{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T05:45:35Z","timestamp":1777787135553,"version":"3.51.4"},"reference-count":17,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":[[2026,3]]},"DOI":"10.1109\/mm.2026.3667115","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:56:24Z","timestamp":1772052984000},"page":"38-50","source":"Crossref","is-referenced-by-count":0,"title":["Demystifying the Cost Versus Benefits of Sparse Large Language Model Acceleration"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0145-9713","authenticated-orcid":false,"given":"Abhimanyu R.","family":"Bambhaniya","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7928-9027","authenticated-orcid":false,"given":"Sheng-Chun","family":"Kao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6659-3927","authenticated-orcid":false,"given":"Geonhwa","family":"Jeong","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8715-8964","authenticated-orcid":false,"given":"Suvinay","family":"Subramanian","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8531-1873","authenticated-orcid":false,"given":"Amir","family":"Yazdanbakhsh","sequence":"additional","affiliation":[{"name":"Google DeepMind, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5738-6942","authenticated-orcid":false,"given":"Tushar","family":"Krishna","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/isca52012.2021.00010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85747-8_6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/hpca56546.2023.10071058"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iiswc53511.2021.00028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/nocs.2012.31"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/micro56248.2022.00096"},{"key":"ref10","volume-title":"Efficient Processing of Deep Neural Networks (Synthesis Lectures on Computer Architecture (SLCA))","author":"Sze","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2021.3098483"},{"key":"ref12","article-title":"The sparsity roofline: Understanding the hardware limits of sparse neural networks","author":"Shinn","year":"2023"},{"key":"ref13","first-page":"10,323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Frantar","year":"2023"},{"key":"ref14","first-page":"1170","article-title":"Progressive gradient flow for robust N:M sparsity training in transformers","volume-title":"Proc. 2nd Conf. Parsimony Learn. (CPAL)","author":"Bambhaniya","year":"2025"},{"key":"ref15","article-title":"Learning N:M fine-grained structured sparse neural networks from scratch","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Zhou","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037749"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00178"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/40\/11498487\/11410568.pdf?arnumber=11410568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:49:41Z","timestamp":1777492181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11410568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":17,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/mm.2026.3667115","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"value":"0272-1732","type":"print"},{"value":"1937-4143","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}