{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T15:52:14Z","timestamp":1784562734210,"version":"3.55.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1109\/access.2022.3184692","type":"journal-article","created":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T19:41:15Z","timestamp":1655840475000},"page":"68468-68481","source":"Crossref","is-referenced-by-count":3,"title":["Scale-Train: A Scalable DNN Training Framework for a Heterogeneous GPU Cloud"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9811-9899","authenticated-orcid":false,"given":"Kyeonglok","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Sungkyunkwan University, Suwon-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeonsu","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sungkyunkwan University, Suwon-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungmin","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sungkyunkwan University, Suwon-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2103-8019","authenticated-orcid":false,"given":"Euiseong","family":"Seo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sungkyunkwan University, Suwon-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref2","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Conf. Netw Syst. Design Implement.","author":"Gu"},{"key":"ref3","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. 14th USENIX Conf. Oper. Syst. Design Implement.","author":"Jiang"},{"key":"ref4","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018","journal-title":"arXiv:1802.05799"},{"key":"ref5","article-title":"Performance analysis and comparison of distributed machine learning systems","author":"Alqahtani","year":"2019","journal-title":"arXiv:1909.02061"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2017.21"},{"key":"ref7","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Conf. Oper. Syst. Design Implement.","author":"Xiao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-66"},{"key":"ref9","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Jeon"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-02845-2"},{"key":"ref11","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016","journal-title":"arXiv:1603.04467"},{"key":"ref12","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref14","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref18","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref19","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015","journal-title":"arXiv:1512.01274"},{"key":"ref20","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 32th Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"ref22","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","first-page":"937","article-title":"KungFu: Making training in distributed machine learning adaptive","volume-title":"Proc. 14th USENIX Conf. Oper. Syst. Design Implement.","author":"Mai"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3064966"},{"key":"ref26","first-page":"1","article-title":"Revisiting distributed synchronous SGD","volume-title":"Proc. Int. Conf. Learn. Represent. Workshop Track","author":"Chen"},{"key":"ref27","article-title":"High throughput synchronous distributed stochastic gradient descent","author":"Teng","year":"2018","journal-title":"arXiv:1803.04209"},{"key":"ref28","first-page":"3043","article-title":"Asynchronous decentralized parallel stochastic gradient descent","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Lian"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378499"},{"key":"ref30","first-page":"3368","article-title":"Gradient coding: Avoiding stragglers in distributed learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Tandon"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421299"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03200-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337873"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09801853.pdf?arnumber=9801853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:41:05Z","timestamp":1706766065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9801853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3184692","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}