首页> 外文会议>IEEE Region 10 Conference >A hash based architecture of longest prefix matching for fast IP processing
【24h】

A hash based architecture of longest prefix matching for fast IP processing

机译:快速IP处理的最长前缀的基于散列架构

获取原文

摘要

A novel hardware architecture of longest prefix match (LPM) search scheme based on hashing and controlled prefix expansion has been presented to achieve fast IP processing. The main idea of this architecture is to simplify the required hash functions and implemented in hardware for faster generation of addresses of the routing tables. The routing table has been implemented using SRAM to accommodate huge number of prefixes for real time packet forwarding. It is also to be noted that this architecture consumes one memory cycle to store new prefixes, search prefixes and modify existing prefixes and is reducing memory requirement unlike conventional and existing LPM solutions.
机译:已经提出了一种基于散列和受控前缀扩展的最长前缀匹配(LPM)搜索方案的新硬件架构,以实现快速的IP处理。此架构的主要思想是简化所需的散列函数,并在硬件中实现,以便更快地生成路由表的地址。路由表已使用SRAM实现,以适应实时数据包转发的大量前缀。还应注意,该架构消耗一个存储器周期来存储新的前缀,搜索前缀并修改现有前缀,并且正在降低与传统和现有的LPM解决方案不同的内存要求。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号