{"id":"https://openalex.org/W4416078391","doi":"https://doi.org/10.1109/jssc.2025.3624011","title":"A Multicore Programmable Variable-Precision Near-Memory Accelerator for CNN and Transformer Models","display_name":"A Multicore Programmable Variable-Precision Near-Memory Accelerator for CNN and Transformer Models","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416078391","doi":"https://doi.org/10.1109/jssc.2025.3624011"},"language":null,"primary_location":{"id":"doi:10.1109/jssc.2025.3624011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2025.3624011","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/A5110776169","display_name":"Yang Yi-ming","orcid":"https://orcid.org/0000-0002-2369-4231"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Yang","raw_affiliation_strings":["School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2369-4231","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076598644","display_name":"Yiyang Yuan","orcid":"https://orcid.org/0000-0002-8261-1707"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyang Yuan","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8261-1707","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639249","display_name":"Xinghua Wang","orcid":"https://orcid.org/0000-0003-1825-7595"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghua Wang","raw_affiliation_strings":["School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1825-7595","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697542","display_name":"Xiaoran Li","orcid":"https://orcid.org/0000-0002-2609-3554"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoran Li","raw_affiliation_strings":["School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2609-3554","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101519326","display_name":"Hao Wu","orcid":"https://orcid.org/0009-0003-7447-7004"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-7447-7004","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006072144","display_name":"Qihao Liu","orcid":"https://orcid.org/0009-0003-0425-7911"},"institutions":[{"id":"https://openalex.org/I4210135812","display_name":"Sinochem Group (China)","ror":"https://ror.org/03x8vck69","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210135812"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihao Liu","raw_affiliation_strings":["Shandong SinoChip Semiconductors Company Ltd., Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-0425-7911","affiliations":[{"raw_affiliation_string":"Shandong SinoChip Semiconductors Company Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210135812"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103163439","display_name":"Weiye Tang","orcid":"https://orcid.org/0009-0007-2696-5117"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiye Tang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2696-5117","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005225432","display_name":"Xiangqu Fu","orcid":"https://orcid.org/0000-0001-7288-9302"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangqu Fu","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7288-9302","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401317","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0003-2316-0392"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2316-0392","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2545014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"61","issue":"6","first_page":"2725","last_page":"2737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.79339998960495,"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":0.79339998960495,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.05480000004172325,"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":0.020999999716877937,"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/transformer","display_name":"Transformer","score":0.6689000129699707},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5673999786376953},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.460999995470047},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4489000141620636},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.3930000066757202},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.38839998841285706},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.3628000020980835},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631000280380249},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6689000129699707},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4471000134944916},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37139999866485596},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.3411000072956085},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jssc.2025.3624011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2025.3624011","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/G2076236949","display_name":null,"funder_award_id":"92464201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3722458669","display_name":null,"funder_award_id":"U2341218","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8556838293","display_name":null,"funder_award_id":"62101038","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2982479999","https://openalex.org/W2990591126","https://openalex.org/W3016123840","https://openalex.org/W3134526034","https://openalex.org/W3195887756","https://openalex.org/W4205984092","https://openalex.org/W4221086307","https://openalex.org/W4221089937","https://openalex.org/W4280496502","https://openalex.org/W4286571779","https://openalex.org/W4286571878","https://openalex.org/W4312847929","https://openalex.org/W4312933868","https://openalex.org/W4312965666","https://openalex.org/W4313639541","https://openalex.org/W4313839325","https://openalex.org/W4319430196","https://openalex.org/W4360605730","https://openalex.org/W4360606196","https://openalex.org/W4360606423","https://openalex.org/W4360606782","https://openalex.org/W4364860236","https://openalex.org/W4385245566","https://openalex.org/W4385732107","https://openalex.org/W4386108348","https://openalex.org/W4390415044","https://openalex.org/W4392746193"],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,10,125],"network":[2,11,126],"(CNN)":[3],"and":[4,17,49,74,121,140,160,168,185],"transformer":[5,166,186],"are":[6],"the":[7,64,113,117,123],"most":[8],"popular":[9],"models":[12,31,42,60],"in":[13,32,155],"computer":[14],"vision":[15],"(CV)":[16],"natural":[18],"language":[19],"processing":[20],"(NLP).":[21],"It":[22],"is":[23,153],"quite":[24],"common":[25],"to":[26,55,84,95,105,112,115,136],"use":[27,100,129],"both":[28,57,183],"these":[29,40],"two":[30,41],"multimodal":[33],"scenarios,":[34],"such":[35],"as":[36],"text-to-image":[37],"generation.":[38],"However,":[39],"have":[43],"very":[44],"different":[45],"memory":[46,81,114,118],"mappings,":[47],"dataflows":[48],"mathematical":[50],"operators,":[51],"making":[52],"it":[53],"difficult":[54],"accelerate":[56],"types":[58],"of":[59],"simultaneously.":[61],"To":[62,91],"address":[63],"forementioned":[65],"challenges,":[66],"we":[67,99],"propose":[68],"a":[69,130,156],"multi-core":[70],"programmable":[71],"near-memory":[72,101],"accelerator":[73],"introduce":[75],"an":[76],"arbitration-free":[77],"multi-port":[78],"static":[79],"random-access":[80],"(SRAM)":[82],"array":[83],"improve":[85],"storage":[86],"utilization":[87],"while":[88,180],"maintaining":[89],"flexibility.":[90],"achieve":[92],"performance":[93],"comparable":[94],"computing-in-memory":[96],"(CIM)":[97],"designs,":[98,179],"variable-precision":[102],"multiplier-accumulators":[103],"(NVMACs)":[104],"perform":[106],"multiply-accumulate":[107],"(MAC)":[108],"operations":[109,147],"tightly":[110],"close":[111],"maximize":[116],"access":[119],"throughput":[120],"support":[122,137],"mixed-precision":[124],"inference.":[127],"We":[128],"fine-grained":[131],"instruction":[132],"set":[133],"architecture":[134],"(ISA)":[135],"software":[138],"sparsity":[139],"reduce":[141],"overhead":[142],"caused":[143],"by":[144],"coarse-grained":[145],"non-MAC":[146],"with":[148,176],"low":[149],"utilization.":[150],"A":[151],"chip":[152],"fabricated":[154],"28":[157],"nm":[158],"process":[159],"achieves":[161],"6.3-to-101.4TOPS/W":[162],"energy":[163],"efficiency":[164],"for":[165,171],"model":[167],"7.3-to-194.6":[169],"TOPS/W":[170],"CNN":[172,184],"model,$1.2\\times":[173],"$to$4.2\\times":[174],"$compared":[175],"other":[177],"state-of-the-art":[178],"efficiently":[181],"supporting":[182],"overloads.":[187]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-11-10T00:00:00"}