版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:Texas Instruments Inc Kilby Labs Dallas TX 75243 USA MIT Dept Elect Engn & Comp Sci Cambridge MA 02139 USA
出 版 物:《IEEE JOURNAL OF SOLID-STATE CIRCUITS》 (IEEE J Solid State Circuits)
年 卷 期:2019年第54卷第1期
页 面:217-230页
核心收录:
主 题:Analog computing binary weights convolutional neural networks (CNNs) dot-product edge-computing energy-efficient SRAM in-memory computation machine learning (ML)
摘 要:This paper presents an energy-efficient static random access memory (SRAM) with embedded dot-product computation capability, for binary-weight convolutional neural networks. A 10T bit-cell-based SRAM array is used to store the 1-b filter weights. The array implements dot-product as a weighted average of the bitline voltages, which are proportional to the digital input values. Local integrating analogto- digital converters compute the digital convolution outputs, corresponding to each filter. We have successfully demonstrated functionality ( 98% accuracy) with the 10 000 test images in the MNIST hand-written digit recognition data set, using 6-b inputs/outputs. Compared to conventional full-digital implementations using small bitwidths, we achieve similar or better energy efficiency, by reducing data transfer, due to the highly parallel in-memory analog computations.