Litcius/Paper detail

AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorch

Dimitrios Danopoulos, Georgios Zervakis, Kostas Siozios, Dimitrios Soudris, Jörg Henkel

2022IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems46 citationsDOI

Abstract

Current state-of-the-art employs approximate multipliers to address the highly increased power demands of deep neural network (DNN) accelerators. However, evaluating the accuracy of approximate DNNs is cumbersome due to the lack of adequate support for approximate arithmetic in DNN frameworks. We address this inefficiency by presenting AdaPT, a fast emulation framework that extends PyTorch to support approximate inference as well as approximation-aware retraining. AdaPT can be seamlessly deployed and is compatible with the most DNNs. We evaluate the framework on several DNN models and application fields, including CNNs, LSTMs, and GANs for a number of approximate multipliers with distinct bitwidth values. The results show substantial error recovery from approximate retraining and reduced inference time up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$53.9 \times $ </tex-math></inline-formula> with respect to the baseline approximate implementation.

Topics & Concepts

EmulationComputer scienceArtificial intelligenceDeep learningParallel computingComputational sciencePsychologySocial psychologyParticle Detector Development and PerformanceRadiation Effects in ElectronicsParticle accelerators and beam dynamics