{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T23:03:33Z","timestamp":1784156613043,"version":"3.55.0"},"reference-count":12,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"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 Micro"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/mm.2024.3373763","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T19:21:18Z","timestamp":1711394478000},"page":"33-39","source":"Crossref","is-referenced-by-count":291,"title":["AI and Memory Wall"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1374-3105","authenticated-orcid":false,"given":"Amir","family":"Gholami","sequence":"first","affiliation":[{"name":"UC Berkeley, , Berkeley, CA, 94720, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7678-4321","authenticated-orcid":false,"given":"Zhewei","family":"Yao","sequence":"additional","affiliation":[{"name":"Snowflake, Bellevue, , WA, 98004, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9339-5480","authenticated-orcid":false,"given":"Sehoon","family":"Kim","sequence":"additional","affiliation":[{"name":"UC Berkeley, , Berkeley, CA, 94720, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5890-610X","authenticated-orcid":false,"given":"Coleman","family":"Hooper","sequence":"additional","affiliation":[{"name":"UC Berkeley, , Berkeley, CA, 94720, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7920-4652","authenticated-orcid":false,"given":"Michael W.","family":"Mahoney","sequence":"additional","affiliation":[{"name":"UC Berkeley, , Berkeley, CA, 94720, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3868-8501","authenticated-orcid":false,"given":"Kurt","family":"Keutzer","sequence":"additional","affiliation":[{"name":"UC Berkeley, , Berkeley, CA, 94720, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"issue":"1","key":"ref4","first-page":"10,882","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref6","first-page":"497","article-title":"Checkmate: Breaking the memory wall with optimal tensor rematerialization","volume":"2","author":"Jain","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref7","article-title":"Full stack optimization of transformer inference: a survey","author":"Kim","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1022594.1022596"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17275"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/40\/10568462\/10477550.pdf?arnumber=10477550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T20:01:12Z","timestamp":1719345672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10477550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":12,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/mm.2024.3373763","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"value":"0272-1732","type":"print"},{"value":"1937-4143","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}