{"id":"https://openalex.org/W4387411255","doi":"https://doi.org/10.1109/esscirc59616.2023.10268686","title":"A 4.27TFLOPS/W FP4/FP8 Hybrid-Precision Neural Network Training Processor Using Shift-Add MAC and Reconfigurable PE Array","display_name":"A 4.27TFLOPS/W FP4/FP8 Hybrid-Precision Neural Network Training Processor Using Shift-Add MAC and Reconfigurable PE Array","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4387411255","doi":"https://doi.org/10.1109/esscirc59616.2023.10268686"},"language":"en","primary_location":{"id":"doi:10.1109/esscirc59616.2023.10268686","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/esscirc59616.2023.10268686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESSCIRC 2023- IEEE 49th European Solid State Circuits Conference (ESSCIRC)","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/A5100698555","display_name":"Sunwoo Lee","orcid":"https://orcid.org/0000-0001-7760-0168"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sunwoo Lee","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information,Seoul,Korea","Department of Intelligence and Information, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089174485","display_name":"Jeongwoo Park","orcid":"https://orcid.org/0000-0002-9603-9588"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongwoo Park","raw_affiliation_strings":["Sungkyunkwan University,Department of Semiconductor Systems Engineering,Suwon,Korea","Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon, Korea"],"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Department of Semiconductor Systems Engineering,Suwon,Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053248335","display_name":"Dongsuk Jeon","orcid":"https://orcid.org/0000-0002-0395-8076"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongsuk Jeon","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information,Seoul,Korea","Department of Intelligence and Information, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100698555"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12398765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.994700014591217,"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/T10320","display_name":"Neural Networks and Applications","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7803030610084534},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5359976887702942},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.5075022578239441},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.48498889803886414},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47950321435928345},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4478048086166382},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.44134920835494995},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.4330254793167114},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4253208339214325},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.42489734292030334},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4046924114227295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37647560238838196},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.13008734583854675},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1070713996887207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09242263436317444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803030610084534},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5359976887702942},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.5075022578239441},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.48498889803886414},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47950321435928345},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4478048086166382},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.44134920835494995},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.4330254793167114},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4253208339214325},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42489734292030334},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4046924114227295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37647560238838196},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.13008734583854675},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1070713996887207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09242263436317444},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/esscirc59616.2023.10268686","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/esscirc59616.2023.10268686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESSCIRC 2023- IEEE 49th European Solid State Circuits Conference (ESSCIRC)","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":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322202","display_name":"IC Design Education Center","ror":"https://ror.org/005v57z85"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2921918777","https://openalex.org/W2953235111","https://openalex.org/W3015729306","https://openalex.org/W3135859967","https://openalex.org/W3172967059","https://openalex.org/W3185047697","https://openalex.org/W6753770798","https://openalex.org/W6760306030","https://openalex.org/W6799014415"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2110265185","https://openalex.org/W3146360095","https://openalex.org/W2184011203","https://openalex.org/W2065289416","https://openalex.org/W2017236304","https://openalex.org/W2136854845"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"energy-efficient":[4],"FP4/FP8":[5],"hybrid-precision":[6],"training":[7,24],"processor.":[8],"Through":[9],"hardware-software":[10],"co-optimization,":[11],"the":[12,66],"design":[13],"efficiently":[14],"implements":[15],"all":[16],"general":[17],"matrix":[18],"multiply":[19],"(GEMM)":[20],"operations":[21],"required":[22],"for":[23,72],"using":[25,57],"only":[26],"shift-add":[27],"multiply-accumulate":[28],"(MAC)":[29],"units.":[30],"The":[31,46],"reconfigurable":[32],"processing":[33],"element":[34],"(PE)":[35],"array":[36],"further":[37],"improves":[38],"efficiency":[39,71],"by":[40,78],"significantly":[41],"reducing":[42],"on-chip":[43,47],"memory":[44],"access.":[45],"convolution":[48],"decomposition":[49],"technique":[50],"supports":[51],"a":[52],"wide":[53],"range":[54],"of":[55],"kernels":[56],"simple":[58],"homogeneous":[59],"data":[60],"routing.":[61],"Fabricated":[62],"in":[63],"40nm":[64],"CMOS,":[65],"processor":[67],"achieves":[68],"2.61TFLOPS/W":[69],"real-model":[70],"ResNet-18":[73],"training,":[74],"outperforming":[75],"prior":[76],"art":[77],"59%.":[79]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}