{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:21:26Z","timestamp":1781886086552,"version":"3.54.5"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["618722374"],"award-info":[{"award-number":["618722374"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272475"],"award-info":[{"award-number":["62272475"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tvlsi.2022.3226185","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:42:18Z","timestamp":1671043338000},"page":"253-266","source":"Crossref","is-referenced-by-count":22,"title":["Multiple-Mode-Supporting Floating-Point FMA Unit for Deep Learning Processors"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4184-4173","authenticated-orcid":false,"given":"Hongbing","family":"Tan","sequence":"first","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gan","family":"Tong","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-3998","authenticated-orcid":false,"given":"Libo","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liquan","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Automatic Speech Recognition","volume":"1","author":"Yu","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2509257"},{"key":"ref5","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016","journal-title":"arXiv:1602.02410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"ref7","article-title":"Reduced-precision memory value approximation for deep learning","author":"Deng","year":"2015"},{"key":"ref8","first-page":"1","article-title":"BinaryNet: Training deep neural networks with weights and activations constrained to +1 or \u22121","volume":"abs\/1602","author":"Courbariaux","year":"2016","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2013.27"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934587"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00054"},{"key":"ref14","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref15","first-page":"1","article-title":"Flexpoint: An adaptive numerical format for efficient training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"K\u00f6ster"},{"key":"ref16","volume-title":"Performance Benefits of Half Precision Floats","author":"Konsor","year":"2012"},{"key":"ref17","volume-title":"How Knights Mill Gets Its Deep Learning Flops","author":"Trader","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875654"},{"key":"ref19","article-title":"A study of BFLOAT16 for deep learning training","author":"Kalamkar","year":"2019","journal-title":"arXiv:1905.12322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356149"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.330"},{"key":"ref23","article-title":"Mixed precision training","author":"Micikevicius","year":"2017","journal-title":"arXiv:1710.03740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2018.8351354"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6189977"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221090256"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IEEESTD.2019.8766229"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1093\/qjmam\/4.2.236"},{"key":"ref29","article-title":"Fast multiplication: Algorithms and implementation","author":"Bewick","year":"1994"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2001.930098"},{"key":"ref31","volume-title":"Berkeley Testfloat","author":"Hauser","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2007.5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS.2010.5724440"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2017.12.009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2007.11.001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2015.10.012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.77"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2895031"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2021.3128435"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/92\/10019332\/09985465.pdf?arnumber=9985465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:13:20Z","timestamp":1706760800000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9985465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2022.3226185","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"value":"1063-8210","type":"print"},{"value":"1557-9999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}