{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T05:01:19Z","timestamp":1780117279368,"version":"3.54.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation through Korean Government","doi-asserted-by":"publisher","award":["RS-2024-00439520"],"award-info":[{"award-number":["RS-2024-00439520"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation through Korean Government Solution for Accelerating Ultra-Large AI Models)","award":["RS-2025-02263669"],"award-info":[{"award-number":["RS-2025-02263669"]}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation -Information Technology Research Center Korean Government","award":["IITP-2026-RS-2023-00260091"],"award-info":[{"award-number":["IITP-2026-RS-2023-00260091"]}]},{"DOI":"10.13039\/501100003836","name":"EDA tool through the IC Design Education Center (IDEC), South Korea.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003836","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tvlsi.2026.3657777","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:11:11Z","timestamp":1770671471000},"page":"1124-1133","source":"Crossref","is-referenced-by-count":0,"title":["E-Flash: Energy-Efficient LLM Mapping on NAND Flash-Based In-Storage Inference Computing"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0061-433X","authenticated-orcid":false,"given":"Gisan","family":"Ji","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7708-3737","authenticated-orcid":false,"given":"Sanghun","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5649-3889","authenticated-orcid":false,"given":"Jangho","family":"Baik","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9669-7310","authenticated-orcid":false,"given":"Wonbo","family":"Shim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0254-391X","authenticated-orcid":false,"given":"Sungju","family":"Ryu","sequence":"additional","affiliation":[{"name":"Department of System Semiconductor Engineering, Sogang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED65674.2025.11261788"},{"issue":"140","key":"ref2","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Colin","year":"2020","journal-title":"JMLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref5","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2023","journal-title":"arXiv:1910.10683"},{"key":"ref6","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019","journal-title":"arXiv:1909.08053"},{"key":"ref7","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref8","article-title":"Using DeepSpeed and megatron to train megatron-turing NLG 530B, a large-scale generative language model","author":"Smith","year":"2022","journal-title":"arXiv:2201.11990"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.12092"},{"key":"ref10","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref11","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref12","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref13","article-title":"Llama2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070946"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992908"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s13391-011-0901-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/isscc.2016.7417945"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2017.2731813"},{"key":"ref19","first-page":"236","article-title":"13.3 a 280-layer 1Tb 4b\/cell 3D-NAND flash memory with a 28.5 Gb\/mm2 areal density and a 3.2 GB\/s high-speed IO rate","volume-title":"IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers","author":"Jung"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LED.2013.2288991"},{"key":"ref21","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sanh"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2137"},{"key":"ref23","article-title":"All you need is a good init","author":"Mishkin","year":"2015","journal-title":"arXiv:1511.06422"},{"key":"ref24","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref25","volume-title":"Accurate and efficient spiking neural networks with 3-D nand flash synaptic array","author":"Song","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2017.05.019"},{"key":"ref28","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref29","article-title":"RPTQ: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023","journal-title":"arXiv:2304.01089"},{"key":"ref30","first-page":"338","article-title":"A flash memory controller for 15 \u03bcs ultra-low-latency SSD using high-speed 3D NAND flash with 3 \u03bcs read time","volume-title":"IEEE Int. Solid-State Circuits Conf. (ISSCC) Dig. Tech. Papers","author":"Cheong"},{"key":"ref31","article-title":"Gemma: Open models based on Gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv:2403.08295"},{"key":"ref32","volume-title":"GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model","author":"Wang","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/92\/11514136\/11380195.pdf?arnumber=11380195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T04:16:29Z","timestamp":1780114589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11380195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":33,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2026.3657777","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"value":"1063-8210","type":"print"},{"value":"1557-9999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}