NERO掌握了30万个CNN细胞

2013 European Conference on Circuit Theory and Design (ECCTD) Pub Date : 2013-11-14 DOI:10.1109/ECCTD.2013.6662202

R. Braunschweig, Jens Müller, Jan Müller, R. Tetzlaff

{"title":"NERO掌握了30万个CNN细胞","authors":"R. Braunschweig, Jens Müller, Jan Müller, R. Tetzlaff","doi":"10.1109/ECCTD.2013.6662202","DOIUrl":null,"url":null,"abstract":"A novel massively-parallel fine-grain architecture featuring a digital emulation of Cellular Nonlinear Networks (CNN) is presented. A virtual cellular network is processed line-by-line by a locally connected linear array of processing elements. The resulting computing system is able to execute complex CNN program code consisting of consecutive operations. Furthermore we present a scalable FPGA implementation of this architecture for currently up to 480 × 640 cells with a precision up to 18 bit.","PeriodicalId":342333,"journal":{"name":"2013 European Conference on Circuit Theory and Design (ECCTD)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"NERO mastering 300k CNN cells\",\"authors\":\"R. Braunschweig, Jens Müller, Jan Müller, R. Tetzlaff\",\"doi\":\"10.1109/ECCTD.2013.6662202\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A novel massively-parallel fine-grain architecture featuring a digital emulation of Cellular Nonlinear Networks (CNN) is presented. A virtual cellular network is processed line-by-line by a locally connected linear array of processing elements. The resulting computing system is able to execute complex CNN program code consisting of consecutive operations. Furthermore we present a scalable FPGA implementation of this architecture for currently up to 480 × 640 cells with a precision up to 18 bit.\",\"PeriodicalId\":342333,\"journal\":{\"name\":\"2013 European Conference on Circuit Theory and Design (ECCTD)\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-11-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 European Conference on Circuit Theory and Design (ECCTD)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ECCTD.2013.6662202\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 European Conference on Circuit Theory and Design (ECCTD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ECCTD.2013.6662202","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 12

摘要

提出了一种具有数字仿真细胞非线性网络(CNN)的新型大规模并行细粒度架构。虚拟蜂窝网络由本地连接的处理单元线性阵列逐行处理。由此产生的计算系统能够执行由连续操作组成的复杂CNN程序代码。此外，我们提出了一种可扩展的FPGA实现该架构，目前可用于高达480 × 640个单元，精度高达18位。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

NERO mastering 300k CNN cells

A novel massively-parallel fine-grain architecture featuring a digital emulation of Cellular Nonlinear Networks (CNN) is presented. A virtual cellular network is processed line-by-line by a locally connected linear array of processing elements. The resulting computing system is able to execute complex CNN program code consisting of consecutive operations. Furthermore we present a scalable FPGA implementation of this architecture for currently up to 480 × 640 cells with a precision up to 18 bit.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2013 European Conference on Circuit Theory and Design (ECCTD)

自引率

0.00%

发文量