{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:20Z","timestamp":1737176840121,"version":"3.33.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825722","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"179-188","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Data-parallel Distributed DNN Training for Big Dataset under Heterogeneous GPU Cluster"],"prefix":"10.1109","author":[{"given":"Shinyoung","family":"Ahn","sequence":"first","affiliation":[{"name":"ETRI,Supercomputing System Research Section,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sookwang","family":"Lee","sequence":"additional","affiliation":[{"name":"ETRI,Supercomputing System Research Section,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyeonseong","family":"Choi","sequence":"additional","affiliation":[{"name":"MangoBoost,Software Team,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaehyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Puzzle AI Inc.,Research Institute,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling laws for neural language models","volume":"abs\/2001.08361","author":"Kaplan","year":"2020","journal-title":"CoRR"},{"key":"ref2","first-page":"571","article-title":"Project Adam: building an efficient and scalable deep learning training system","volume-title":"Proceedings of the 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Chilimbi"},{"key":"ref3","first-page":"265","article-title":"On optimization methods for deep learning","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML\u201911)","author":"Le"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877890"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2834146"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC.2018.8539420"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553486"},{"key":"ref10","first-page":"1232","article-title":"Large scale distributed deep networks","volume-title":"Proceedings of 26th Annual Conference on Neural Information Processing (NIPS\u201912)","author":"Dean"},{"key":"ref11","article-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","year":"2014","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2996464"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25255-1_65"},{"article-title":"Revisiting distributed synchronous SGD","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR) Workshop Track","author":"Chen","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref17","first-page":"685","article-title":"Deep learning with elastic averaging sgd","volume-title":"Advances in Neural Information Processing Systems 28","author":"Zhang","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0028"},{"key":"ref19","article-title":"Demystifying parallel and distributed deep learning: An in-depth concurrency analysis","volume":"52","author":"Ben-Nun","year":"2019","journal-title":"ACM Comput. Surv."},{"key":"ref20","article-title":"Imagenet\/resnet-50 training in 224 seconds","volume":"abs\/1811.05233","author":"Mikami","year":"2018","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17813"},{"key":"ref22","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proceedings of the 25th Advances in Neural Information Processing Systems (NIPS\u201911)","author":"Recht"},{"key":"ref23","article-title":"Zero-offload: Democratizing billion-scale model training","volume":"abs\/2101.06840","author":"Ren","year":"2021","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1145\/3458817.3476209","article-title":"Efficient large-scale language model training on gpu clusters using megatron-lm","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Narayanan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps53621.2022.00065"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","article-title":"You only look once: Unified, real-time object detection","volume":"abs\/1506.02640","author":"Redmon","year":"2015","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4324\/9780203978948-13"},{"article-title":"Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","year":"2022","author":"Wang","key":"ref30"},{"volume-title":"Yolov5 release v6.1.","author":"Glenn","key":"ref31"},{"article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","year":"2017","author":"Goyal","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"article-title":"Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes","volume-title":"Proceedings of Workshop on Machine Learning Systems in The 32th Annual Conference on Neural Information Processing Systems","author":"Jia","key":"ref34"},{"key":"ref35","volume":"abs\/1811.06992","author":"Ying","year":"2018","journal-title":"Image classification at supercomputer scale"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825722.pdf?arnumber=10825722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:48:05Z","timestamp":1737100085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825722","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}