{"id":"https://openalex.org/W4376607430","doi":"https://doi.org/10.1109/jssc.2023.3269148","title":"A 28-nm 8-bit Floating-Point Tensor Core-Based Programmable CNN Training Processor With Dynamic Structured Sparsity","display_name":"A 28-nm 8-bit Floating-Point Tensor Core-Based Programmable CNN Training Processor With Dynamic Structured Sparsity","publication_year":2023,"publication_date":"2023-05-15","ids":{"openalex":"https://openalex.org/W4376607430","doi":"https://doi.org/10.1109/jssc.2023.3269148"},"language":"en","primary_location":{"id":"doi:10.1109/jssc.2023.3269148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2023.3269148","pdf_url":null,"source":{"id":"https://openalex.org/S83637746","display_name":"IEEE Journal of Solid-State Circuits","issn_l":"0018-9200","issn":["0018-9200","1558-173X"],"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 Journal of Solid-State Circuits","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/A5062825809","display_name":"Shreyas Kolala Venkataramanaiah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Kolala Venkataramanaiah","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","Apple, Cupertino, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063343008","display_name":"Jian Meng","orcid":"https://orcid.org/0000-0002-7703-5020"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Meng","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-7703-5020","affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066342752","display_name":"Han-Sok Suh","orcid":"https://orcid.org/0000-0002-4466-4824"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han-Sok Suh","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-4466-4824","affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057187008","display_name":"Injune Yeo","orcid":"https://orcid.org/0000-0002-4596-6170"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Injune Yeo","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","Department of Electrical Engineering, Chosun University, Gwangju, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4596-6170","affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Department of Electrical Engineering, Chosun University, Gwangju, South Korea","institution_ids":["https://openalex.org/I152238500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110952916","display_name":"Jyotishman Saikia","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyotishman Saikia","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008325583","display_name":"Sai Kiran Cherupally","orcid":"https://orcid.org/0000-0002-6305-1935"},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Kiran Cherupally","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","TI Kilby Labs, Dallas, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-6305-1935","affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"TI Kilby Labs, Dallas, TX, USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444205","display_name":"Yichi Zhang","orcid":"https://orcid.org/0009-0005-1156-5538"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"],"raw_orcid":"https://orcid.org/0009-0005-1156-5538","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037210004","display_name":"Zhiru Zhang","orcid":"https://orcid.org/0000-0002-0778-0308"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiru Zhang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-0778-0308","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007690955","display_name":"Jae-sun Seo","orcid":"https://orcid.org/0000-0002-4551-7789"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jae-Sun Seo","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-4551-7789","affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.36,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80355975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"58","issue":"7","first_page":"1885","last_page":"1897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9972000122070312,"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/T12303","display_name":"Tensor decomposition and applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8892861604690552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8058304786682129},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.7087653875350952},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6697807312011719},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6601858735084534},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6197207570075989},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4187774658203125},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41395899653434753},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.358229398727417},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35664820671081543},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3342014253139496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3074268698692322},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27126508951187134}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8892861604690552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058304786682129},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.7087653875350952},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6697807312011719},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6601858735084534},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6197207570075989},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4187774658203125},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41395899653434753},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.358229398727417},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35664820671081543},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3342014253139496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3074268698692322},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27126508951187134},{"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/jssc.2023.3269148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2023.3269148","pdf_url":null,"source":{"id":"https://openalex.org/S83637746","display_name":"IEEE Journal of Solid-State Circuits","issn_l":"0018-9200","issn":["0018-9200","1558-173X"],"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 Journal of Solid-State Circuits","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1513466694","display_name":"CAREER: Designing Ultra-Energy-Efficient Intelligent Hardware with On-Chip Learning, Attention, and Inference","funder_award_id":"1652866","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2331143823","https://openalex.org/W2523246573","https://openalex.org/W2806990599","https://openalex.org/W2894740066","https://openalex.org/W2896006880","https://openalex.org/W2898985762","https://openalex.org/W2921918777","https://openalex.org/W2953235111","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2978610144","https://openalex.org/W2980812807","https://openalex.org/W2990765879","https://openalex.org/W2990865680","https://openalex.org/W3005680577","https://openalex.org/W3035524453","https://openalex.org/W3048705738","https://openalex.org/W3048842964","https://openalex.org/W3091592563","https://openalex.org/W3092345941","https://openalex.org/W3107401339","https://openalex.org/W3109309915","https://openalex.org/W3135859967","https://openalex.org/W3137841151","https://openalex.org/W3157114665","https://openalex.org/W3172967059","https://openalex.org/W3185047697","https://openalex.org/W3187235458","https://openalex.org/W3208821873","https://openalex.org/W3213238321","https://openalex.org/W4205806473","https://openalex.org/W4214700987","https://openalex.org/W4226353746","https://openalex.org/W4286571873","https://openalex.org/W4287906222","https://openalex.org/W4292874289","https://openalex.org/W4308089906","https://openalex.org/W4312235774","https://openalex.org/W4313117725","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6727249380","https://openalex.org/W6751913510","https://openalex.org/W6753770798","https://openalex.org/W6755166560","https://openalex.org/W6755526309","https://openalex.org/W6768742326","https://openalex.org/W6770166933","https://openalex.org/W6772013979","https://openalex.org/W6774314701","https://openalex.org/W6792046235","https://openalex.org/W6796875897","https://openalex.org/W6798034730","https://openalex.org/W6846382154"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W3100944160","https://openalex.org/W2560894929","https://openalex.org/W2156524298","https://openalex.org/W2106942255","https://openalex.org/W4292794827","https://openalex.org/W4224939635"],"abstract_inverted_index":{"Training":[0],"deep/convolutional":[1],"neural":[2],"networks":[3],"(DNNs/CNNs)":[4],"requires":[5],"a":[6,99],"large":[7,119],"amount":[8],"of":[9,65],"memory":[10],"and":[11,17,60,87,111,131,140],"iterative":[12],"computation,":[13],"which":[14,39],"necessitates":[15],"speedup":[16,135],"energy":[18,127],"reduction,":[19],"especially":[20],"for":[21,73,137],"edge":[22],"devices":[23],"with":[24],"resource/energy":[25],"constraints.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"present":[31],"an":[32],"8-bit":[33],"floating-point":[34,122],"(FP8)":[35],"training":[36,67,112,133,142],"the":[37,66,93],"processor":[38],"implements:":[40],"1)":[41],"highly":[42],"parallel":[43],"tensor":[44],"cores":[45],"(fused":[46],"multiply\u2013add":[47],"trees)":[48],"that":[49],"maintain":[50],"high":[51],"utilization":[52],"throughout":[53],"forward":[54],"propagation":[55,58],"(FP),":[56],"backward":[57],"(BP),":[59],"weight":[61,80],"update":[62],"(WU)":[63],"phases":[64],"process;":[68],"2)":[69],"hardware-efficient":[70],"channel":[71],"gating":[72],"dynamic":[74,79],"output":[75],"activation":[76],"sparsity;":[77],"3)":[78],"sparsity":[81],"(WS)":[82],"based":[83,91],"on":[84,92],"group":[85],"Lasso;":[86],"4)":[88],"gradient":[89],"skipping":[90],"FP":[94],"prediction":[95],"error.":[96],"We":[97],"develop":[98],"custom":[100],"instruction":[101],"set":[102],"architecture":[103],"(ISA)":[104],"to":[105],"flexibly":[106],"support":[107],"different":[108],"CNN":[109],"topologies":[110],"parameters.":[113],"The":[114],"28-nm":[115],"prototype":[116],"chip":[117],"demonstrates":[118],"improvements":[120],"in":[121],"operations":[123],"(FLOPs)":[124],"reduction":[125],"(7.3\u00d7),":[126],"efficiency":[128],"(16.4":[129],"TFLOPS/W),":[130],"overall":[132],"latency":[134],"(4.7\u00d7),":[136],"both":[138],"supervised":[139],"self-supervised":[141],"tasks.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}