{"id":"https://openalex.org/W3189487902","doi":"https://doi.org/10.1109/tcad.2021.3102191","title":"Search-Free Inference Acceleration for Sparse Convolutional Neural Networks","display_name":"Search-Free Inference Acceleration for Sparse Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-08-03","ids":{"openalex":"https://openalex.org/W3189487902","doi":"https://doi.org/10.1109/tcad.2021.3102191","mag":"3189487902"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2021.3102191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3102191","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits 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/A5068283310","display_name":"Bosheng Liu","orcid":"https://orcid.org/0000-0001-7123-7425"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bosheng Liu","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420361","display_name":"Xiaoming Chen","orcid":"https://orcid.org/0000-0002-7337-1844"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Chen","raw_affiliation_strings":["Center for Intelligent Computing Systems, State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Computing Systems, State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016864694","display_name":"Yinhe Han","orcid":"https://orcid.org/0000-0003-0904-6681"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinhe Han","raw_affiliation_strings":["Center for Intelligent Computing Systems, State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Computing Systems, State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060755096","display_name":"Jigang Wu","orcid":"https://orcid.org/0000-0002-6470-9794"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jigang Wu","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015299890","display_name":"Liang Chang","orcid":"https://orcid.org/0000-0002-7262-4707"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Chang","raw_affiliation_strings":["Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346801","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0002-2329-502X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044810210","display_name":"Haobo Xu","orcid":"https://orcid.org/0000-0002-0243-6516"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Xu","raw_affiliation_strings":["Center for Intelligent Computing Systems, State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Computing Systems, State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068283310"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.1942,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48872193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"41","issue":"7","first_page":"2156","last_page":"2169"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7254209518432617},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6532751321792603},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6405783295631409},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6156562566757202},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5455996990203857},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5018100738525391},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4530111253261566},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.44026315212249756},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4308212101459503},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.42484864592552185},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34521734714508057},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33479011058807373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3122630715370178},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2660163640975952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254209518432617},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6532751321792603},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6405783295631409},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6156562566757202},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5455996990203857},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5018100738525391},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4530111253261566},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.44026315212249756},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4308212101459503},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.42484864592552185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34521734714508057},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33479011058807373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3122630715370178},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2660163640975952},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2021.3102191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3102191","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1411627799","display_name":null,"funder_award_id":"XDB44000000","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G536329181","display_name":null,"funder_award_id":"61966009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G558307529","display_name":null,"funder_award_id":"62072118","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6029430578","display_name":null,"funder_award_id":"2018B030311007","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G6546932133","display_name":null,"funder_award_id":"U1711263","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6840496190","display_name":null,"funder_award_id":"U1811264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7311825020","display_name":null,"funder_award_id":"ZDBS-LY-JSC012","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W2048266589","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2105102111","https://openalex.org/W2108598243","https://openalex.org/W2119144962","https://openalex.org/W2152839228","https://openalex.org/W2154590891","https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2516141709","https://openalex.org/W2554302513","https://openalex.org/W2909419460","https://openalex.org/W2945146780","https://openalex.org/W2964081807","https://openalex.org/W2979439447","https://openalex.org/W3006098440","https://openalex.org/W3010389911","https://openalex.org/W3013495280","https://openalex.org/W3016542674","https://openalex.org/W3017059173","https://openalex.org/W3038838661","https://openalex.org/W3119549454","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W6682848092","https://openalex.org/W6724998850","https://openalex.org/W6738105350"],"related_works":["https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2058965144","https://openalex.org/W3167919718","https://openalex.org/W2164382479","https://openalex.org/W2187181201","https://openalex.org/W2076915000","https://openalex.org/W1523361724","https://openalex.org/W2807127337","https://openalex.org/W3157543420"],"abstract_inverted_index":{"Sparse":[0],"convolution":[1,143],"neural":[2],"networks":[3],"(CNNs)":[4],"are":[5],"promising":[6],"in":[7,63,67,200],"reducing":[8],"both":[9],"memory":[10,83],"usage":[11],"and":[12,41,51,82,133,147,218],"computational":[13],"complexity":[14],"while":[15],"still":[16],"preserving":[17],"high":[18,27],"inference":[19,129],"accuracy.":[20],"State-of-the-art":[21],"sparse":[22,43,100,136,142],"CNN":[23,101,137],"accelerators":[24,44],"can":[25],"deliver":[26],"throughput":[28],"by":[29,175],"skipping":[30],"zero":[31],"weights":[32,40,50,110],"and/or":[33],"activations.":[34],"To":[35],"operate":[36],"on":[37,191],"only":[38,155],"nonzero":[39,49],"activations,":[42],"typically":[45],"search":[46,60,97,119],"pairs":[47],"of":[48,75,79,99,106,204],"activations":[52,114],"for":[53,121,135,145,166],"multiplication-accumulation":[54],"(MAC)":[55],"operations.":[56,123],"However,":[57],"the":[58,68,76,96,104,107,112,118,157,177,181,186,197,235],"conventional":[59],"operation":[61],"results":[62],"a":[64,91,163,171,192,201],"severe":[65],"limitation":[66],"processing":[69],"element":[70],"(PE)":[71],"array":[72,238],"scale":[73],"because":[74],"enormous":[77],"demands":[78],"internal":[80],"interconnection":[81,146],"bandwidth.":[84],"In":[85],"this":[86],"article,":[87],"we":[88],"first":[89],"provide":[90],"design":[92],"principle":[93],"to":[94,116,184],"free":[95],"process":[98,120,194],"accelerations.":[102,138],"Specifically,":[103],"indexes":[105],"static":[108],"compressed":[109],"access":[111],"dynamic":[113],"directly":[115],"avoid":[117],"MAC":[122],"We":[124,169],"then":[125],"develop":[126],"two":[127],"search-free":[128,141,158],"accelerators,":[130],"called":[131],"Swan":[132,139],"Swan-flexible,":[134],"supports":[140],"accelerations":[144],"bandwidth":[148],"saving.":[149],"Compared":[150],"with":[151,180,234],"Swan,":[152],"Swan-flexible":[153],"not":[154],"has":[156],"capability":[159],"but":[160],"also":[161],"comprises":[162],"configurable":[164,178],"architecture":[165],"optimum":[167],"throughput.":[168,188],"formulate":[170],"mathematical":[172],"optimization":[173],"problem":[174],"combining":[176],"characterization":[179],"compressive":[182],"dataflow":[183],"optimize":[185],"overall":[187],"Evaluations":[189],"based":[190],"place-and-route":[193],"show":[195],"that":[196],"proposed":[198],"designs,":[199],"compact":[202],"factor":[203],"4096":[205],"PEs,":[206],"achieve":[207],"1.5\u2013":[208],"<inline-formula":[209,220],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[210,221],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[211,222],"<tex-math":[212,223],"notation=\"LaTeX\">$2.7\\times":[213],"$":[214,225],"</tex-math></inline-formula>":[215,226],"higher":[216],"speedup":[217],"6.0\u2013":[219],"notation=\"LaTeX\">$13.6\\times":[224],"better":[227],"energy":[228],"efficiency":[229],"than":[230],"representative":[231],"accelerator":[232],"baselines":[233],"same":[236],"PE":[237],"scale.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}