{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:13:14Z","timestamp":1758089594182,"version":"3.44.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11133230","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["AttenPIM: Accelerating LLM Attention with Dual-mode GEMV in Processing-in-Memory"],"prefix":"10.1109","author":[{"given":"Liyan","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Micro\/Nano Electronics,Shanghai,China"}]},{"given":"Dongxu","family":"Lyu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Micro\/Nano Electronics,Shanghai,China"}]},{"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Micro\/Nano Electronics,Shanghai,China"}]},{"given":"Jianfei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Micro\/Nano Electronics,Shanghai,China"}]},{"given":"Qin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Micro\/Nano Electronics,Shanghai,China"}]},{"given":"Zhigang","family":"Mao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Micro\/Nano Electronics,Shanghai,China"}]},{"given":"Naifeng","family":"Jing","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Micro\/Nano Electronics,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2404.14294"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46783.2024.10631397"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2023.3305386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10664793"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254717"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895629"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783753"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"ref13","first-page":"815","article-title":"Aespa: Asynchronous execution scheme to exploit bank-level parallelism of processing-in-memory","volume-title":"Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Kal"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9567191"},{"key":"ref15","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"JEDEC","key":"ref16","article-title":"High Bandwidth Memory DRAM (HBM3)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00029"},{"key":"ref18","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint arXiv:2005.14165"},{"key":"ref19","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"article-title":"Stanford alpaca: An instruction-following llama model","year":"2023","author":"Taori","key":"ref20"},{"journal-title":"ShareGPT Team","article-title":"ShareGPT","year":"2023","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2973991"},{"key":"ref24","first-page":"41","article-title":"Fine-grained dram: Energy-efficient dram for extreme bandwidth systems","volume-title":"Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture","author":"O\u2019Connor"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2025,6,22]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11133230.pdf?arnumber=11133230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:50:48Z","timestamp":1758001848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11133230","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}