| {HetPipe}: Enabling large {DNN} training on (whimpy) heterogeneous {GPU} clusters through integration of pipelined model parallelism and data parallelism JH Park, G Yun, MY Chang, NT Nguyen, S Lee, J Choi, SH Noh, Y Choi 2020 USENIX Annual Technical Conference (USENIX ATC 20), 307-321, 2020 | 150 | 2020 |
