An Energy-Efficient Deep Neural Network Training Processor with Bit-Slice-Level Reconfigurability and Sparsity Exploitation

Donghyeon Han, Dongseok Im, Gwangtae Park, YoungWoo Kim, Seokchan Song, Juhyoung Lee, Hoi-Jun Yoo. An Energy-Efficient Deep Neural Network Training Processor with Bit-Slice-Level Reconfigurability and Sparsity Exploitation. In IEEE Symposium in Low-Power and High-Speed Chips, COOL CHIPS 2021, Tokyo, Japan, April 14-16, 2021. pages 1-3, IEEE, 2021. [doi]

@inproceedings{HanIPKSLY21,
  title = {An Energy-Efficient Deep Neural Network Training Processor with Bit-Slice-Level Reconfigurability and Sparsity Exploitation},
  author = {Donghyeon Han and Dongseok Im and Gwangtae Park and YoungWoo Kim and Seokchan Song and Juhyoung Lee and Hoi-Jun Yoo},
  year = {2021},
  doi = {10.1109/COOLCHIPS52128.2021.9410324},
  url = {https://doi.org/10.1109/COOLCHIPS52128.2021.9410324},
  researchr = {https://researchr.org/publication/HanIPKSLY21},
  cites = {0},
  citedby = {0},
  pages = {1-3},
  booktitle = {IEEE Symposium in Low-Power and High-Speed Chips, COOL CHIPS 2021, Tokyo, Japan, April 14-16, 2021},
  publisher = {IEEE},
  isbn = {978-1-6654-1503-3},
}