics, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103994442","display_name":"Tongqing Xu","orcid":"https://orcid.org/0009-0009-6214-613X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongqing Xu","raw_affiliation_strings":["School of Microelectronics, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113864232","display_name":"Zhenyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyang Wu","raw_affiliation_strings":["School of Microelectronics, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101552420","display_name":"Hao Xiao","orcid":"https://orcid.org/0000-0003-4009-3689"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Xiao","raw_affiliation_strings":["School of Microelectronics, Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034974345"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.9971,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78375899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":"5","first_page":"1278","last_page":"1291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.989300012588501,"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":0.989300012588501,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9890000224113464,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/workload","display_name":"Workload","score":0.7283135652542114},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7275758385658264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6176348924636841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4041094183921814},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3663991093635559},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12417897582054138}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7283135652542114},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7275758385658264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176348924636841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4041094183921814},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3663991093635559},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12417897582054138}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2024.3515217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3515217","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/G1738348546","display_name":null,"funder_award_id":"61974039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G744300498","display_name":null,"funder_award_id":"61834006","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":37,"referenced_works":["https://openalex.org/W2070167224","https://openalex.org/W2750173518","https://openalex.org/W2899481200","https://openalex.org/W2900228909","https://openalex.org/W2921918777","https://openalex.org/W2940399336","https://openalex.org/W3006336861","https://openalex.org/W3015599230","https://openalex.org/W3038838661","https://openalex.org/W3088144810","https://openalex.org/W3092513807","https://openalex.org/W3093799822","https://openalex.org/W3097528158","https://openalex.org/W3118404249","https://openalex.org/W3132745255","https://openalex.org/W3133293092","https://openalex.org/W3147182033","https://openalex.org/W3159322265","https://openalex.org/W3164019007","https://openalex.org/W3165088248","https://openalex.org/W3174641885","https://openalex.org/W3187481008","https://openalex.org/W3196365326","https://openalex.org/W4205884968","https://openalex.org/W4206672975","https://openalex.org/W4229439743","https://openalex.org/W4240168186","https://openalex.org/W4285250061","https://openalex.org/W4291653242","https://openalex.org/W4311412773","https://openalex.org/W4360770687","https://openalex.org/W4367728006","https://openalex.org/W4387886174","https://openalex.org/W4389459222","https://openalex.org/W4390771525","https://openalex.org/W4392796609","https://openalex.org/W6638783484"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547"],"abstract_inverted_index":{"Sparse":[0],"convolutional":[1,32],"neural":[2,33],"networks":[3,34],"(SCNNs)":[4],"which":[5,51,68,148],"can":[6,69],"prune":[7],"trivial":[8],"parameters":[9],"in":[10],"the":[11,15,28,37,53,56,72,98,103,123,129,179,193],"network":[12],"while":[13],"maintaining":[14],"model":[16],"accuracy":[17],"has":[18,187],"been":[19,188],"proved":[20],"to":[21,26,45,89,96,114,127,135,155,212,234],"be":[22],"an":[23,64,182],"attractive":[24],"approach":[25],"alleviate":[27,97,128],"heavy":[29],"computation":[30,49,125],"of":[31,55,174],"(CNNs).":[35],"However,":[36],"invalid":[38],"data":[39,157],"resulting":[40],"from":[41,158],"sparse":[42,91],"patterns":[43],"leads":[44],"unnecessary":[46],"and":[47,77,152,165,190,226],"irregular":[48],"workload,":[50],"challenges":[52],"efficiency":[54,225],"underlying":[57],"hardware":[58],"accelerators.":[59],"Therefore,":[60],"this":[61],"article":[62],"proposes":[63],"SCNN":[65,184],"inference":[66,185],"accelerator,":[67],"deal":[70],"with":[71,119,199],"imbalanced":[73],"workload":[74],"both":[75],"intra-":[76],"interprocessing":[78],"element":[79],"(PE).":[80],"A":[81],"valid":[82],"weight":[83,142],"encoding":[84],"(VWE)":[85],"scheme":[86],"is":[87,112,146],"proposed":[88,113,180],"compress":[90],"weights":[92],"into":[93,122],"dense":[94],"ones":[95],"load":[99,108,130],"imbalance":[100,131],"intra-PE.":[101],"Leveraging":[102],"VWE":[104],"scheme,":[105,181],"a":[106,140,150],"randomized":[107],"rearrangement":[109],"(RLR)":[110],"method":[111],"dynamically":[115],"schedule":[116],"convolution":[117],"kernels":[118],"similar":[120],"sparsity":[121],"same":[124],"batch":[126],"inter-PEs.":[132],"In":[133],"addition,":[134],"reduce":[136],"off-chip":[137,163],"memory":[138],"accesses,":[139],"recurrent":[141],"stationary":[143],"(RWS)":[144],"dataflow":[145],"proposed,":[147],"adopts":[149],"small-batch":[151],"multichannel":[153],"strategy":[154],"stack":[156],"multiple":[159],"channels":[160],"within":[161],"one":[162],"access":[164],"let":[166],"them":[167],"compute":[168],"simultaneously":[169],"thereby":[170],"enabling":[171],"efficient":[172,183],"reuse":[173],"on-chip":[175],"data.":[176],"Based":[177],"on":[178,192],"accelerator":[186],"designed":[189],"verified":[191],"field-programmable":[194],"gate":[195],"array":[196],"(FPGA).":[197],"Compared":[198],"state-of-the-art":[200],"works,":[201],"our":[202],"design":[203],"achieves":[204],"<inline-formula":[205,213,227,235],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[206,214,228,236],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[207,215,229,237],"<tex-math":[208,216,230,238],"notation=\"LaTeX\">$1.16\\times":[209],"$":[210,218,232,240],"</tex-math></inline-formula>":[211,219,233,241],"notation=\"LaTeX\">$2.77\\times":[217],"higher":[220,242],"digital":[221],"signal":[222],"processors":[223],"(DSPs)":[224],"notation=\"LaTeX\">$1.75\\times":[231],"notation=\"LaTeX\">$15\\times":[239],"logic":[243],"efficiency.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}