Litcius/Paper detail

ProxSim: GPU-based Simulation Framework for Cross-Layer Approximate DNN Optimization

Cecilia De la Parra, Andre Guntoro, Akash Kumar

202037 citationsDOI

Abstract

Through cross-layer approximation of Deep Neural Networks (DNN) significant improvements in hardware resources utilization for DNN applications can be achieved. This comes at the cost of accuracy degradation, which can be compensated through different optimization methods. However, DNN optimization is highly time-consuming in existing simulation frameworks for cross-layer DNN approximation, as they are usually implemented for CPU usage only. Specially for large-scale image processing tasks, the need of a more efficient simulation framework is evident. In this paper we present ProxSim, a specialized, GPU-accelerated simulation framework for approximate hardware, based on Tensorflow, which supports approximate DNN inference and retraining. Additionally, we propose a novel hardware-aware regularization technique for approximate DNN optimization. By using ProxSim, we report up to 11× savings in execution time, compared to a multi-thread CPU-based framework, and an accuracy recovery of up to 30% for three case studies of image classification with MNIST, CIFAR-10 and ImageNet.

Topics & Concepts

MNIST databaseComputer scienceArtificial neural networkDeep neural networksInferenceRegularization (linguistics)Computer engineeringArtificial intelligenceParallel computingAdvanced Neural Network ApplicationsAdversarial Robustness in Machine LearningDomain Adaptation and Few-Shot Learning