PRDT(2,1)架构的NoC系统容错路由算法  

Fault-tolerant routing algorithm for PRDT(2,1)——based NoCs

作　　者：段新明[1] 潮升 武继刚[1] 

机构地区：[1]天津工业大学计算机科学与软件学院,天津300387

出　　处：《计算机工程与应用》2015年第3期89-92,147,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60970016)

摘　　要：链路和节点的故障会导致网络中许多节点无法相互通讯,因此容错性是NoC系统设计中的一个重要问题。基于一种新的NoC网络拓扑结构PRDT(2,1),提出一种PRDT(2,1)容错路由算法以及相应的节点失效算法。节点失效算法通过使较少数量的无故障节点失效来构造矩形故障区域,PRDT(2,1)容错路由算法仅使用了最小数量的虚拟通道并提供足够的自适应性以实现无死锁容错路由。只要故障区域没有断开网络,这一算法能够保证路由的连通性。算法在不同故障率的PRDT(2,1)网络中仿真,结果显示这一算法具有良好的平滑降级使用特性。Fault tolerance is a dominant issue facing the design of No C systems, since faulty links or nodes may isolate a large fraction of nodes. Based on a novel network topology PRDT（2,1）, a new fault tolerant routing algorithm and a corresponding node deactivated scheme are presented. The node deactivated scheme converts fault regions into rectangular in shape without disabling a large number of non-faulty nodes. The proposed routing algorithm only employs as few virtual channels as possible and provides enough adaptability for deadlock-free fault-tolerance routing. Messages can certainly be routed from a source node to a destination node unless fault regions physically disconnect the network. The result of simulation shows the feasibility of gracefully degraded operation for the proposed algorithm.

关 键 词：PRDT(2 1)构架 路由算法 无死锁 容错 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]