A Family Of Reconfigurable Neurocomputers For The "Intelligent Factory"

S. Erdogan, A. Wahab
{"title":"A Family Of Reconfigurable Neurocomputers For The \"Intelligent Factory\"","authors":"S. Erdogan, A. Wahab","doi":"10.1109/ETFA.1992.683282","DOIUrl":null,"url":null,"abstract":"The neural network simulation plallorm provided by a family of Reconfigurable Machines (RM) suitable for massively parallel computations is presented in this paper. The RM family of neurocomputers range from a single board system capable (of providing supercomputer power to more elaborate systems suitable for very complex real time neural computation. The major architectural breakthrough in the design of RM neurocomputers is the fact that a completely reconfigurable platform, not only in the domain of communications and control but also in the domain of processing elements, is provided. Another contribution is the implementation of a last floating point sum of products circuit which uses special carry-save multipliers and extensive pipelining.","PeriodicalId":154369,"journal":{"name":"IEEE International Workshop on Emerging Technologies and Factory Automation,","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE International Workshop on Emerging Technologies and Factory Automation,","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ETFA.1992.683282","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

The neural network simulation plallorm provided by a family of Reconfigurable Machines (RM) suitable for massively parallel computations is presented in this paper. The RM family of neurocomputers range from a single board system capable (of providing supercomputer power to more elaborate systems suitable for very complex real time neural computation. The major architectural breakthrough in the design of RM neurocomputers is the fact that a completely reconfigurable platform, not only in the domain of communications and control but also in the domain of processing elements, is provided. Another contribution is the implementation of a last floating point sum of products circuit which uses special carry-save multipliers and extensive pipelining.
面向“智能工厂”的可重构神经计算机系列
本文介绍了一种适用于大规模并行计算的可重构机(RM)系列提供的神经网络仿真平台。RM系列神经计算机的范围从能够提供超级计算机能力的单板系统到适合非常复杂的实时神经计算的更复杂的系统。RM神经计算机设计的主要架构突破是提供了一个完全可重构的平台,不仅在通信和控制领域,而且在处理元素领域。另一个贡献是实现了最后一个浮点乘积和电路,它使用了特殊的进位节省乘法器和广泛的流水线。
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