{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:35:54Z","timestamp":1781714154777,"version":"3.54.5"},"reference-count":6,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"IBM IIDAI and Google"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/lca.2024.3397747","type":"journal-article","created":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T17:19:39Z","timestamp":1716571179000},"page":"117-120","source":"Crossref","is-referenced-by-count":25,"title":["Exploiting Intel Advanced Matrix Extensions (AMX) for Large Language Model Inference"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1157-0127","authenticated-orcid":false,"given":"Hyungyo","family":"Kim","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7211-9750","authenticated-orcid":false,"given":"Gaohan","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1431-0067","authenticated-orcid":false,"given":"Nachuan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8199-7671","authenticated-orcid":false,"given":"Amir","family":"Yazdanbakhsh","sequence":"additional","affiliation":[{"name":"Google Deepmind, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref3","first-page":"22964","article-title":"What language model architecture and pretraining objective works best for zero-shot generalization?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref4","article-title":"Training large neural networks with constant memory using a new execution algorithm","author":"Pudipeddi","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref6","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sheng"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10208\/10375809\/10538369.pdf?arnumber=10538369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T04:31:54Z","timestamp":1716870714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10538369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":6,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2024.3397747","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":[[2024,1]]}}}