DL-RSIM: A Reliability and Deployment Strategy Simulation Framework for ReRAM-based CNN Accelerators
Journal
ACM Transactions on Embedded Computing Systems
Journal Volume
21
Journal Issue
3
Date Issued
2022-05-01
Author(s)
Lin, Wei Ting
Cheng, Hsiang Yun
Lin, Meng Yao
Lien, Kai
Hu, Han Wen
Chang, Hung Sheng
Li, Hsiang Pang
Chang, Meng Fan
Tsou, Yen Ting
Nien, Chin Fu
Abstract
Memristor-based deep learning accelerators provide a promising solution to improve the energy efficiency of neuromorphic computing systems. However, the electrical properties and crossbar structure of memristors make these accelerators error-prone. In addition, due to the hardware constraints, the way to deploy neural network models on memristor crossbar arrays affects the computation parallelism and communication overheads. To enable reliable and energy-efficient memristor-based accelerators, a simulation platform is needed to precisely analyze the impact of non-ideal circuit/device properties on the inference accuracy and the influence of different deployment strategies on performance and energy consumption. In this paper, we propose a flexible simulation framework, DL-RSIM, to tackle this challenge. A rich set of reliability impact factors and deployment strategies are explored by DL-RSIM, and it can be incorporated with any deep learning neural networks implemented by TensorFlow. Using several representative convolutional neural networks as case studies, we show that DL-RSIM can guide chip designers to choose a reliability-friendly design option and energy-efficient deployment strategies and develop optimization techniques accordingly.
Subjects
deep learning accelerator | energy efficiency | processing-in-memory | reliability | resistive random access memory | Simulation framework
SDGs
Publisher
ASSOC COMPUTING MACHINERY
Type
journal article