A Novel Encoding Scheme for Low Power in Network on Chip Links

Deepa N. Sarma, G. Lakshminarayanan, K. Chavali
{"title":"A Novel Encoding Scheme for Low Power in Network on Chip Links","authors":"Deepa N. Sarma, G. Lakshminarayanan, K. Chavali","doi":"10.1109/VLSID.2012.80","DOIUrl":null,"url":null,"abstract":"Dynamic power dissipation in interconnects is a major contributor to power consumption in Network on Chips (NoCs). This is mainly due to two factors, self switching activity of the particular link and coupling switching activity among adjacent links. Two novel techniques are proposed to reduce power consumption due to switching transition and cross talk. First technique reorders the data in such a way that switching transition is brought down. In the second technique, it is ensured that power consumption due to cross coupling activity is reduced. An end to end encoding scheme facilitating two stage coding to reduce power consumption in wormhole routed network on chip is designed using the proposed power reduction techniques. Encoder and Decoder exhibiting the proposed scheme have been described in RTL level in Verilog HDL, synthesized and mapped into UMC180 nm technology library. It has been observed that the proposed technique (TSC) offers an average reduction in dynamic power consumption of 17.34%. Proposed scheme was compared with existing techniques and observations concluded that there was not much degradation in area, speed and static power dissipation. Power reduction when subjected to different kinds of data streams was analyzed and results indicate that proposed scheme offers uniform power reduction irrespective of the nature of data stream unlike the existing techniques.","PeriodicalId":405021,"journal":{"name":"2012 25th International Conference on VLSI Design","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 25th International Conference on VLSI Design","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VLSID.2012.80","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

Dynamic power dissipation in interconnects is a major contributor to power consumption in Network on Chips (NoCs). This is mainly due to two factors, self switching activity of the particular link and coupling switching activity among adjacent links. Two novel techniques are proposed to reduce power consumption due to switching transition and cross talk. First technique reorders the data in such a way that switching transition is brought down. In the second technique, it is ensured that power consumption due to cross coupling activity is reduced. An end to end encoding scheme facilitating two stage coding to reduce power consumption in wormhole routed network on chip is designed using the proposed power reduction techniques. Encoder and Decoder exhibiting the proposed scheme have been described in RTL level in Verilog HDL, synthesized and mapped into UMC180 nm technology library. It has been observed that the proposed technique (TSC) offers an average reduction in dynamic power consumption of 17.34%. Proposed scheme was compared with existing techniques and observations concluded that there was not much degradation in area, speed and static power dissipation. Power reduction when subjected to different kinds of data streams was analyzed and results indicate that proposed scheme offers uniform power reduction irrespective of the nature of data stream unlike the existing techniques.
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
一种基于片上链路的低功耗网络编码方案
互连中的动态功耗是片上网络(noc)功耗的主要贡献者。这主要是由两个因素造成的,一是特定环节的自交换活动,二是相邻环节之间的耦合交换活动。提出了两种新的技术来降低由于切换转换和串扰造成的功耗。第一种技术是对数据重新排序,使切换转换降低。在第二种技术中,可以确保减少由于交叉耦合活动而导致的功耗。利用所提出的降功耗技术,设计了一种端到端编码方案,实现了两级编码,从而降低了片上虫洞路由网络的功耗。采用该方案的编码器和解码器在Verilog HDL语言中进行了RTL级描述,合成并映射到umc180nm技术库中。据观察,提出的技术(TSC)提供了17.34%的动态功耗平均降低。将该方案与现有技术进行了比较,结果表明该方案在面积、速度和静态功耗方面没有太大的下降。对不同类型数据流下的功耗降低进行了分析,结果表明,与现有技术不同,所提出的方案无论数据流的性质如何,都能提供均匀的功耗降低。
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
Two Graph Based Circuit Simulator for PDE-Electrical Analogy Tutorial T8A: Designing Silicon-Photonic Communication Networks for Manycore Systems Efficient Online RTL Debugging Methodology for Logic Emulation Systems Low-Overhead Maximum Power Point Tracking for Micro-Scale Solar Energy Harvesting Systems A Framework for TSV Serialization-aware Synthesis of Application Specific 3D Networks-on-Chip
×
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