GLP4NN: A Convergence-invariant and Network-agnostic Light-weight Parallelization Framework for Deep Neural Networks on Modern GPUs

Hao Fu, Shanjiang Tang, Bingsheng He, Ce Yu, Jizhou Sun. GLP4NN: A Convergence-invariant and Network-agnostic Light-weight Parallelization Framework for Deep Neural Networks on Modern GPUs. In Proceedings of the 47th International Conference on Parallel Processing, ICPP 2018, Eugene, OR, USA, August 13-16, 2018. ACM, 2018. [doi]

Abstract

Abstract is missing.