{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:05:24Z","timestamp":1776121524969,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFC0803700"],"award-info":[{"award-number":["2017YFC0803700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832006"],"award-info":[{"award-number":["61832006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2021,4,1]]},"DOI":"10.1109\/tc.2020.2990321","type":"journal-article","created":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T15:38:31Z","timestamp":1588606711000},"page":"552-565","source":"Crossref","is-referenced-by-count":7,"title":["TurboDL: Improving the CNN Training on GPU With Fine-Grained Multi-Streaming Scheduling"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-7605","authenticated-orcid":false,"given":"Hai","family":"Jin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0814-0919","authenticated-orcid":false,"given":"Wenchao","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8451-8656","authenticated-orcid":false,"given":"Xuanhua","family":"Shi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5671-0576","authenticated-orcid":false,"given":"Ligang","family":"He","sequence":"additional","affiliation":[]},{"given":"Bing Bing","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342276"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref32","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851158"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304072"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.52"},{"key":"ref40","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.53"},{"key":"ref16","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","author":"zhang","year":"2017","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967944"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225077"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref28","year":"2019"},{"key":"ref4","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref27","year":"2019"},{"key":"ref3","year":"2019"},{"key":"ref6","first-page":"951","article-title":"DeepCPU: Serving RNN-based deep learning models 10X faster","author":"zhang","year":"0","journal-title":"Proc USENIX Conf Usenix Annu Techn Conf"},{"key":"ref29","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref5","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref7","first-page":"937","article-title":"Cavs: An efficient runtime system for dynamic neural networks","author":"xu","year":"2018","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref1","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref22","article-title":"Deep learning with dynamic computation graphs","author":"looks","year":"2017"},{"key":"ref21","article-title":"Training deep nets with sublinear memory cost","author":"chen","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190551"},{"key":"ref41","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc Int Conf Neural Inf Process Syst Workshop"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190530"},{"key":"ref26","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190541"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/9378888\/09086163.pdf?arnumber=9086163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:51:12Z","timestamp":1641988272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9086163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tc.2020.2990321","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":[[2021,4,1]]}}}