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.
出处
《计算机科学》
CSCD
北大核心
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
关键词
故障诊断
比较诊断模型
超立方网络
系统级诊断
Fault diagnosis
Comparison diagnosis model
Hypercube network
System-level diagnosis
