{"id":"https://openalex.org/W7128428047","doi":"https://doi.org/10.1109/tvlsi.2026.3657777","title":"E-Flash: Energy-Efficient LLM Mapping on NAND Flash-Based In-Storage Inference Computing","display_name":"E-Flash: Energy-Efficient LLM Mapping on NAND Flash-Based In-Storage Inference Computing","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128428047","doi":"https://doi.org/10.1109/tvlsi.2026.3657777"},"language":null,"primary_location":{"id":"doi:10.1109/tvlsi.2026.3657777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2026.3657777","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Transactions on Very Large Scale Integration (VLSI) Systems","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/A5119620347","display_name":"Gisan Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gisan Ji","raw_affiliation_strings":["Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-0061-433X","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067102582","display_name":"Sanghun Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghun Shin","raw_affiliation_strings":["Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-7708-3737","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125467042","display_name":"Jangho Baik","orcid":null},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jangho Baik","raw_affiliation_strings":["Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-5649-3889","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125450964","display_name":"Wonbo Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonbo Shim","raw_affiliation_strings":["Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9669-7310","affiliations":[{"raw_affiliation_string":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079596428","display_name":"Sungju Ryu","orcid":"https://orcid.org/0000-0002-0254-391X"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungju Ryu","raw_affiliation_strings":["Department of System Semiconductor Engineering, Sogang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0254-391X","affiliations":[{"raw_affiliation_string":"Department of System Semiconductor Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.11605411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"4","first_page":"1124","last_page":"1133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.7730000019073486,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.7730000019073486,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.12240000069141388,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.0284000001847744,"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/nand-gate","display_name":"NAND gate","score":0.5819000005722046},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5795999765396118},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4113999903202057},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3871999979019165},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37299999594688416},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3652999997138977},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3589000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519999742507935},{"id":"https://openalex.org/C124296912","wikidata":"https://www.wikidata.org/wiki/Q575178","display_name":"NAND gate","level":3,"score":0.5819000005722046},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C2777526259","wikidata":"https://www.wikidata.org/wiki/Q221836","display_name":"Flash (photography)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C64142963","wikidata":"https://www.wikidata.org/wiki/Q1153902","display_name":"Phase-change memory","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2026.3657777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2026.3657777","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Transactions on Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9076977968215942,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G5097109023","display_name":null,"funder_award_id":"RS-2024-00439520","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"have":[5,54],"achieved":[6],"remarkable":[7],"success":[8],"across":[9],"a":[10,50,84,96,118],"wide":[11],"range":[12],"of":[13,26],"applications":[14],"such":[15,49],"as":[16],"image":[17],"and":[18,29,38,137,145],"text":[19],"generation":[20],"tasks.":[21],"However,":[22],"The":[23],"continuous":[24],"growth":[25],"model":[27,76],"size":[28],"memory":[30,39],"demands":[31],"imposes":[32],"significant":[33,71],"pressure":[34],"on":[35,134],"energy":[36,66,124],"consumption":[37,67],"bandwidth,":[40],"especially":[41],"during":[42],"weight":[43,92,104],"access":[44],"operations.":[45],"To":[46],"deal":[47],"with":[48,152],"challenge,":[51],"prior":[52],"studies":[53],"investigated":[55],"NAND":[56,86],"flash-based":[57,87],"processing-in-memory":[58],"(PIM)":[59],"architectures,":[60],"but":[61],"it":[62],"still":[63],"experiences":[64],"large":[65],"due":[68],"to":[69,106,143],"the":[70,74],"increase":[72],"in":[73,110,148],"recent":[75],"sizes.":[77],"In":[78,116],"this":[79],"work,":[80],"we":[81],"present":[82],"E-Flash,":[83],"digital":[85],"architecture":[88],"for":[89],"energy-efficient":[90],"DNN":[91],"access.":[93],"E-Flash":[94],"introduces":[95],"novel":[97],"state-switching":[98],"algorithm":[99],"that":[100],"reallocates":[101],"frequently":[102],"occurring":[103],"patterns":[105,129],"low-power":[107],"cell":[108,112],"states":[109],"triple-level":[111],"(TLC)":[113],"flash":[114],"memory.":[115],"addition,":[117],"cell-first":[119],"allocation":[120],"scheme":[121],"further":[122],"amplifies":[123],"savings":[125],"by":[126],"aligning":[127],"bit":[128],"within":[130],"cells.":[131],"Evaluation":[132],"results":[133],"quantized":[135],"BERT":[136],"Llama":[138],"2":[139],"models":[140],"demonstrate":[141],"up":[142],"37.73%":[144],"16.74%":[146],"reduction":[147],"read":[149],"energy,":[150],"respectively,":[151],"negligible":[153],"hardware":[154],"overhead.":[155]},"counts_by_year":[],"updated_date":"2026-05-12T06:07:45.972803","created_date":"2026-02-10T00:00:00"}