Input-Splitting of Large Neural Networks for Power-Efficient Accelerator with Resistive Crossbar Memory Array

Yulhwa Kim, Hyungjun Kim, Daehyun Ahn, Jae-Joon Kim
{"title":"Input-Splitting of Large Neural Networks for Power-Efficient Accelerator with Resistive Crossbar Memory Array","authors":"Yulhwa Kim, Hyungjun Kim, Daehyun Ahn, Jae-Joon Kim","doi":"10.1145/3218603.3218605","DOIUrl":null,"url":null,"abstract":"Resistive Crossbar memory Arrays (RCA) have been gaining interest as a promising platform to implement Convolutional Neural Networks (CNN). One of the major challenges in RCA-based design is that the number of rows in an RCA is often smaller than the number of input neurons in a layer. Previous works used high-resolution Analog-to-Digital Converters (ADCs) to compute the partial weighted sum in each array and merged partial sums from multiple arrays outside the RCAs. However, such approach suffers from significant power consumption due to the need for high-resolution ADCs. In this paper, we propose a methodology to more efficiently construct a large CNN with multiple RCAs. By splitting the input feature map and retraining the CNN with proper initialization, we demonstrate that any CNN model can be represented with multiple arrays without using intermediate partial sums. The experimental results show that the ADC power of the proposed design is 32x smaller and the total chip power of the proposed design is 3x smaller than those of the baseline design.","PeriodicalId":20456,"journal":{"name":"Proceedings of the 2007 international symposium on Low power electronics and design (ISLPED '07)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"21","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2007 international symposium on Low power electronics and design (ISLPED '07)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3218603.3218605","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 21

Abstract

Resistive Crossbar memory Arrays (RCA) have been gaining interest as a promising platform to implement Convolutional Neural Networks (CNN). One of the major challenges in RCA-based design is that the number of rows in an RCA is often smaller than the number of input neurons in a layer. Previous works used high-resolution Analog-to-Digital Converters (ADCs) to compute the partial weighted sum in each array and merged partial sums from multiple arrays outside the RCAs. However, such approach suffers from significant power consumption due to the need for high-resolution ADCs. In this paper, we propose a methodology to more efficiently construct a large CNN with multiple RCAs. By splitting the input feature map and retraining the CNN with proper initialization, we demonstrate that any CNN model can be represented with multiple arrays without using intermediate partial sums. The experimental results show that the ADC power of the proposed design is 32x smaller and the total chip power of the proposed design is 3x smaller than those of the baseline design.
电阻交叉存储器阵列节能加速器的大神经网络输入分割
电阻交叉棒存储器阵列(RCA)作为实现卷积神经网络(CNN)的一个有前途的平台,已经引起了人们的兴趣。基于RCA设计的主要挑战之一是RCA中的行数通常小于一层中输入神经元的数量。以前的工作使用高分辨率模数转换器(adc)来计算每个阵列中的部分加权和,并合并来自rca外多个阵列的部分和。然而,由于需要高分辨率adc,这种方法的功耗很大。在本文中,我们提出了一种更有效地构建具有多个rca的大型CNN的方法。通过分割输入特征映射并使用适当的初始化对CNN进行重新训练,我们证明了任何CNN模型都可以用多个数组表示,而无需使用中间部分和。实验结果表明,该设计的ADC功耗比基准设计小32倍,芯片总功耗比基准设计小3倍。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信