首页> 外文会议>International Conference on Computer and Knowledge Engineering >P4 to SDNet: Automatic Generation of an Efficient Protocol-Independent Packet Parser on Reconfigurable Hardware
【24h】

P4 to SDNet: Automatic Generation of an Efficient Protocol-Independent Packet Parser on Reconfigurable Hardware

机译:P4到SDNet:在可重新配置的硬件上自动生成高效的协议无关的数据包解析器

获取原文

摘要

Nowadays network managers look for ways to change the design and management of networks that can make decisions on the control plane. Future switches should be able to support the new features and flexibility required for parsing and processing packets. One of the critical components of switches is the packet parser that processes the headers of the packets to be able to decide on the incoming packets. Here the data plane, and particularly packet parser in OpenFlow switches, which should have the flexibility and programmability to support the new requirements and OpenFlow multiple versions, are focused. Designed here is an architecture that unlike the static network equipments, it has the flexibility and programmability in the data plane network, especially the SDN network, and supports the parsing and processing of specific packets. To describe this architecture, a high-level P4 language is used to implement it on a reconfigurable hardware (i.e., FPGA). After automatic generating the protocol-independent Packet parser architecture on the Virtex-7, it is compiled to firmware by Xilinx SDNet, and ultimately an FPGA Platform is implemented. It has fewer consumption resources and it is more efficient in terms of throughput and processing speed in comparison with other architectures.
机译:如今,网络管理员正在寻找改变网络设计和管理的方法,这些方法可以在控制平面上做出决策。未来的交换机应该能够支持解析和处理数据包所需的新功能和灵活性。交换机的关键组件之一是数据包解析器,该解析器处理数据包的报头,以便能够确定传入的数据包。这里重点介绍了数据平面,尤其是OpenFlow交换机中的数据包解析器,它应该具有灵活性和可编程性以支持新要求和OpenFlow多个版本。这里设计的体系结构与静态网络设备不同,它在数据平面网络(尤其是SDN网络)中具有灵活性和可编程性,并支持特定数据包的解析和处理。为了描述这种架构,使用了高级P4语言在可重配置的硬件(即FPGA)上实现它。在Virtex-7上自动生成与协议无关的数据包解析器架构后,Xilinx SDNet将其编译为固件,并最终实现了FPGA平台。与其他架构相比,它具有更少的消耗资源,并且在吞吐量和处理速度方面更加高效。

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