Reliability of Large Scale GPU Clusters for Deep Learning Workloads.

@inproceedings{qian-2021-reliability, author = {Junjie Qian and Taeyoon Kim and Myeongjae Jeon}, editor = {Jure Leskovec and Marko Grobelnik and Marc Najork and Jie Tang and Leila Zia}, title = {{Reliability of Large Scale GPU Clusters for Deep Learning Workloads}}, booktitle = {{Companion of The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021}}, pages = {179--181}, publisher = {ACM / IW3C2}, year = {2021}, url = {https://doi.org/10.1145/3442442.3452056}, doi = {https://doi.org/10.1145/3442442.3452056} }