Logo image
A Relaxed Quantization Training Method for Hardware Limitations of Resistive Random-Access Memory (ReRAM)-based Computing-In-Memory
期刊文章   開放取用(OA)

A Relaxed Quantization Training Method for Hardware Limitations of Resistive Random-Access Memory (ReRAM)-based Computing-In-Memory

Wei-Chen Wei, Chuan-Jia Jhang, Yi-Ren Chen, Cheng-Xin Xue, Syuan-Hao Sie, Jye-Luen Lee, Hao-Wen Kuo, Chih-Cheng Lu, Meng-Fan ChangKea-Tiong Tang
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
2020

摘要

Compression Computing In-memory Deep Learning Quantization Resistive RAM Electronic Optical and Magnetic Materials Hardware and Architecture Electrical and Electronic Engineering
Nonvolatile computing-in-memory (nvCIM) exhibits high potential for neuromorphic computing involving massive parallel computations and for achieving high energy efficiency. nvCIM is especially suitable for deep neural networks, which are required to perform large amounts of matrix&null multiplications. However, a comprehensive quantization algorithm has yet to be developed that overcomes the hardware limitations of ReRAM-based nvCIM, such as the number of I/O, word lines (WL), and ADC outputs. In this paper, we propose a quantization training method for compressing deep models. The method comprises three steps: input and weight quantization, ReRAM convolution (ReConv), and ADC quantization. ADC quantization optimizes the error sampling problem by using the Gumbel-softmax trick. Under a 4-bit ADC of nvCIM, the accuracy only decreases by 0.05% and 1.31% for the MNIST and CIFAR-10 respectively, compared with the corresponding accuracies obtained under an ideal ADC. The experimental results indicate that the proposed method is effective for compensating the hardware limitations of nvCIM macros.

檔案與連結 (1)

url
https://doi.org/10.1109/JXCDC.2020.2992306檢視
已出版(紀錄版本) 開放

相關連結

指標

1 檢視次數

詳細資料

Logo image