English

Zero Aware Configurable Data Encoding by Skipping Transfer for Error Resilient Applications

Hardware Architecture 2021-05-18 v1

Abstract

In this paper, we propose Zero Aware Configurable Data Encoding by Skipping Transfer (ZAC-DEST), a data encoding scheme to reduce the energy consumption of DRAM channels, specifically targeted towards approximate computing and error resilient applications. ZAC-DEST exploits the similarity between recent data transfers across channels and information about the error resilience behavior of applications to reduce on-die termination and switching energy by reducing the number of 1's transmitted over the channels. ZAC-DEST also provides a number of knobs for trading off the application's accuracy for energy savings, and vice versa, and can be applied to both training and inference. We apply ZAC-DEST to five machine learning applications. On average, across all applications and configurations, we observed a reduction of 4040% in termination energy and 3737% in switching energy as compared to the state of the art data encoding technique BD-Coder with an average output quality loss of 1010%. We show that if both training and testing are done assuming the presence of ZAC-DEST, the output quality of the applications can be improved upto 9 times as compared to when ZAC-DEST is only applied during testing leading to energy savings during training and inference with increased output quality.

Keywords

Cite

@article{arxiv.2105.07432,
  title  = {Zero Aware Configurable Data Encoding by Skipping Transfer for Error Resilient Applications},
  author = {Chandan Kumar Jha and Shreyas Singh and Riddhi Thakker and Manu Awasthi and Joycee Mekie},
  journal= {arXiv preprint arXiv:2105.07432},
  year   = {2021}
}
R2 v1 2026-06-24T02:09:17.468Z