TSGA:新型的片上网络低功耗映射算法

TSGA: novel network-on-chip low power mapping algorithm

针对如何将越来越复杂的应用任务有效地映射到片上网络处理单元上,达到以更少的能耗完成任务的目的,提出了一种遗传算法和禁忌搜索算法相融合的新型片上网路低功耗映射算法。该方法充分利用遗传算法强大的全局搜索能力,融合禁忌搜索的局部搜索能力和突出的翻山特性来弥补遗传算法的局部搜索能力弱和早熟的缺陷,取得了更好的片上网络低功耗效果。实验结果表明,在同样的实验平台和功耗模型下,禁忌搜索遗传算法相比于早期的遗传算法能耗降低显著,相比于后来改进的MGA、AGA算法也有能效优势。

In order to effectively map complex application tasks to the network on chip processing unit and achieve the task with less energy consumption,this paper proposed a novel network on chip mapping algorithm that combined genetic algorithm and tabu search algorithm. The method made full use of the powerful global search ability of the genetic algorithm,and combined the local search ability of the tabu search and the prominent mountain features to compensate for the weak local search ability and premature defects of the genetic algorithm,then achieved a better network on chip low power effect. Under the same experimental platform and power consumption model,compared with the early genetic algorithm,the tabu search genetic algorithm has significant energy efficiency improvement,and it has energy efficiency advantages compared with the later improved MGA and AGA algorithms.