{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:50:22Z","timestamp":1775598622675,"version":"3.50.1"},"reference-count":11,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of IITP grant funded by the Korea government","award":["2021-0-00863"],"award-info":[{"award-number":["2021-0-00863"]}]},{"name":"Institute of IITP grant funded by the Korea government","award":["IITP-2023-RS-2023-00256081"],"award-info":[{"award-number":["IITP-2023-RS-2023-00256081"]}]},{"name":"PRISM"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/lca.2023.3305386","type":"journal-article","created":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T17:28:28Z","timestamp":1692120508000},"page":"113-116","source":"Crossref","is-referenced-by-count":13,"title":["Unleashing the Potential of PIM: Accelerating Large Batched Inference of Transformer-Based Generative Models"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2447-4369","authenticated-orcid":false,"given":"Jaewan","family":"Choi","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5623-6985","authenticated-orcid":false,"given":"Jaehyun","family":"Park","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4243-2111","authenticated-orcid":false,"given":"Kwanhee","family":"Kyung","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0442-5634","authenticated-orcid":false,"given":"Nam Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"shoeybi","year":"2019"},{"key":"ref9","first-page":"521","article-title":"ORCA: A distributed serving system for transformer-based generative models","author":"yu","year":"2022","journal-title":"Proc 16th USENIX Symp Operating Syst Des Implementation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124545"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480080"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref5","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref10","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","author":"zaheer","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref2","first-page":"616","article-title":"DFX: A low-latency multi-FPGA appliance for accelerating transformer-based text generation","author":"hong","year":"2022","journal-title":"Proc IEEE\/ACM 55th Int Symp Microarchitecture"},{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10208\/10189818\/10218731.pdf?arnumber=10218731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T18:44:08Z","timestamp":1696877048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10218731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":11,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2023.3305386","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":[[2023,7]]}}}