{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:44:00Z","timestamp":1783788240241,"version":"3.55.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Research Funding Incubation Center of Samsung Electronics","award":["SRFC-IT1801-04"],"award-info":[{"award-number":["SRFC-IT1801-04"]}]},{"name":"Samsung Research Funding Incubation Center of Samsung Electronics","award":["SRFC-IT1902-03"],"award-info":[{"award-number":["SRFC-IT1902-03"]}]},{"DOI":"10.13039\/501100003836","name":"IC Design Education Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003836","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tc.2023.3253050","type":"journal-article","created":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T18:39:47Z","timestamp":1678127987000},"page":"2522-2535","source":"Crossref","is-referenced-by-count":30,"title":["FlexBlock: A Flexible DNN Training Accelerator With Multi-Mode Block Floating Point Support"],"prefix":"10.1109","volume":"72","author":[{"given":"Seock-Hwan","family":"Noh","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science and Technology (DGIST), Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jahyun","family":"Koo","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science and Technology (DGIST), Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seunghyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science and Technology (DGIST), Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6629-449X","authenticated-orcid":false,"given":"Jongse","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Korea Advanced Institute of Science and Technology (KAIST), Daejon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6151-8602","authenticated-orcid":false,"given":"Jaeha","family":"Kung","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173191"},{"key":"ref4","first-page":"207","article-title":"A graph placement methodology for fast chip design","volume-title":"Nature","volume":"594","author":"Mirhoseini","year":"2021"},{"key":"ref5","article-title":"Mixed precision training","author":"Micikevicius","year":"2017"},{"key":"ref6","article-title":"BFloat16: The secret to high performance on cloud TPUs","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH48897.2020.00029"},{"key":"ref8","article-title":"Regularized evolution for image classifier architecture search","author":"Real","year":"2018"},{"key":"ref9","first-page":"1740","article-title":"FlexPoint: An adaptive numerical format for efficient training of deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"K\u00f6ster"},{"key":"ref10","first-page":"451","article-title":"Training DNNs with hybrid block floating point","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Drumond"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"ref12","first-page":"1","article-title":"BitBlade: Area and energy-efficient precision-scalable neural network accelerator with bitwise summation","volume-title":"Proc. IEEE\/ACM Des. Automat. Conf.","author":"Ryu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858358"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2018.00021"},{"key":"ref17","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","author":"Huang","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00064"},{"key":"ref20","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref21","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"issue":"187","key":"ref22","first-page":"1","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","first-page":"1796","article-title":"Ultra-low precision 4-bit training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00067"},{"key":"ref25","first-page":"7686","article-title":"Training deep neural networks with 8-bit floating point numbers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9366031"},{"key":"ref27","first-page":"4900","article-title":"Hybrid 8-bit floating point (HFP8) training and inference for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/78.492531"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870350"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310262"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465915"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2950386"},{"key":"ref34","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref35","article-title":"CIFAR-10 and CIFAR-100 dataset","author":"Krizhevsky","year":"2010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref37","first-page":"12","article-title":"Findings of the 2014 workshop on statistical machine translation","volume-title":"Proc. 9th Workshop Statist. Mach. Transl.","author":"Bojar"},{"key":"ref38","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref39","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2918284"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","article-title":"Design compiler user guide: Version N-2017.09","year":"2017"},{"key":"ref44","article-title":"IC compiler II implementation user guide: Version L-2016.03","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/4.509850"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2011.6105405"},{"key":"ref47","article-title":"Scale-sim: Systolic CNN accelerator simulator","author":"Samajdar","year":"2018"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/10213258\/10059122.pdf?arnumber=10059122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T01:04:14Z","timestamp":1709427854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10059122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":47,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tc.2023.3253050","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]}}}