{"id":"https://openalex.org/W4378801068","doi":"https://doi.org/10.1145/3583781.3590318","title":"A Scalable BFloat16 Dot-Product Architecture for Deep Learning","display_name":"A Scalable BFloat16 Dot-Product Architecture for Deep Learning","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4378801068","doi":"https://doi.org/10.1145/3583781.3590318"},"language":"en","primary_location":{"id":"doi:10.1145/3583781.3590318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583781.3590318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2023","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/A5100601932","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-4190-3065"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044840341","display_name":"Libo Huang","orcid":"https://orcid.org/0000-0001-7878-3998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Huang","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019476529","display_name":"Hongbing Tan","orcid":"https://orcid.org/0000-0003-4184-4173"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbing Tan","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Zheng","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101617974","display_name":"Hui Guo","orcid":"https://orcid.org/0000-0001-5131-0437"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Guo","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.865,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68228137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9940000176429749,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9926999807357788,"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/rounding","display_name":"Rounding","score":0.7469701170921326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7052540183067322},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6052951216697693},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5980820655822754},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5758787393569946},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5307778120040894},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.44765201210975647},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4476251006126404},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4172445833683014},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.408985435962677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.270308256149292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11926966905593872},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0917162299156189}],"concepts":[{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.7469701170921326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052540183067322},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6052951216697693},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5980820655822754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5758787393569946},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5307778120040894},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.44765201210975647},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4476251006126404},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4172445833683014},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.408985435962677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.270308256149292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11926966905593872},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0917162299156189},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583781.3590318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583781.3590318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2012090333","https://openalex.org/W2132729131","https://openalex.org/W2313356641","https://openalex.org/W2947629474","https://openalex.org/W4243590860","https://openalex.org/W4284978237","https://openalex.org/W4285200511","https://openalex.org/W4312291691","https://openalex.org/W4312872667"],"related_works":["https://openalex.org/W4220780102","https://openalex.org/W2410881844","https://openalex.org/W3196334750","https://openalex.org/W1502401885","https://openalex.org/W2004257129","https://openalex.org/W2116281088","https://openalex.org/W2357551824","https://openalex.org/W2016668641","https://openalex.org/W2019368960","https://openalex.org/W2349094459"],"abstract_inverted_index":{"BFloat16(BF16)":[0],"format":[1],"has":[2],"recently":[3],"driven":[4],"the":[5,21,48,64,67,96,99,118,121,131],"development":[6],"of":[7,66,113,120],"deep":[8],"learning":[9],"due":[10],"to":[11,77,87],"its":[12],"higher":[13,141],"energy":[14,138],"efficiency":[15,139],"and":[16,80,83,90,109,140,147],"less":[17],"memory":[18],"consumption":[19],"than":[20],"traditional":[22],"format.":[23],"This":[24],"paper":[25],"presents":[26],"a":[27,44,110],"scalable":[28],"BF16":[29],"dot-product(DoP)":[30],"architecture":[31,101,133],"for":[32,106,129],"high-performance":[33],"deep-learning":[34],"computing.":[35],"A":[36],"novel":[37],"4-term":[38,52,107],"DoP":[39,53,59,122],"unit":[40],"is":[41,75,115],"proposed":[42,100,132],"as":[43,117],"fundamental":[45,68],"module":[46],"in":[47,55,70],"architecture,":[49],"which":[50,71],"performs":[51],"operation":[54,123],"three":[56],"cycles.":[57],"More-term":[58],"units":[60],"are":[61,85],"constructed":[62],"through":[63],"extension":[65],"unit,":[69],"early":[72],"exponent":[73],"comparison":[74],"performed":[76],"hide":[78],"latency,":[79],"intermediate":[81],"normalization":[82],"rounding":[84],"omitted":[86],"improve":[88],"accuracy":[89],"further":[91],"reduce":[92],"latency.":[93],"Compared":[94,125],"with":[95,126,143],"discrete":[97],"design,":[98],"reduces":[102],"latency":[103,114],"by":[104],"22.8%":[105],"DoP,":[108],"larger":[111],"proportion":[112],"reduced":[116],"size":[119],"increases.":[124],"existing":[127],"designs":[128],"BF16,":[130],"at":[134,144],"64-term":[135],"exhibits":[136],"better-normalized":[137],"throughput":[142],"least":[145],"1.88\u00d7":[146],"20.3\u00d7":[148],"improvement,":[149],"respectively.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}