{"id":"https://openalex.org/W4210396250","doi":"https://doi.org/10.1109/tcad.2022.3146202","title":"BitCluster: Fine-Grained Weight Quantization for Load-Balanced Bit-Serial Neural Network Accelerators","display_name":"BitCluster: Fine-Grained Weight Quantization for Load-Balanced Bit-Serial Neural Network Accelerators","publication_year":2022,"publication_date":"2022-01-25","ids":{"openalex":"https://openalex.org/W4210396250","doi":"https://doi.org/10.1109/tcad.2022.3146202"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2022.3146202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2022.3146202","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/A5100413656","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3615-6755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3615-6755","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028066238","display_name":"Huiyu Mo","orcid":"https://orcid.org/0000-0002-3373-7178"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Mo","raw_affiliation_strings":["School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017205152","display_name":"Wenping Zhu","orcid":"https://orcid.org/0000-0002-3276-4019"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenping Zhu","raw_affiliation_strings":["School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3276-4019","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456471","display_name":"Li Qiang","orcid":"https://orcid.org/0000-0002-8505-8556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Li","raw_affiliation_strings":["Mobileye R&#x0026;D China, Intel Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobileye R&#x0026;D China, Intel Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054524841","display_name":"Shouyi Yin","orcid":"https://orcid.org/0000-0003-2309-572X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyi Yin","raw_affiliation_strings":["School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036023084","display_name":"Shaojun Wei","orcid":"https://orcid.org/0000-0001-5117-7920"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wei","raw_affiliation_strings":["School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358856","display_name":"Leibo Liu","orcid":"https://orcid.org/0000-0001-7548-4116"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leibo Liu","raw_affiliation_strings":["School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7548-4116","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8597,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.86395165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"41","issue":"11","first_page":"4747","last_page":"4757"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7762830853462219},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7028759121894836},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6864199638366699},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6602382659912109},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6232516765594482},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.512782633304596},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4626859426498413},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4090612530708313},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4054747223854065},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3977759778499603},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3819187879562378},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3654785752296448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25472402572631836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24315595626831055}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7762830853462219},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7028759121894836},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6864199638366699},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6602382659912109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6232516765594482},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.512782633304596},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4626859426498413},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4090612530708313},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4054747223854065},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3977759778499603},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3819187879562378},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3654785752296448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25472402572631836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24315595626831055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2022.3146202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2022.3146202","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/G7358963331","display_name":null,"funder_award_id":"2018YFB2202101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7442261201","display_name":null,"funder_award_id":"61834002","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2067523571","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2330958039","https://openalex.org/W2522548197","https://openalex.org/W2794141774","https://openalex.org/W2931118404","https://openalex.org/W2962843773","https://openalex.org/W2963367920","https://openalex.org/W2963703197","https://openalex.org/W2979515806","https://openalex.org/W3016163932","https://openalex.org/W3092182048","https://openalex.org/W3092348244","https://openalex.org/W3108835732","https://openalex.org/W4247198796","https://openalex.org/W6637373629","https://openalex.org/W6696004547","https://openalex.org/W6696798448","https://openalex.org/W6727690538","https://openalex.org/W6729126992","https://openalex.org/W6730047919","https://openalex.org/W6737664043","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6763456558","https://openalex.org/W6773270737","https://openalex.org/W6785885990"],"related_works":["https://openalex.org/W2777249922","https://openalex.org/W156843270","https://openalex.org/W2470589840","https://openalex.org/W4294734199","https://openalex.org/W2007449167","https://openalex.org/W2898755250","https://openalex.org/W3042701997","https://openalex.org/W3216454443","https://openalex.org/W2770717529","https://openalex.org/W4289086683"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,115],"network":[2],"(CNN)":[3],"has":[4],"demonstrated":[5],"great":[6],"success":[7],"in":[8,35,69,113],"pattern":[9],"recognition":[10],"scenarios":[11],"at":[12],"the":[13,32,40,47,59,98,131,138,167],"cost":[14],"of":[15,18,46,65,79,101],"nearly":[16],"billions":[17],"parameters":[19],"and":[20,62,181],"consequent":[21],"convolution":[22],"operations.":[23],"Various":[24],"dedicated":[25],"hardware":[26,73,179],"designs":[27],"are":[28],"proposed":[29,92,120],"to":[30,93,110,121],"accelerate":[31],"CNN":[33,158],"computation":[34],"more":[36],"energy-efficient":[37],"manners.":[38],"Especially,":[39],"bit-serial":[41],"accelerator":[42],"(BSA)":[43],"is":[44,91,119,146],"one":[45],"most":[48],"effective":[49],"approaches":[50],"on":[51,149,190,206],"resource-limited":[52],"platforms":[53],"by":[54,154],"eliminating":[55],"zero-bit":[56],"computations.":[57],"However,":[58],"irregular":[60],"distribution":[61],"varying":[63],"number":[64,100],"effectual":[66,102],"(nonzero)":[67],"bits":[68,103],"weights":[70],"significantly":[71,136],"cause":[72],"underutilization,":[74],"impeding":[75],"further":[76,123],"performance":[77,140],"improvement":[78],"state-of-the-art":[80,193],"BSAs.":[81],"To":[82],"address":[83],"this":[84],"issue,":[85],"BitCluster,":[86],"a":[87,150],"hardware-friendly":[88],"quantization":[89,133],"method,":[90],"make":[94],"each":[95],"weight":[96,111,126],"with":[97,141,195],"identical":[99],"for":[104,124],"load-balanced":[105],"computation.":[106],"Considering":[107],"distinct":[108],"sensitivities":[109],"precision":[112],"different":[114],"layers,":[116],"layer-level":[117],"BitCluster":[118,145],"design":[122,153],"fine-grained":[125],"quantization.":[127],"It":[128],"systematically":[129],"determines":[130],"layerwise":[132],"configurations,":[134],"which":[135],"improve":[137],"overall":[139],"<1%":[142],"accuracy":[143],"loss.":[144],"comprehensively":[147],"evaluated":[148],"BitCluster-compatible":[151],"BSA":[152,169],"taking":[155],"six":[156],"mainstream":[157],"models":[159],"as":[160],"benchmarks.":[161],"The":[162],"experimental":[163],"results":[164],"show":[165],"that":[166],"BitCluster-based":[168],"achieves":[170],"<inline-formula":[171,182,196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172,183,197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[173,184,198],"<tex-math":[174,185,199],"notation=\"LaTeX\">$1.6\\times":[175],"$":[176,187,201],"</tex-math></inline-formula>":[177,188,202],"higher":[178],"utilization":[180],"notation=\"LaTeX\">$3.4\\times":[186],"speedup":[189],"average":[191],"than":[192],"BSAs,":[194],"notation=\"LaTeX\">$5\\times":[200],"better":[203],"energy":[204],"efficiency":[205],"average.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}