IETCAM:基于信息熵的低功耗TCAM分类器

IETCAM:low power TCAM classifier based on information entropy

目前,三态内容寻址器被广泛应用于数据平面的高速转发,但现有的索引式TCAM在降低功耗和运行时间等方面仍存在问题。针对这些不足,提出了一种基于信息熵的低功耗索引式TCAM分类器,利用了信息熵技术,有效地解决了规则集在TCAM子块中分布不均、功耗较大的问题。实验表明,在2k大小的规则集下,该算法相较于经典的SmartPC算法平均可以提高63%的功耗降低率,运算时间更新速度缩小了97%,存储开销仅增加了10%。

At present,the ternary content addresser is widely used in high-speed forwarding of the data plane.However,the existing indexed TCAM still has some problems in reducing power consumption and running time.This paper proposed a low-power index TCAM classifier based on information entropy to solve this problem.Information entropy technology effectively solved the problem of uneven distribution of rule sets in TCAM sub blocks and high power consumption.Experimental results show that,compared with the classic SmartPC algorithm,the proposed algorithm can improve the power consumption reduction rate by 63%,reduce the update speed by 97%and increase the storage cost by 10%in 2k rule set.