Packet classification is a vital and complicated task as the processing of packets should be done at a specified line speed. In order to classify a packet as belonging to a particular flow or set of flows, network nodes must perform a search over a set of filters using multiple fields of the packet as the search key. Hence the matching of packets should be much faster and simpler for quick processing and classification. A hardware accelerator or a classifier has been proposed here using a modified version of the HyperCuts packet classification algorithm. A new pre-cutting process has been implemented to reduce the memory size to fit in an FPGA. This classifier can classify packets with high speed and with a power consumption factor of less than 3W. This methodology removes the need for floating point division to be performed by replacing the region compaction scheme of HyperCuts by pre-cutting, while classifying the packets and concentrates on classifying the packets at the core of the network.
翻译:包件分类是一项重要而复杂的任务, 因为包件的处理应该以指定的行速进行。 为了将包件分类为属于特定的流或流动集, 网络节点必须使用包件的多个字段作为搜索键对一组过滤器进行搜索。 因此, 要快速处理和分类, 包包的匹配应该快得多、 简单得多。 在此提议了硬件加速器或分类器, 使用的是 HyperCuts 包分类算法的修改版本 。 已经实施了一个新的预切程序, 以降低内存大小, 以适合 FPGA 。 此分类器可以对包件进行高速分类, 且电源消耗因子小于 3W 。 这样的方法就不需要通过预切换 CypercCuts 区域压缩方案来进行浮动点分割, 同时对包件进行分类, 并集中对网络核心的包件进行分类 。