CIMAT: a transpose SRAM-based compute-in-memory architecture for deep neural network on-chip training

Hongwu Jiang, Xiaochen Peng, Shanshi Huang, Shimeng Yu. CIMAT: a transpose SRAM-based compute-in-memory architecture for deep neural network on-chip training. In Proceedings of the International Symposium on Memory Systems, MEMSYS 2019, Washington, DC, USA, September 30 - October 03, 2019. pages 490-496, ACM, 2019. [doi]

@inproceedings{JiangPHY19,
  title = {CIMAT: a transpose SRAM-based compute-in-memory architecture for deep neural network on-chip training},
  author = {Hongwu Jiang and Xiaochen Peng and Shanshi Huang and Shimeng Yu},
  year = {2019},
  doi = {10.1145/3357526.3357552},
  url = {https://doi.org/10.1145/3357526.3357552},
  researchr = {https://researchr.org/publication/JiangPHY19},
  cites = {0},
  citedby = {0},
  pages = {490-496},
  booktitle = {Proceedings of the International Symposium on Memory Systems, MEMSYS 2019, Washington, DC, USA, September 30 - October 03, 2019},
  publisher = {ACM},
  isbn = {978-1-4503-7206-0},
}