Multistage Sorting Module With VCSEL Based Free-space Optical Interconnects

F. Sauer, N. Craft, D. Guise, J. Avins, M. LaValva, J. Turlip
{"title":"Multistage Sorting Module With VCSEL Based Free-space Optical Interconnects","authors":"F. Sauer, N. Craft, D. Guise, J. Avins, M. LaValva, J. Turlip","doi":"10.1109/LEOSST.1994.700479","DOIUrl":null,"url":null,"abstract":"Free-space optical ir erconnects promise highly parallel implementations of multistage interconnection networks (MINs) for sorting and switching applications. The largest network demonstrated so far [ l ] had 1,024 channels in parallel, ran at a clock rate of 100 kHz, and was based on SEED devices [2]. The practical difficulties associated with the employment of SEED devices (tight wavelength and temperature tolerances, complex optical systems for the modulator type devices) motivate us to investigate the use of active light emitting devices. In particular, the novel vertical cavity surface emitting laser (VCSEL) [3] is a promising candidate for free-space optical interconnects. In this paper, we present the first demonstration of a MIN which employs VCSEL based optical interconnects. Figure 1 shows schematically the MIN we have implemented. Six switching stages, each consisting of four parallel 2x2 crossbar switching nodes, are interconnected in a non-local way. In our system, the numbers to be sorted are represented in binary format and are synchronously fed into the network with most significant bits leading. The control of the network is distributed. Each node compares the two numbers arriving at its input ports in a bitsequential way and routes the greater number through the upper, the smaller number through the lower output port [4]. From another point of view, the network performs a core function of a self-routing packet switch. The network sorts according to the leading bits (address headers), and it delivers the trailing bits (payloads) to the corresponding destination ports.","PeriodicalId":379594,"journal":{"name":"Proceedings of IEE/LEOS Summer Topical Meetings: Integrated Optoelectronics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of IEE/LEOS Summer Topical Meetings: Integrated Optoelectronics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/LEOSST.1994.700479","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Free-space optical ir erconnects promise highly parallel implementations of multistage interconnection networks (MINs) for sorting and switching applications. The largest network demonstrated so far [ l ] had 1,024 channels in parallel, ran at a clock rate of 100 kHz, and was based on SEED devices [2]. The practical difficulties associated with the employment of SEED devices (tight wavelength and temperature tolerances, complex optical systems for the modulator type devices) motivate us to investigate the use of active light emitting devices. In particular, the novel vertical cavity surface emitting laser (VCSEL) [3] is a promising candidate for free-space optical interconnects. In this paper, we present the first demonstration of a MIN which employs VCSEL based optical interconnects. Figure 1 shows schematically the MIN we have implemented. Six switching stages, each consisting of four parallel 2x2 crossbar switching nodes, are interconnected in a non-local way. In our system, the numbers to be sorted are represented in binary format and are synchronously fed into the network with most significant bits leading. The control of the network is distributed. Each node compares the two numbers arriving at its input ports in a bitsequential way and routes the greater number through the upper, the smaller number through the lower output port [4]. From another point of view, the network performs a core function of a self-routing packet switch. The network sorts according to the leading bits (address headers), and it delivers the trailing bits (payloads) to the corresponding destination ports.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于VCSEL的自由空间光互连多级分选模块
自由空间光互连为分类和交换应用提供了多级互连网络(MINs)的高度并行实现。迄今为止演示的最大的网络[1]有1024个并行通道,以100 kHz的时钟速率运行,并基于SEED设备[2]。与使用SEED器件相关的实际困难(严格的波长和温度公差,调制器类型器件的复杂光学系统)促使我们研究主动发光器件的使用。特别是,新型垂直腔面发射激光器(VCSEL)[3]是自由空间光互连的一个有前途的候选者。在本文中,我们首次展示了采用基于VCSEL的光互连的MIN。图1显示了我们实现的MIN的示意图。6个交换级,每个交换级由4个并联的2x2交叉交换节点组成,以非本地方式互连。在我们的系统中,要排序的数字以二进制格式表示,并以最高有效位为先导同步输入网络。网络的控制是分布式的。每个节点以位顺序的方式比较到达其输入端口的两个数字,并将较大的数字通过上输出端口,较小的数字通过下输出端口[4]。从另一个角度来看,网络执行自路由分组交换机的核心功能。网络根据前导位(地址报头)进行排序,并将尾随位(有效载荷)传递到相应的目的端口。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Adaptive Attenuating Spatial Light Modulator MOVPE Growth Chamber Pressure Influence In Si Doping Of InP And InGaAs 10 Gb/s Manolithically Integrated Pin-MEMT Receiver OEIC: Realization And Comparison Of Different Circuit Concepts Semiconductor Guided-wave Switching For Optical Networks Ultra-fast Clock Recovery And Subcarrier-based Signaling Technique For Optical Packet Switched Networks
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1