SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.13977 · 2020

Bit Error Robustness for Energy-Efficient DNN Accelerators

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep neural network (DNN) accelerators received considerable attention in past years due to saved energy compared to mainstream hardware. Low-voltage operation of DNN accelerators allows to further reduce energy consumption significantly, however, causes bit-level failures in the memory storing the quantized DNN weights. In this paper, we show that a combination of robust fixed-point quantization, weight clipping, and random bit error training (RandBET) improves robustness against random bit errors in (quantized) DNN weights significantly. This leads to high energy savings from both low-voltage operation as well as low-precision quantization. Our approach generalizes across operating voltages and accelerators, as demonstrated on bit errors from profiled SRAM arrays. We also discuss why weight clipping alone is already a quite effective way to achieve robustness against bit errors. Moreover, we specifically discuss the involved trade-offs regarding accuracy, robustness and precision: Without losing more than 1% in accuracy compared to a normally trained 8-bit DNN, we can reduce energy consumption on CIFAR-10 by 20%. Higher energy savings of, e.g., 30%, are possible at the cost of 2.5% accuracy, even for 4-bit DNNs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.13977")
get_code_for_paper("2006.13977")
have("2006.13977")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.13977.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.13977.svg)](https://syntology.ai/paper/2006.13977)

Connect an agent — have() is free.