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

TL;DR

This paper introduces ZAC-DEST, a data encoding scheme that reduces energy consumption in DRAM channels for error resilient applications by skipping data transfer, with adjustable accuracy-energy trade-offs and significant energy savings demonstrated on machine learning tasks.

Contribution

ZAC-DEST is a novel configurable data encoding method that exploits data similarity and application error resilience to reduce energy use in DRAM channels, applicable during training and inference.

Findings

40% reduction in termination energy

37% reduction in switching energy

up to 9 times improvement in output quality when training and testing with ZAC-DEST

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 $40$% in termination energy and $37$% in switching energy as compared to the state of the art data encoding technique BD-Coder with an average output quality loss of $10$%. 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.