基于改进遗传算法的3D NoC测试优化  

Test Optimization of 3D NoC Based on Improved Genetic Algorithm

作　　者：凌景[1] 杨汉生[1] 王静[1] LING Jing;YANG Hansheng;WANG Jing(Chaohu University, Hefei 238000, Chin)

机构地区：[1]巢湖学院,合肥238000

出　　处：《重庆科技学院学报（自然科学版）》2018年第3期44-48,共5页Journal of Chongqing University of Science and Technology：Natural Sciences Edition

基　　金：国家自然科学基金项目"基于NoC重用的三维片上网络测试规划研究"(61561012);巢湖学院校级项目"3D NoC测试调度协同优化研究"(XLY-201705);巢湖学院校级项目"基于概率潮流分析的微网分布式协调控制策略研究"(XLZ-201702)

摘　　要：将云模型与遗传算法相结合对三维片上网络(3D NoC)测试端口进行优化。在测试过程中,重复使用系统本身的硬件资源即重用NoC作为TAM,采用XYZ路由算法,以测试时间为约束函数,采用改进的遗传算法为待测IP核选择合适的调度顺序以获得最短测试时间,提高测试效率。实验结果表明,针对不同规模的3D NoC,使用云模型更新寻优到精英种群后再使用遗传算法更新个体的方法能实现端口的优化,找到最优测试方案,减小测试时间,提高资源利用率。This paper combines the cloud model and genetic algorithm to optimize 3 D NoC test ports. In the process of the test, hardware resources of the NoC system are reused （reusing NoC） as the test access mechanism, and XYZ routing algorithm is adopted. The test time is taken as constraint function, appropriate scheduling order for IP core under improved genetic algorithm is chosen to get the shortest test time and improve test efficiency. The experi- ment results show, for different sizes of 3D NoC, after finding the elite population by using cloud model optimiza- tion, the method of genetic algorithm updating individual can implement port optimization to find the optimal test plan, which can reduce test time and improve resource utilization.

关 键 词：三维片上网络 云模型 遗传算法 端口优化 

分 类 号：TP306[自动化与计算机技术—计算机系统结构]