{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T21:15:01Z","timestamp":1773436501901,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea government","award":["RS-2024-00357037"],"award-info":[{"award-number":["RS-2024-00357037"]}]},{"DOI":"10.13039\/100004358","name":"Samsung Electronics Company, Ltd","doi-asserted-by":"crossref","award":["IO250214-11969-01"],"award-info":[{"award-number":["IO250214-11969-01"]}],"id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Topics Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tetc.2025.3626723","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T18:37:02Z","timestamp":1762281422000},"page":"3-16","source":"Crossref","is-referenced-by-count":0,"title":["MaxiMoff: Designing Matrix Multiplication Accelerator for Effective Multiply-Add Operations Offloading"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0106-6590","authenticated-orcid":false,"given":"Sungwoo","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4090-4025","authenticated-orcid":false,"given":"Dongho","family":"Ha","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Sunnyvale, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2523-7043","authenticated-orcid":false,"given":"Seunghwan","family":"Sung","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5390-6445","authenticated-orcid":false,"given":"Won Woo","family":"Ro","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref2","article-title":"NVIDIA T4 tensor core GPU","year":"2019"},{"key":"ref3","article-title":"NVIDIA A100 tensor core GPU architecture","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3011893"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00032"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cluster48925.2021.00035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00043"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3152217"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517869"},{"key":"ref13","first-page":"367","article-title":"MAD MAcce: Supporting multiply-add operations for democratizing matrix-multiplication accelerators","volume-title":"Proc. 56th Annu. IEEE\/ACM Int. Symp. Microarchitecture","author":"Sung"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"ref15","first-page":"552","article-title":"SIMD2: A generalized matrix instruction set for accelerating tensor computation beyond GEMM","volume-title":"Proc. 49th Annu. Int. Symp. Comput. Archit.","author":"Zhang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref18","article-title":"NVIDIA Tesla V100 GPU architecture","year":"2017"},{"key":"ref19","article-title":"NVIDIA hopper architecture in-depth","volume-title":"NVIDIA Tech. Blog","author":"Andersch","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441599"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2005.52"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/math3020337"},{"issue":"1","key":"ref23","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.nima.2005.11.140","article-title":"High precision numerical accuracy in physics research","volume":"559","author":"de Dinechin","year":"2006","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A: Accel. Spectrometers Detect. Assoc. Equip."},{"issue":"15","key":"ref24","doi-asserted-by":"crossref","first-page":"3584","DOI":"10.1016\/j.cam.2011.04.025","article-title":"Parallel preconditioned conjugate gradient algorithm on GPU","volume":"236","author":"Helfenstein","year":"2012","journal-title":"J. Comput. Appl. Math."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1051\/0004-6361:20021761"},{"key":"ref26","article-title":"CUDA k-means data clustering","author":"Giuroiu","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2010.5654017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2011.04.053"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3322125"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2517327.2442530"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw.2018.00091"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532377"},{"key":"ref33","article-title":"cuTlass 3.1","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221090256"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476157"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/isca45697.2020.00047"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480063"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref40","article-title":"Cuda samples v12.1","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108171"},{"key":"ref43","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","volume":"127","author":"Stratton","year":"2012","journal-title":"Center Reliable High-Perform. Comput."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1063\/5.0014475"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245516\/11433431\/11226949.pdf?arnumber=11226949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T19:54:42Z","timestamp":1773431682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11226949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":45,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tetc.2025.3626723","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"value":"2168-6750","type":"electronic"},{"value":"2376-4562","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}