功耗优化的片上网络协同映射  

Co-mapping Algorithm for Network on Chip with Optimal Power Consumption

作　　者：葛芬[1] 吴宁[1] 

机构地区：[1]南京航空航天大学信息科学与技术学院,江苏南京210016

出　　处：《应用科学学报》2008年第6期606-612,共7页Journal of Applied Sciences

基　　金：江苏省自然科学基金(No.BK2008387);江苏省研究生创新基金(No.cx07B_105z)资助项目

摘　　要：通过分析片上网络功耗模型和映射流程,提出了一种基于遗传算法的片上网络协同映射算法,使片上网络通讯功耗最小化.该算法结合IP核选择和任务分配实现IP核在片上网络体系结构中的自动映射,并采用多组随机基准实验和一个复杂视频/音频系统验证了算法性能.实验结果表明,该协同映射算法与已有的两步式映射和仅有IP核映射算法相比,分别可节省30%和60%左右的通讯功耗.Based on analysis of Network on Chip （NoC） power model and mapping flow, a co-mapping algorithm based on genetic algorithm is proposed to minimize total communication power consumption. The algorithm automatically maps IP cores onto the NoC architecture combining IP selection and task assignment. Experiments are performed on various random benchmarks and a complex video/audio application to conform efficiency of the algorithm. The results show that the proposed algorithm saves on average 30% and 60% of power consumption, respectively, compared to the existing two-step mapping and the IP core-only mapping algorithms.

关 键 词：片上系统 片上网络 映射 功耗 遗传算法 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]