{"id":"https://openalex.org/W7162100208","doi":"https://doi.org/10.1109/lca.2026.3695938","title":"High-Bandwidth Flash for KV Caches: Endurance and Performance Implications","display_name":"High-Bandwidth Flash for KV Caches: Endurance and Performance Implications","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162100208","doi":"https://doi.org/10.1109/lca.2026.3695938"},"language":null,"primary_location":{"id":"doi:10.1109/lca.2026.3695938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3695938","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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/A5002219153","display_name":"Kwanhee Kyung","orcid":"https://orcid.org/0000-0003-4243-2111"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanhee Kyung","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-4243-2111","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071719407","display_name":"Yeon Ji Moon","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeon Ji Moon","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0005-0941-0713","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136745275","display_name":"Juhwan Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhwan Cho","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0000-2560-3447","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136448364","display_name":"J Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Ho Ahn","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1733-1394","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54568727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"1","first_page":"210","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.7264999747276306,"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":0.7264999747276306,"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":0.04610000178217888,"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/T10138","display_name":"Network Traffic and Congestion Control","score":0.033799998462200165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/flash","display_name":"Flash (photography)","score":0.6136999726295471},{"id":"https://openalex.org/keywords/non-volatile-memory","display_name":"Non-volatile memory","score":0.2583000063896179},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.2581000030040741},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.25440001487731934}],"concepts":[{"id":"https://openalex.org/C2777526259","wikidata":"https://www.wikidata.org/wiki/Q221836","display_name":"Flash (photography)","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.546500027179718},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.40070000290870667},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C177950962","wikidata":"https://www.wikidata.org/wiki/Q10997658","display_name":"Non-volatile memory","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.25130000710487366},{"id":"https://openalex.org/C200769187","wikidata":"https://www.wikidata.org/wiki/Q2360656","display_name":"Arc flash","level":3,"score":0.23989999294281006}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2026.3695938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2026.3695938","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2792589388","https://openalex.org/W4401211704","https://openalex.org/W4409248688","https://openalex.org/W7119941304","https://openalex.org/W7127686171"],"related_works":[],"abstract_inverted_index":{"During":[0],"Large":[1],"Language":[2],"Model":[3],"(LLM)":[4],"inference,":[5],"the":[6,40,45,118,151],"key-value":[7],"(KV)":[8],"cache":[9,120],"is":[10],"a":[11,74,101],"critical":[12],"bottleneck":[13],"in":[14,141],"both":[15,150],"capacity":[16,34,152],"and":[17,108,153],"memory":[18,56,93],"bandwidth":[19,31,80,154],"as":[20,73],"context":[21,126],"lengths":[22],"surge.":[23],"While":[24],"High-Bandwidth":[25,68],"Memory":[26],"(HBM)":[27],"can":[28],"meet":[29],"current":[30],"demands,":[32],"its":[33],"has":[35,71,94],"not":[36],"kept":[37],"pace":[38],"with":[39,84,124,129],"rapidly":[41],"growing":[42],"footprint":[43],"of":[44,156],"KV":[46,49,98,119,136],"cache.":[47],"Consequently,":[48],"caches":[50,99,137],"are":[51],"frequently":[52],"offloaded":[53],"to":[54,82,86,138],"CPU":[55],"for":[57],"higher":[58,89],"capacity,":[59],"yet":[60],"performance":[61],"remains":[62],"constrained":[63],"by":[64],"limited":[65,95],"interconnect":[66],"bandwidth.":[67],"Flash":[69,92],"(HBF)":[70],"emerged":[72],"promising":[75],"alternative,":[76],"offering":[77],"sequential":[78],"read":[79,109],"comparable":[81],"HBM4":[83],"up":[85],"an":[87,145],"order-of-magnitude":[88],"capacity.":[90],"Although":[91],"write":[96],"endurance,":[97],"exhibit":[100],"favorable":[102],"access":[103],"pattern,":[104],"being":[105],"written":[106],"once":[107],"many":[110],"times":[111],"during":[112],"inference.":[113],"Our":[114],"analysis":[115],"demonstrates":[116],"that":[117],"read-to-write":[121],"ratio":[122],"increases":[123],"longer":[125],"lengths,":[127],"particularly":[128],"larger":[130],"output":[131],"sequences.":[132],"This":[133],"characteristic":[134],"enables":[135],"be":[139],"stored":[140],"HBF":[142],"while":[143],"maintaining":[144],"acceptable":[146],"device":[147],"lifetime,":[148],"addressing":[149],"challenges":[155],"contemporary":[157],"LLM":[158],"systems.":[159]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-05-23T00:00:00"}
