{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T12:04:00Z","timestamp":1752667440841,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3488004","type":"journal-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:55:34Z","timestamp":1730310934000},"page":"160190-160204","source":"Crossref","is-referenced-by-count":1,"title":["Accelerating CNN Training With Concurrent Execution of GPU and Processing-in-Memory"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4259-0566","authenticated-orcid":false,"given":"Jungwoo","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Inter-University Semiconductor Research Center (ISRC), Seoul National University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8895-9117","authenticated-orcid":false,"given":"Hyuk-Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Inter-University Semiconductor Research Center (ISRC), Seoul National University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8094-9843","authenticated-orcid":false,"given":"Kyomin","family":"Sohn","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Hwaseong-si, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2782-5264","authenticated-orcid":false,"given":"Hak-Soo","family":"Yu","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Hwaseong-si, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7851-1703","authenticated-orcid":false,"given":"Chae Eun","family":"Rhee","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref4","article-title":"Fast training of convolutional networks through FFTs","author":"Mathieu","year":"2013","journal-title":"arXiv:1312.5851"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00042"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357532"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00072"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2984496"},{"key":"ref13","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2020.2975055"},{"key":"ref16","first-page":"14","article-title":"Restructuring batch normalization to accelerate CNN training","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Jung"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401434"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3287624.3287718"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071134"},{"key":"ref20","article-title":"Dissecting the NVIDIA Volta GPU architecture via microbenchmarking","author":"Jia","year":"2018","journal-title":"arXiv:1804.06826"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/isscc.2018.8310257"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.51"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237036"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818979"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00016"},{"volume-title":"CUTLASS: CUDA Template Library for Dense Linear Algebra at All Levels and Scales","year":"2018","key":"ref30"},{"key":"ref31","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s21082852"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628096"},{"key":"ref35","article-title":"Efficient and robust parallel DNN training through model parallelism on multi-GPU platform","author":"Chen","year":"2018","journal-title":"arXiv:1809.02839"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967940"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001159"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480103"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00591"},{"key":"ref42","first-page":"264","article-title":"Mini-batch serialization: CNN training with inter-layer data reuse","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Lym"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304038"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00030"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2020.3021397"},{"key":"ref46","first-page":"1","article-title":"FPGA-based low-batch training accelerator for modern CNNs featuring high bandwidth memory","volume-title":"Proc. IEEE\/ACM Int. Conf. Comput. Aided Design (ICCAD)","author":"Venkataramanaiah"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2911999"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00059"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2022.3167391"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303950"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538932"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502359"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10738803.pdf?arnumber=10738803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T04:38:32Z","timestamp":1732682312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10738803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3488004","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}