Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation. Awan, A. A., Bédorf, J., Chu, C., Subramoni, H., & Panda, D. K. CoRR, 2018.
Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation [link]Paper  bibtex   
@article{DBLP:journals/corr/abs-1810-11112,
  author    = {Ammar Ahmad Awan and
               Jeroen B{\'{e}}dorf and
               Ching{-}Hsiang Chu and
               Hari Subramoni and
               Dhabaleswar K. Panda},
  title     = {Scalable Distributed {DNN} Training using TensorFlow and CUDA-Aware
               {MPI:} Characterization, Designs, and Performance Evaluation},
  journal   = {CoRR},
  volume    = {abs/1810.11112},
  year      = {2018},
  url       = {http://arxiv.org/abs/1810.11112},
  archivePrefix = {arXiv},
  eprint    = {1810.11112},
  timestamp = {Wed, 31 Oct 2018 00:00:00 +0100},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1810-11112},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0