A 28nm 1.644TFLOPS/W Floating-Point Computation SRAM Macro with Variable Precision for Deep Neural Network Inference and Training

Sangsu Jeong, Jeongwoo Park, Dongsuk Jeon. A 28nm 1.644TFLOPS/W Floating-Point Computation SRAM Macro with Variable Precision for Deep Neural Network Inference and Training. In 48th IEEE European Solid State Circuits Conference, ESSCIRC 2022, Milan, Italy, September 19-22, 2022. pages 145-148, IEEE, 2022. [doi]

@inproceedings{JeongPJ22,
  title = {A 28nm 1.644TFLOPS/W Floating-Point Computation SRAM Macro with Variable Precision for Deep Neural Network Inference and Training},
  author = {Sangsu Jeong and Jeongwoo Park and Dongsuk Jeon},
  year = {2022},
  doi = {10.1109/ESSCIRC55480.2022.9911450},
  url = {https://doi.org/10.1109/ESSCIRC55480.2022.9911450},
  researchr = {https://researchr.org/publication/JeongPJ22},
  cites = {0},
  citedby = {0},
  pages = {145-148},
  booktitle = {48th IEEE European Solid State Circuits Conference, ESSCIRC 2022, Milan, Italy, September 19-22, 2022},
  publisher = {IEEE},
  isbn = {978-1-6654-8494-7},
}