The problem that sequential decomposition tries to solve in this chapter can be stated intuitively as follows: how can we squeeze the most information possible into TCAM chips with little or no performance loss? Solving this problem helps to address almost all limitations of TCAMs. Given a packet classifier, if we can represent it using fewer bits, we can use a smaller TCAM chip, which will result in lower power consumption, less heat generation, less board space, and lower hardware cost. Furthermore, reducing the number of TCAM rules results in less power consumption and heat generation because the energy consumed by a TCAM grows linearly with the number of ternary rules it stores [Yu et al(2005)Yu, Lakshman, Motoyama, and Katz].
KeywordsOutgoing Edge Packet Processing Packing Approach Nonterminal Node Packing Scheme
Unable to display preview. Download preview PDF.