1 / 18

Large-Scale Wire-Speed Packet Classification on FPGAs

Large-Scale Wire-Speed Packet Classification on FPGAs. Author: Weirong Jiang, Viktor K. Prasanna Publisher: FPGA 2009 Presenter: Chung-Yi Lee. Outline. Architecture and Algorithm Algorithmic Motivations Architecture Overview Algorithm Implementation Experimental Results.

perlaj
Télécharger la présentation

Large-Scale Wire-Speed Packet Classification on FPGAs

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Large-Scale Wire-Speed Packet Classification on FPGAs Author: Weirong Jiang, Viktor K. Prasanna Publisher: FPGA 2009 Presenter: Chung-Yi Lee

  2. Outline • Architecture and Algorithm • Algorithmic Motivations • Architecture Overview • Algorithm • Implementation • Experimental Results

  3. Architecture and Algorithm Algorithmic Motivations HyperCuts algorithm suffers from memory explosion due to rule duplication.

  4. Architecture and Algorithm Algorithmic Motivations 1.Rule overlap reduction R1 R2 R4 R1 Push common rule upwards Rule overlap reduction

  5. Architecture and Algorithm Algorithmic Motivations 2. Precise range cutting

  6. Architecture and Algorithm Architecture Overview

  7. Architecture and Algorithm Algorithm Recursively cut the tree nodes until the number of rule in all the leaf nodes is smaller than a parameter named listsize. Restrict the maximum number of cuts at each node to be 64. Since more bits are needed to store the cut points than to store the number of cuts, we restrict the number of cuts on port fields to be at most 2.

  8. Architecture and Algorithm Algorithm

  9. Architecture and Algorithm Algorithm The memory distribution across stages should be balanced not only for the Tree Pipeline, but also for all the Rule Pipelines. Constraint. If node A is an ancestor of node B in the tree, then A must be mapped to a stage preceding the stage to which B is mapped.

  10. Architecture and Algorithm Algorithm

  11. Architecture and Algorithm Algorithm H =4, listSize =2

  12. Implementation Pipeline for Decision Tree Each node stored in the local memory of a pipeline stage has one extra field: the distance to the pipeline stage where the child node is stored. When a packet is passed through a stage, the distance value is decremented by 1. When the distance value becomes 0, the child node’s address is used to access the memory in that stage.

  13. Implementation

  14. Implementation Pipeline for Rule Lists When a packet accesses the memory in a Tree Pipeline stage, it will obtain the pointer to the rule list associated with the current tree node being accessed.

  15. Implementation Prefix Match Port Match Protocol Match

  16. Experimental Results Performance of algorithms for rule sets of various sizes

  17. Experimental Results Distribution over Tree Pipeline stages for ACL_10K H = 11 listSize = 8

  18. Experimental Results Performance comparison 1258.9

More Related