基于比较诊断模型的超立方网络诊断算法  

Hypercube Network Diagnosis Algorithm under Comparison Model

作　　者：陈秒江 梁家荣[1] 张乾[1] 

机构地区：[1]广西大学计算机与电子信息学院,南宁530004

出　　处：《计算机科学》2017年第6期85-90,共6页Computer Science

基　　金：国家自然科学基金项目:新型互连网络的嵌入性与容错性研究(61364002)资助

摘　　要：一个有效的诊断算法对多处理器系统而言极其重要。在多处理器系统中,识别所有故障节点的能力称为诊断系统的诊断度。在比较模型下,诊断的执行是通过一个比较器处理器,给与之相邻的一对处理器发送相同的输入信号,并比较两者间的响应状态。为了提高超立方网络的诊断度,提出了一种新型的基于比较模型的超立方故障诊断算法,其利用超立方网络节点连接的特性生成一个拓扑图ES(k;n),最终得出一个3位二进制的诊断症候集,从而确定系统故障节点。该算法的诊断度最优能达到4n,大于传统超立方的诊断度n。An efficient diagnosis is very important for a multiprocessor system.The ability to identify all the faulty nodes in a multiprocessor system is known as diagnosability.In the comparison model,the diagnosis is performed by sending two identical signals from a processor to a pair of distinct neighbors,and comparising the responses.To improve the diagnosability of hypercube network,we presented a novel hypercube network algorithm under the comparison model,which uses the characteristic of the hypercube links to produce a topology netword ES（k;n）and obtains a three-binary diagnosis syndrome to determine the fault node of the system.In the optimal conditions,the diagnosability of algorithm is 4n,which is bigger than its ordinary diagnosability n.

关 键 词：故障诊断 比较诊断模型 超立方网络 系统级诊断 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]