首页> 外文OA文献 >Design and Implementation of Multistage Interconnection Networks for SoC Networks
【2h】

Design and Implementation of Multistage Interconnection Networks for SoC Networks

机译:soC多级互连网络的设计与实现   网络

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

In this paper the focus is on a family of Interconnection Networks (INs)known as Multistage Interconnection Networks (MINs). When it is exploited inNetwork-on-Chip (NoC) architecture designs, smaller circuit area, lower powerconsumption, less junctions and broader bandwidth can be achieved. Each MIN canbe considered as an alternative for an NoC architecture design for its simpletopology and easy scalability with low degree. This paper includes two majorcontributions. First, it compares the performance of seven prominent MINs (i.e.Omega, Butterfly, Flattened Butterfly, Flattened Baseline, Generalized Cube,Bene\v{s} and Clos networks) based on 45nm-CMOS technology and under differenttypes of Synthetic and Trace-driven workloads. Second, a network calledMeta-Flattened Network (MFN), was introduced that can decrease the blockingprobability by means of reduction the number of hops and increase theintermediate paths between stages. This is also led into significant decreasein power consumption.
机译:在本文中,重点是称为多级互连网络(MIN)的互连网络(IN)系列。在片上网络(NoC)架构设计中加以利用时,可以实现更小的电路面积,更低的功耗,更少的结点和更宽的带宽。每个MIN都可以认为是NoC架构设计的替代方案,因为它的拓扑简单且易于扩展且具有低程度。本文包括两个主要贡献。首先,它比较了基于45nm-CMOS技术以及在不同类型的合成驱动和跟踪驱动下的七个主要MIN(即,Omega,Butterfly,Blattened Butterfly,Blattened Baseline,Generalized Cube,Bene \ v {s}和Clos网络)的性能。工作量。其次,引入了一种称为元扁平化网络(MFN)的网络,该网络可以通过减少跳数和增加级之间的中间路径来降低阻塞概率。这也导致功耗的显着降低。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号