未来多核可扩展纳米光子互连设计

Avinash Karanth Kodi, R. Morris
{"title":"未来多核可扩展纳米光子互连设计","authors":"Avinash Karanth Kodi, R. Morris","doi":"10.1145/1882486.1882516","DOIUrl":null,"url":null,"abstract":"As communication-centric computing paradigm gathers momentum due to increased wire delays and excess power dissipation with technology scaling, researchers have focused their attention on developing alternate technology solutions for Network-on-Chips (NoCs) architectures. One potential solution is nanophotonics because of higher bandwidth, reduced power dissipation and increased wiring simplification. In this paper, we propose PROPEL, a balanced power and area-efficient on-chip photonic interconnect for future multicores. PROPEL overcomes two fundamental issues facing NoCs architectures, namely power dissipation and area overhead, by a combination of multiplexing techniques (wave-length and space) and by exploiting the recent advances in optical component design space. We also propose a scalable version of PROPEL, called E-PROPEL which can scale to 256 cores. Our results indicate that PROPEL and E-PROPEL are power, cost and area-effective networks when compared to competing on-chip optical topologies when the number of optical components and overall power loss in the network are considered. Simulation results on synthetic traffic indicate that PROPEL performs better (throughput and power) than electrical and optical topologies.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"49 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Design of a scalable nanophotonic interconnect for future multicores\",\"authors\":\"Avinash Karanth Kodi, R. Morris\",\"doi\":\"10.1145/1882486.1882516\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As communication-centric computing paradigm gathers momentum due to increased wire delays and excess power dissipation with technology scaling, researchers have focused their attention on developing alternate technology solutions for Network-on-Chips (NoCs) architectures. One potential solution is nanophotonics because of higher bandwidth, reduced power dissipation and increased wiring simplification. In this paper, we propose PROPEL, a balanced power and area-efficient on-chip photonic interconnect for future multicores. PROPEL overcomes two fundamental issues facing NoCs architectures, namely power dissipation and area overhead, by a combination of multiplexing techniques (wave-length and space) and by exploiting the recent advances in optical component design space. We also propose a scalable version of PROPEL, called E-PROPEL which can scale to 256 cores. Our results indicate that PROPEL and E-PROPEL are power, cost and area-effective networks when compared to competing on-chip optical topologies when the number of optical components and overall power loss in the network are considered. Simulation results on synthetic traffic indicate that PROPEL performs better (throughput and power) than electrical and optical topologies.\",\"PeriodicalId\":329300,\"journal\":{\"name\":\"Symposium on Architectures for Networking and Communications Systems\",\"volume\":\"49 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-10-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Symposium on Architectures for Networking and Communications Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/1882486.1882516\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Symposium on Architectures for Networking and Communications Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1882486.1882516","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

摘要

随着以通信为中心的计算范式随着技术扩展而增加的线延迟和过剩的功耗而积聚势头,研究人员将注意力集中在开发片上网络(noc)架构的替代技术解决方案上。一个潜在的解决方案是纳米光子学,因为它具有更高的带宽、更低的功耗和更简单的布线。在本文中,我们提出了一种用于未来多核的平衡功率和面积效率的片上光子互连。PROPEL通过结合多路复用技术(波长和空间)以及利用光学元件设计空间的最新进展,克服了noc架构面临的两个基本问题,即功耗和面积开销。我们还提出了一个可扩展版本的PROPEL,称为E-PROPEL,可以扩展到256核。我们的研究结果表明,当考虑光器件数量和网络中的总功耗损失时,与竞争的片上光拓扑相比,PROPEL和E-PROPEL是功率,成本和面积有效的网络。综合流量的仿真结果表明,PROPEL拓扑在吞吐量和功耗方面都优于电拓扑和光拓扑。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Design of a scalable nanophotonic interconnect for future multicores
As communication-centric computing paradigm gathers momentum due to increased wire delays and excess power dissipation with technology scaling, researchers have focused their attention on developing alternate technology solutions for Network-on-Chips (NoCs) architectures. One potential solution is nanophotonics because of higher bandwidth, reduced power dissipation and increased wiring simplification. In this paper, we propose PROPEL, a balanced power and area-efficient on-chip photonic interconnect for future multicores. PROPEL overcomes two fundamental issues facing NoCs architectures, namely power dissipation and area overhead, by a combination of multiplexing techniques (wave-length and space) and by exploiting the recent advances in optical component design space. We also propose a scalable version of PROPEL, called E-PROPEL which can scale to 256 cores. Our results indicate that PROPEL and E-PROPEL are power, cost and area-effective networks when compared to competing on-chip optical topologies when the number of optical components and overall power loss in the network are considered. Simulation results on synthetic traffic indicate that PROPEL performs better (throughput and power) than electrical and optical topologies.
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
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