29 citations · 35 across the 3 of their papers we have counts for
3 papers
cs.DC2020★ 5 cited
Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads
Siyu Wang, Yi Rong, Shiqing Fan +6
The last decade has witnessed growth in the computational requirements for training deep neural networks. Current approaches (e.g., data/model parallelism, pipeline parallelism) pa…
cs.DC2020★ 29 cited
DAPPLE: A Pipelined Data Parallel Approach for Training Large Models
Shiqing Fan, Yi Rong, Chen Meng +10
It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an e…
cs.DC2020★ 1 cited
DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging
Qinggang Zhou, Yawen Zhang, Pengcheng Li +4
The state-of-the-art deep learning algorithms rely on distributed training systems to tackle the increasing sizes of models and training data sets. Minibatch stochastic gradient de…