{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:10:03Z","timestamp":1759133403612,"version":"3.44.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683053","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"1453-1457","source":"Crossref","is-referenced-by-count":1,"title":["Workload-aware Automatic Parallelization for Multi-GPU DNN Training"],"prefix":"10.1109","author":[{"given":"Sungho","family":"Shin","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngmin","family":"Jo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungwook","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swagath","family":"Venkataramani","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijayalakshmi","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonyong","family":"Sung","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Parallax: Automatic data-parallel training of deep neural networks","year":"2018","author":"kim","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7056.001.0001"},{"year":"0","key":"ref12"},{"key":"ref13","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"article-title":"One weird trick for parallelizing convo-lutional neural networks","year":"2014","author":"krizhevsky","key":"ref14"},{"year":"0","key":"ref15"},{"article-title":"Dynet: The dynamic neural network toolkit","year":"2017","author":"neubig","key":"ref16"},{"article-title":"Horovod: fast and easy distributed deep learning in tensorflow","year":"2018","author":"sergeev","key":"ref17"},{"key":"ref18","first-page":"2274","article-title":"Exploring hidden dimensions in accelerating convolutional neural networks","author":"qi","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning (ICML 2018)"},{"year":"0","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"abadi","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2016.7539037"},{"article-title":"Very deep convo-lutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref2"},{"key":"ref1","first-page":"1097","article-title":"Ima-genet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4_12"},{"year":"0","key":"ref20"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683053.pdf?arnumber=8683053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:29:29Z","timestamp":1755714569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683053","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}