{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:58:26Z","timestamp":1781294306933,"version":"3.54.1"},"reference-count":14,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/lca.2026.3695938","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:35:16Z","timestamp":1779478516000},"page":"210-213","source":"Crossref","is-referenced-by-count":0,"title":["High-Bandwidth Flash for KV Caches: Endurance and Performance Implications"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4243-2111","authenticated-orcid":false,"given":"Kwanhee","family":"Kyung","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0941-0713","authenticated-orcid":false,"given":"Yeon Ji","family":"Moon","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2560-3447","authenticated-orcid":false,"given":"Juhwan","family":"Cho","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1733-1394","authenticated-orcid":false,"given":"Jung Ho","family":"Ahn","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/isscc.2018.8310322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2026.3660969"},{"key":"ref4","first-page":"47561","article-title":"HiFC: High-efficiency flash-based KV cache swapping for scaling LLM inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jeong","year":"2025"},{"key":"ref5","first-page":"18015","article-title":"S$^{3}$3: Increasing GPU utilization during generative inference for higher throughput","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref6","first-page":"155","article-title":"InfiniGen: Efficient generative inference of large language models with dynamic KV cache management","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Lee"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2026.3652916"},{"key":"ref8","article-title":"NAND flash memory","year":"2026"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref11","article-title":"Storage warranty period","year":"2022"},{"key":"ref12","article-title":"High-bandwidth flash","year":"2025"},{"key":"ref13","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref14","first-page":"521","article-title":"ORCA: A distributed serving system for transformer-based generative models","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Yu"},{"key":"ref15","article-title":"The new LLM bottleneck: A systems perspective on latent attention and mixture-of-experts","author":"Yun","year":"2025"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11321093\/11534083.pdf?arnumber=11534083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:41:48Z","timestamp":1781293308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11534083\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":14,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2026.3695938","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}