A longest prefix first search tree for IP lookup

Wuu, Lih‐Chyau; Liu, Tzong-Jye; Chen, Kuo-Ming

doi:10.1016/j.comnet.2007.01.023

Cited by 16 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, due to the rapid growth of network traffic and bandwidth, currently a router becomes a bottleneck for higher link. Therefore, a variety of algorithms have been presented such as LPM, binary trie [6] , level and path compression trie (LC-trie) [7], Binary prefix tree (BPT) [9], priority trie (P-trie) [8], content addressable memories (CAM), ternary content addressable memories (TCAM) [10] and blooming tree (BT) [11] trying to improve the efficiency and speed of the lookup. In addition, [12] gave an outline for those algorithms.…”

Section: A Routing Forward Design Of Netfpga-basedmentioning

confidence: 99%

The Development Status and Trend of NetFPGA

Cao

Zheng

Sun

2015

2015 International Conference on Network and Information Systems for Computers

View full text Add to dashboard Cite

In recent years, with the rapid development of the Internet, ever increasing traffic and link-bandwidths presented serious challenges for computer network-related research such as high-speed algorithm and development of high-performance network equipment. Of course, increasing complication in hardware, firewall filtering and Encryption technology, makes programmability getting more and more attention in switches, routers and other network devices. This paper introduces the development process of NetFPGA, makes a comprehensive summary in the study of high performance network, and describes its advantages in high-speed, parallel and real-time. We present a brief introduction to our current work simultaneously. Finally, the paper points out the NetFPGA development direction and trends in future work.

show abstract

Section: A Routing Forward Design Of Netfpga-basedmentioning

confidence: 99%

The Development Status and Trend of NetFPGA

Cao

Zheng

Sun

2015

2015 International Conference on Network and Information Systems for Computers

View full text Add to dashboard Cite

show abstract

“…Additionally, to compare our algorithms with other solutions, two recent B-tree solutions PIBT [10] and BTLPT [11] and one Trie based solution LPFST [12] were implemented in software for both IP versions IPv4 and IPv6. A simple hardware implementation is also done using FPGA.…”

Section: Software and Hardware Implementationsmentioning

confidence: 99%

“…One of the most recent range-based lookup algorithms is BTLPT [11]. This algorithm uses two structures: a Btree for disjoint prefixes and a Trie based structure called LPFST [12] for the remaining prefixes. Simulation results of [11] show that the performance of BTLPT is better than PIBT in average search and update times and also for the storage requirement.…”

Section: Introductionmentioning

confidence: 99%

IP Lookup Using the Novel Idea of Scalar Prefix Search with Fast Table Updates

Behdadfar

Saidi

Hashemi

et al. 2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYRecently, we have proposed a new prefix lookup algorithm which would use the prefixes as scalar numbers. This algorithm could be applied to different tree structures such as Binary Search Tree and some other balanced trees like RB-tree, AVL-tree and B-tree with minor modifications in the search, insert and/or delete procedures to make them capable of finding the prefixes of an incoming string e.g. an IP address. As a result, the search procedure complexity would be O(log n) where n is the number of prefixes stored in the tree. More important, the search complexity would not depend on the address length w i.e. 32 for IPv4 and 128 for IPv6. Here, it is assumed that interface to memory is wide enough to access the prefix and some simple operations like comparison can be done in O(1) even for the word length w. Moreover, insertion and deletion procedures of this algorithm are much simpler and faster than its competitors. In what follows, we report the software implementation results of this algorithm and compare it with other solutions for both IPv4 and IPv6. It also reports on a simple hardware implementation of the algorithm for IPv4. Comparison results show better lookup and update performances or superior storage requirements for Scalar Prefix Search in both average and worst cases.

show abstract

“…However, its worstcase memory access is so large that many techniques have been incorporated to reduce the height of the trie (like Patricia [6], LC trie [7], LPFST [13] etc). Unfortunately these techniques lead to complicated update, or to memory expansion.…”

Section: Introductionmentioning

confidence: 99%

A hierarchical hashing scheme to accelerate longest prefix matching

Sun

Valgenti³

et al. 2014

2014 IEEE Global Communications Conference

View full text Add to dashboard Cite

Longest Prefix Matching in IP Address lookup remains a bottleneck for high-speed routers where large volumes of traffic at multi-gigabyte link speeds require extremely fast lookup time. By taking advantage of bitmap and hashing techniques effectively used in Tree Bitmap algorithm and Binary hash searching on prefix length algorithm we propose a hierarchical hashing scheme based on observations about prefix length distribution in real routing tables. Theoretical analysis and experiments using real routing tables show that our scheme significantly improve IP lookup efficiency by remarkably reducing the number of memory access, consuming less memory and enabling fast update.

show abstract

A longest prefix first search tree for IP lookup

Cited by 16 publications

References 10 publications

The Development Status and Trend of NetFPGA

The Development Status and Trend of NetFPGA

IP Lookup Using the Novel Idea of Scalar Prefix Search with Fast Table Updates

A hierarchical hashing scheme to accelerate longest prefix matching

Contact Info

Product

Resources

About