1. 1 A Novel Scalable IPv6 Lookup Scheme Using Compressed Pipelined Tries Author: Michel Hanna, Sangyeun Cho, and Rami Melhem Publisher: NETWORKING 2011 Presenter: Han-Chen Chen Date: 2011/5/11

2. 2 Introduction  IPv6 packet forwarding  IPv4 trie based packet forwarding algorithms port to IPv6  Trie height  Memory  TCAM  High power consumption  Poor scalability to long IPv6 prefixes  Hash-based hardware engines  Constant search time  Collision chaining causes unbounded memory access time

3. 3 Introduction  The outcome of any IP lookup operation is an interface (or output port) number.  Real-life backbone routers contain a relatively small number of output ports  The routers assign many next hop addresses to one output port.  This means that the number of unique next hop information is greater than the number of output ports.

4. 4 Introduction

5. 5 Multibit trie (a) Multibit trie for Figure 1(a) with strides {3, 2, 2}. (b) Its leaf-pushed trie.

6. 6 Uncompressed multibit trie -2 : with child link -1 : null >0 : port number

7. 7 Compressed multibit trie Inter-Node Compressed TrieUncompressed trieCompressing the leaves

8. 8 Performance Evaluation (1/5) Statistics of IPv6 tables on June 2010. H is the number of output ports.

9. 9 Performance Evaluation (2/5) Number of INCT trie levels vs. total memory (KB) for Linx2 and Eugene1

10. 10 Performance Evaluation (3/5) Memory (KB) of INCT(7) vs. Uncompressed(7) trie

11. 11 Performance Evaluation (4/5) Memory (MB) of Lulea(6)/Tree Bitmap, INCT(6), MIPS(57) and Binary INCT(57). MIPS & Binary INCT {8,1…56} Lulea & INCT {16,16,8,8,8,8}

12. 12 Performance Evaluation (5/5)