Checksum calculation method and network processor

Abstract

An embodiment of the invention discloses a checksum calculation method. The method comprises the steps that a multi-thread micro-engine obtains calculation parameters corresponding to a current thread based on a received user instruction and descriptor fields in a data storage unit, and sends the calculation parameters to a calculation unit; the calculation unit performs checksum calculation based on source data read from the data storage unit and the calculation parameters, and a thread scheduling module schedules a current thread to enter a sleep state; when finishing the calculation, the calculation unit writes a calculated checksum in a checksum register of the current thread and instructs the thread scheduling module to schedule the current thread to enter a wakeup state; and when the thread scheduling module schedules the current thread to enter a work state from the wakeup state, the multi-thread micro-engine writes the calculated checksum in a position corresponding to the current thread in the data storage unit. An embodiment of the invention furthermore discloses a network processor.

Description

technical field [0001] The invention relates to the technical field of network processors, in particular to a checksum calculation method and a network processor. Background technique [0002] A checksum is the sum of a set of data items used for verification purposes in the fields of data processing and data communication. It is usually used in communication, especially in long-distance communication to ensure the integrity and correctness of data. There are checksum fields in the IP header, TCP header, and UDP header of a packet. In the process of message forwarding, the correctness of the transmission is ensured by calculating, modifying and verifying the checksum field. Therefore, the calculation of the checksum is a very important function for the network processor and is indispensable. . [0003] At present, there are many ways to realize the checksum calculation of the network processor. A completely independent checksum calculation coprocessor requires a micro-eng...

AI Technical Summary

Problems solved by technology

[0003] At present, there are many ways to realize the checksum calculation of the network processor. A completely independent checksum calculation coprocessor requires a micro-engine to read out the data to be calculated and send it to the coprocessor for each calculation. After the calculation is completed, the result is returned to the micro-engine. This method saves resources the most. Multiple micro-engines can share a coprocessor, but it will increase the scheduling process of data entering and leaving the coprocessor, increase the extra overhead of the coprocessor and increase the reporting rate. The residence time of the file in the network processor affects the performance of the network processor

Images