@inproceedings {234916, author = {Myeongjae Jeon and Shivaram Venkataraman and Amar Phanishayee and Junjie Qian and Wencong Xiao and Fan Yang}, title = {Analysis of {Large-Scale} {Multi-Tenant} {GPU} Clusters for {DNN} Training Workloads}, booktitle = {2019 USENIX Annual Technical Conference (USENIX ATC 19)}, year = {2019}, isbn = {978-1-939133-03-8}, address = {Renton, WA}, pages = {947--960}, url = {https://www.usenix.org/conference/atc19/presentation/jeon}, publisher = {USENIX Association}, month = jul } @inproceedings {227623, author = {Juncheng Gu and Mosharaf Chowdhury and Kang G. Shin and Yibo Zhu and Myeongjae Jeon and Junjie Qian and Hongqiang Liu and Chuanxiong Guo}, title = {Tiresias: A {GPU} Cluster Manager for Distributed Deep Learning}, booktitle = {16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)}, year = {2019}, isbn = {978-1-931971-49-2}, address = {Boston, MA}, pages = {485--500}, url = {https://www.usenix.org/conference/nsdi19/presentation/gu}, publisher = {USENIX Association}, month = feb }