Design and implemetion of DDR2 wrapper for cluster based MPSoC

L. Zhuo, Gaoming Du, Duoli Zhang, Y. Song, Li Li, H. Pan
{"title":"Design and implemetion of DDR2 wrapper for cluster based MPSoC","authors":"L. Zhuo, Gaoming Du, Duoli Zhang, Y. Song, Li Li, H. Pan","doi":"10.1109/ICASID.2010.5551837","DOIUrl":null,"url":null,"abstract":"Network on Chip (NoC) has emerged as a competitive and efficient communication infrastructure for multi-core System on Chip, of which there are three kind of components, processing element(processor, memory, IP, etc), communication element(such as router) and interface module between router and PE. One of the key problems is how to solve the memory bottleneck under the circumstances that multiple processing nodes access memories at the same time. In this paper, a cluster based MPSoC is designed, using Packet Connect Circuit (PCC) rout technique as the inter-cluster communication backbone. And the processing elements are grouped as a cluster, in which there usually consists of several processors and other IPs. Special effort is focused on the DDR2 interface design that can provide memory access through PCC between clusters and off-chip memory. The DDR2 wrapper links a DDR2 SDRAM to one of the router nodes. Dedicate circuit has been designed to meet the frequency changes between the on chip data processing units and the off chip data storage resources. The MPSoC has been implemented in FPGA to verify functionality. The experiment results show that the proposed MPSoC prototype can steadily run at 90 MHz, providing the memory throughput of 2880Mbps.","PeriodicalId":391931,"journal":{"name":"2010 International Conference on Anti-Counterfeiting, Security and Identification","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 International Conference on Anti-Counterfeiting, Security and Identification","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASID.2010.5551837","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Network on Chip (NoC) has emerged as a competitive and efficient communication infrastructure for multi-core System on Chip, of which there are three kind of components, processing element(processor, memory, IP, etc), communication element(such as router) and interface module between router and PE. One of the key problems is how to solve the memory bottleneck under the circumstances that multiple processing nodes access memories at the same time. In this paper, a cluster based MPSoC is designed, using Packet Connect Circuit (PCC) rout technique as the inter-cluster communication backbone. And the processing elements are grouped as a cluster, in which there usually consists of several processors and other IPs. Special effort is focused on the DDR2 interface design that can provide memory access through PCC between clusters and off-chip memory. The DDR2 wrapper links a DDR2 SDRAM to one of the router nodes. Dedicate circuit has been designed to meet the frequency changes between the on chip data processing units and the off chip data storage resources. The MPSoC has been implemented in FPGA to verify functionality. The experiment results show that the proposed MPSoC prototype can steadily run at 90 MHz, providing the memory throughput of 2880Mbps.
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
基于集群的MPSoC DDR2封装器的设计与实现
片上网络(Network on Chip, NoC)是多核片上系统(System on Chip)的一种具有竞争力的高效通信基础设施,它有三种组成部分:处理元件(处理器、存储器、IP等)、通信元件(如路由器)和路由器与片上系统(PE)之间的接口模块。在多个处理节点同时访问内存的情况下,如何解决内存瓶颈是关键问题之一。本文设计了一种基于集群的MPSoC,采用分组连接电路(PCC)路由技术作为集群间通信骨干。处理元素被分组为一个集群,其中通常由几个处理器和其他ip组成。特别的工作集中在DDR2接口设计上,它可以通过PCC在集群和片外存储器之间提供存储器访问。DDR2封装器将DDR2 SDRAM连接到路由器节点之一。为了满足片上数据处理单元与片外数据存储资源之间的频率变化,设计了专用电路。MPSoC已在FPGA中实现以验证功能。实验结果表明,所提出的MPSoC原型可以稳定运行在90 MHz,提供2880Mbps的内存吞吐量。
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
Low-power low-noise CMOS chopper amplifier Homogeneous Markov source information entropy proof based on C-K equation A compact output stage for low-power low-distortion amplifier with diode negative feedback A comparator with flexible programming of the hysteresis Design of elder alarm system based on body posture reorganization
×
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