{"id":"https://openalex.org/W7134915761","doi":"https://doi.org/10.1109/asp-dac66049.2026.11420572","title":"M3DKV: Monolithic 3D Gain Cell Memory Enabled Efficient KV Cache & Processing","display_name":"M3DKV: Monolithic 3D Gain Cell Memory Enabled Efficient KV Cache & Processing","publication_year":2026,"publication_date":"2026-01-19","ids":{"openalex":"https://openalex.org/W7134915761","doi":"https://doi.org/10.1109/asp-dac66049.2026.11420572"},"language":null,"primary_location":{"id":"doi:10.1109/asp-dac66049.2026.11420572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asp-dac66049.2026.11420572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","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/A5101517293","display_name":"Jiaqi Yang","orcid":"https://orcid.org/0000-0001-7715-7864"},"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":"Jiaqi Yang","raw_affiliation_strings":["Institute for Artificial Intelligence Peking University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence Peking University,Beijing,China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014139819","display_name":"Yanbo Su","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbo Su","raw_affiliation_strings":["Tsinghua University,School of Integrated Circuits, Beijing Advanced Innovation Center for Integrated Circuits, BNRist,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Integrated Circuits, Beijing Advanced Innovation Center for Integrated Circuits, BNRist,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105267000","display_name":"Y. Fu","orcid":"https://orcid.org/0000-0002-7370-7395"},"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":"Yihan Fu","raw_affiliation_strings":["Institute for Artificial Intelligence Peking University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence Peking University,Beijing,China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianshi Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianshi Tang","raw_affiliation_strings":["Tsinghua University,School of Integrated Circuits, Beijing Advanced Innovation Center for Integrated Circuits, BNRist,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Integrated Circuits, Beijing Advanced Innovation Center for Integrated Circuits, BNRist,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128703311","display_name":"Bonan Yan","orcid":null},"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":"Bonan Yan","raw_affiliation_strings":["Institute for Artificial Intelligence Peking University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence Peking University,Beijing,China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101517293"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53414761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11315","display_name":"Phase-change materials and chalcogenides","score":0.17589999735355377,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11315","display_name":"Phase-change materials and chalcogenides","score":0.17589999735355377,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10472","display_name":"Semiconductor materials and devices","score":0.13840000331401825,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.09600000083446503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.3968999981880188},{"id":"https://openalex.org/keywords/memory-cell","display_name":"Memory cell","score":0.3122999966144562},{"id":"https://openalex.org/keywords/integrated-circuit","display_name":"Integrated circuit","score":0.29789999127388},{"id":"https://openalex.org/keywords/non-volatile-memory","display_name":"Non-volatile memory","score":0.2937000095844269},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.2890999913215637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.492000013589859},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.3668000102043152},{"id":"https://openalex.org/C49040817","wikidata":"https://www.wikidata.org/wiki/Q193091","display_name":"Optoelectronics","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C2776638159","wikidata":"https://www.wikidata.org/wiki/Q18343761","display_name":"Memory cell","level":4,"score":0.3122999966144562},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C530198007","wikidata":"https://www.wikidata.org/wiki/Q80831","display_name":"Integrated circuit","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C177950962","wikidata":"https://www.wikidata.org/wiki/Q10997658","display_name":"Non-volatile memory","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2711000144481659},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asp-dac66049.2026.11420572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asp-dac66049.2026.11420572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","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":0.7938771843910217}],"awards":[],"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":25,"referenced_works":["https://openalex.org/W2082055514","https://openalex.org/W2116567461","https://openalex.org/W2754347129","https://openalex.org/W2979826702","https://openalex.org/W2985830373","https://openalex.org/W3017024317","https://openalex.org/W3085139254","https://openalex.org/W3189877953","https://openalex.org/W3214365409","https://openalex.org/W4225501806","https://openalex.org/W4226194411","https://openalex.org/W4280496502","https://openalex.org/W4312847929","https://openalex.org/W4386764212","https://openalex.org/W4390587691","https://openalex.org/W4391594512","https://openalex.org/W4392780160","https://openalex.org/W4401568333","https://openalex.org/W4404133532","https://openalex.org/W4405928733","https://openalex.org/W4409474770","https://openalex.org/W4411403450","https://openalex.org/W4411485931","https://openalex.org/W4411486323","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"generative":[1],"large":[2],"language":[3,9],"models":[4],"(LLMs)":[5],"have":[6],"revolutionized":[7],"natural":[8],"processing,":[10],"yet":[11],"their":[12],"quadratic":[13],"growth":[14],"in":[15,18,117],"computational":[16],"complexity":[17],"context":[19],"length":[20],"creates":[21],"severe":[22],"inference":[23],"bottlenecks.":[24],"While":[25],"LLM":[26],"keyvalue":[27],"cache":[28,39,65],"(KV":[29],"cache)":[30],"enhances":[31],"decoding":[32,119],"efficiency,":[33],"prolonged":[34],"contexts":[35],"infer":[36],"frequent":[37],"KV":[38,69],"reloads":[40],"that":[41],"exacerbate":[42],"memory":[43],"bandwidth":[44,106],"constraints.":[45],"To":[46],"address":[47],"this":[48],"hardware":[49],"challenge,":[50],"we":[51],"propose":[52],"M3DKV-a":[53],"monolithic":[54],"three-dimensional":[55],"(3D)":[56],"gain":[57],"cell":[58],"near-memory":[59],"computing":[60],"accelerator":[61],"featuring":[62],"back-end-of-line":[63],"(BEOL)":[64],"layers":[66],"for":[67,80],"in-situ":[68],"matrix":[70],"buffering":[71],"and":[72,74,92,121],"computation":[73,94],"a":[75],"front-end-of-line":[76],"(FEOL)":[77],"base":[78],"layer":[79],"full":[81],"selfattention":[82],"operations.":[83],"Through":[84],"optimized":[85],"3D":[86],"data":[87],"organization,":[88],"inter-layer":[89],"dataflow":[90],"management,":[91],"intelligent":[93],"scheduling,":[95],"our":[96],"design":[97],"achieves":[98],"$0.29":[99],"\\mathrm{~TB}":[100],"/":[101,111],"\\mathrm{s}":[102],"/$":[103],"core":[104],"on-die":[105],"while":[107],"demonstrating":[108],"$97.03":[109],"\\times":[110],"268.01":[112],"\\times$":[113,124],"speedup":[114],"over":[115],"GPU/CPU":[116],"the":[118],"stage":[120],"$1.72":[122],"\\times-262.16":[123],"better":[125],"area":[126],"efficiency":[127],"per":[128],"parameter":[129],"versus":[130],"state-of-the-art":[131],"accelerators.":[132]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-12T00:00:00"}