{"id":"https://openalex.org/W4406137899","doi":"https://doi.org/10.1109/jssc.2024.3522304","title":"A Computing-in-Memory Engine Supporting One-Shot Floating-Point NN Inference and On-Device Fine-Tuning for Edge AI","display_name":"A Computing-in-Memory Engine Supporting One-Shot Floating-Point NN Inference and On-Device Fine-Tuning for Edge AI","publication_year":2025,"publication_date":"2025-01-07","ids":{"openalex":"https://openalex.org/W4406137899","doi":"https://doi.org/10.1109/jssc.2024.3522304"},"language":"en","primary_location":{"id":"doi:10.1109/jssc.2024.3522304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2024.3522304","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/A5032812622","display_name":"Haikang Diao","orcid":"https://orcid.org/0000-0001-7379-4284"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haikang Diao","raw_affiliation_strings":["Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045313745","display_name":"Haoyang Luo","orcid":"https://orcid.org/0009-0003-3342-7086"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Luo","raw_affiliation_strings":["Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011379172","display_name":"Jiahao Song","orcid":"https://orcid.org/0000-0001-6296-1905"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Song","raw_affiliation_strings":["Institute for Neural Computation (INC), University of California at San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Neural Computation (INC), University of California at San Diego, La Jolla, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101353993","display_name":"Bocheng Xu","orcid":"https://orcid.org/0009-0007-6539-7896"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bocheng Xu","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002760019","display_name":"Runsheng Wang","orcid":"https://orcid.org/0000-0002-7514-0767"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runsheng Wang","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002438548","display_name":"Yuan Wang","orcid":"https://orcid.org/0000-0002-4951-4286"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Wang","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066653944","display_name":"Xiyuan Tang","orcid":"https://orcid.org/0000-0003-2181-9042"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyuan Tang","raw_affiliation_strings":["Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5032812622"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":1.4935,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79748736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"60","issue":"9","first_page":"3403","last_page":"3415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9983999729156494,"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":0.9980999827384949,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9937999844551086,"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/floating-point","display_name":"Floating point","score":0.6755203008651733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6521585583686829},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6156169772148132},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5894593000411987},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5118054747581482},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.5102238655090332},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49222221970558167},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4238664507865906},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.41920650005340576},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.413899302482605},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39314335584640503},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.39193448424339294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22082287073135376},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13170728087425232},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11685314774513245}],"concepts":[{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.6755203008651733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6521585583686829},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6156169772148132},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5894593000411987},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5118054747581482},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.5102238655090332},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49222221970558167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4238664507865906},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41920650005340576},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.413899302482605},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39314335584640503},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.39193448424339294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22082287073135376},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13170728087425232},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11685314774513245},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jssc.2024.3522304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2024.3522304","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":[],"awards":[{"id":"https://openalex.org/G5760870415","display_name":null,"funder_award_id":"62304009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6847781164","display_name":null,"funder_award_id":"B18001","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2591601611","https://openalex.org/W2618530766","https://openalex.org/W2920326572","https://openalex.org/W2922487710","https://openalex.org/W2963037989","https://openalex.org/W3034344052","https://openalex.org/W3134526034","https://openalex.org/W3175873985","https://openalex.org/W3208788005","https://openalex.org/W4220922172","https://openalex.org/W4220990849","https://openalex.org/W4221038786","https://openalex.org/W4221101426","https://openalex.org/W4224916569","https://openalex.org/W4360605483","https://openalex.org/W4360605703","https://openalex.org/W4360605969","https://openalex.org/W4360606939","https://openalex.org/W4360607288","https://openalex.org/W4385245566","https://openalex.org/W4389799305","https://openalex.org/W4396918237","https://openalex.org/W4396918368","https://openalex.org/W4396918650","https://openalex.org/W4401328386"],"related_works":["https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W2760721665","https://openalex.org/W2107954672","https://openalex.org/W330130819","https://openalex.org/W2288610023","https://openalex.org/W2112044895","https://openalex.org/W3121416282","https://openalex.org/W4280610722","https://openalex.org/W3185228140"],"abstract_inverted_index":{"With":[0],"the":[1,7,47,64,90,110,115,120,139,145,167],"rapid":[2],"advancement":[3],"of":[4,9,68,92,114,196,203],"edge":[5,12],"AI,":[6],"complexity":[8],"tasks":[10],"on":[11,41],"devices":[13],"is":[14,99,133,153,181],"continually":[15],"increasing,":[16],"demanding":[17],"better":[18],"efficiency":[19,65,195],"and":[20,59,66,85,160,199,223],"precision":[21],"from":[22],"AI":[23],"accelerators.":[24],"Pre-aligned":[25],"floating-point":[26,42],"computing-in-memory":[27,77],"(FP":[28],"CIM)":[29],"has":[30],"been":[31],"proposed":[32,100,154],"to":[33,101,118,124,136,155,183],"achieve":[34],"high-precision":[35],"neural":[36],"network":[37],"(NN)":[38],"computations":[39],"based":[40],"(FP)":[43],"data":[44],"precision.":[45],"However,":[46],"complex":[48],"digital":[49],"circuitry":[50],"required":[51],"for":[52,80],"integer":[53,121],"(INT)":[54],"mantissa":[55,122,162],"multiply-accumulate":[56],"(MAC)":[57],"computation":[58,141],"exponent":[60,158],"alignment":[61],"severely":[62],"limits":[63],"throughput":[67,91],"FP":[69,82,93,103],"CIM.":[70],"This":[71],"work":[72],"proposes":[73],"an":[74,149,193],"energy-and":[75],"area-efficient":[76],"(CIM)":[78],"engine":[79],"one-shot":[81,96],"NN":[83,112,117],"inference":[84,168],"on-device":[86,177],"fine-tuning.":[87],"To":[88,143,165],"improve":[89],"CIM,":[94],"a":[95,175,200,215],"compute":[97],"scheme":[98],"perform":[102],"operation":[104],"within":[105],"one":[106],"cycle.":[107],"It":[108],"adopts":[109],"multiply-less":[111],"instead":[113],"multiply-based":[116],"simplify":[119,144,161],"MAC":[123],"minimum":[125,131],"selection.":[126],"A":[127],"customized":[128],"8-bit":[129],"parallel":[130,140],"selector":[132],"also":[134],"designed":[135,182],"further":[137],"reduce":[138],"cost.":[142],"FP/INT":[146],"conversion":[147],"process,":[148],"input\u2013weight":[150],"co-alignment":[151],"workflow":[152],"eliminate":[156],"maximum":[157],"selection":[159],"shifting":[163],"logic.":[164],"minimize":[166],"accuracy":[169],"loss":[170],"caused":[171],"by":[172],"environmental":[173],"changes,":[174],"lightweight":[176],"fine-tuning":[178],"core":[179],"(ODFC)":[180],"support":[184],"online":[185],"weight":[186],"updates.":[187],"The":[188],"28-nm":[189],"fabricated":[190],"chip":[191],"achieves":[192],"energy":[194],"128":[197],"TFLOPS/W":[198],"computational":[201],"density":[202],"7.02":[204],"TFLOPS/mm":[205],"<inline-formula":[206,217,225],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[207,218,226],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[208,219,227],"<tex-math":[209,220,228],"notation=\"LaTeX\">$^2$</tex-math>":[210],"</inline-formula>":[211,222,230],"at":[212],"BF16,":[213],"representing":[214],"4.1":[216],"notation=\"LaTeX\">$\\times$</tex-math>":[221,229],"3.4":[224],"improvement":[231],"over":[232],"previous":[233],"state-of-the-art":[234],"works,":[235],"respectively.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}