English

Leveraging Residue Number System for Designing High-Precision Analog Deep Neural Network Accelerators

Hardware Architecture 2023-06-19 v1 Emerging Technologies Machine Learning Neural and Evolutionary Computing

Abstract

Achieving high accuracy, while maintaining good energy efficiency, in analog DNN accelerators is challenging as high-precision data converters are expensive. In this paper, we overcome this challenge by using the residue number system (RNS) to compose high-precision operations from multiple low-precision operations. This enables us to eliminate the information loss caused by the limited precision of the ADCs. Our study shows that RNS can achieve 99% FP32 accuracy for state-of-the-art DNN inference using data converters with only 66-bit precision. We propose using redundant RNS to achieve a fault-tolerant analog accelerator. In addition, we show that RNS can reduce the energy consumption of the data converters within an analog accelerator by several orders of magnitude compared to a regular fixed-point approach.

Keywords

Cite

@article{arxiv.2306.09481,
  title  = {Leveraging Residue Number System for Designing High-Precision Analog Deep Neural Network Accelerators},
  author = {Cansu Demirkiran and Rashmi Agrawal and Vijay Janapa Reddi and Darius Bunandar and Ajay Joshi},
  journal= {arXiv preprint arXiv:2306.09481},
  year   = {2023}
}
R2 v1 2026-06-28T11:06:36.265Z