ACIMS: Analog CIM Simulator for DNN Resilience

Dong Ding,Hongjun He,Kai Hu,Lei Wang,Zhijie Yang

doi:10.3390/electronics10060686

Abstract

Analog Computing In Memory (ACIM) combines the advantages of both Compute In Memory (CIM) and analog computing, making it suitable for the design of energy-efficient hardware accelerators for computationally intensive DNN applications. However, their use will introduce hardware faults that decrease the accuracy of DNN. In this work, we take Sandwich-Ram as the real hardware example of ACIM and are the first to propose a fault injection and fault-aware training framework for it, named Analog Computing In Memory Simulator (ACIMS). Using this framework, we can simulate and repair the hardware faults of ACIM. The experimental results show that ACIMS can recover 91.0%, 93.7% and 89.8% of the DNN’s accuracy drop through retraining on the MNIST, SVHN and Cifar-10 datasets, respectively; moreover, their adjusted accuracy can reach 97.0%, 95.3% and 92.4%.

Highlights

Recent hardware development in the field of deep learning has exhibited a migration from general-purpose designs to more specialized hardware in order to improve the computational efficiency
Given a dataset and DNN model, Analog CIM Simulator (ACIMS) will go through two stages of training and obtain three test accuracies
In the first training stage, ACIMS trains the original model and obtains the first test accuracy, GoldenAcc, which is taken as a baseline

Summary

Introduction

Recent hardware development in the field of deep learning has exhibited a migration from general-purpose designs to more specialized hardware in order to improve the computational efficiency. Analog computing utilizes continuous physical quantities such as voltage, current, frequency and pulse-width. Both CIM and analog computing speed up the DNN algorithm; they reduce the DNN’s reliability. Analog computing has an inherent random error and a low noise margin, both factors that significantly reduce the resilience of DNN. We suppose that ACIM error has a certain mathematical expression so that DNN can adapt the error as well as to accomplish classification. This ability is the DNN’s inherent resilience, as discussed in previous works (e.g., [7])

Objectives

Results

Conclusion