基于芯核的SOC测试调度

Test Scheduling for Core-Based SOC

针对大规模SOC的测试问题,基于不同优先级、资源、芯核约束的SOC测试优化模型,引入了SOC测试调度用神经网络, 同时利用试探性随机搜索技术对神经网络进行了改进. 仿真结果表明,采用已改进的神经网络不仅能解决SOC的测试问题,而且能够在一个合理的计算时间内找到最优解,在解决SOC测试调度问题方面具有较优异的性能.

To solve the large size SOC test problems, the modeling of Sytem-On-a-Chip (SOC) test optimization has been formulated with different precedence, resource and core constraints.A neural network for SOC test scheduling is firstly presented,then, a neural network combined with heuristic algorithm has been developed to solve the large size SOC test problems.As demonstrated by the results that computer implement,the developed method can not only solve the large size SOC test problems, but also be capable of finding the optimal solutions within reasonable computing time. As the result shows, it has good performance in solving SOC test scheduling problems.