Abstract:
In this work, we introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. The control variate technique is us...Show MoreMetadata
Abstract:
In this work, we introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. The control variate technique is used in Monte Carlo methods to achieve variance reduction. Our approach significantly decreases the induced error due to approximate multiplications in DNN inference, without requiring time-exhaustive retraining compared to state-of-the-art. Leveraging our control variate method, we use highly approximated multipliers to generate power-optimized DNN accelerators. Our experimental evaluation on six DNNs, for Cifar-10 and Cifar100 datasets, demonstrates that, compared to the accurate design, our control variate approximation achieves same performance and 24% power reduction for a merely 0.16% accuracy loss.
Published in: 2021 58th ACM/IEEE Design Automation Conference (DAC)
Date of Conference: 05-09 December 2021
Date Added to IEEE Xplore: 08 November 2021
ISBN Information:
Print on Demand(PoD) ISSN: 0738-100X