Neural network acceleration coprocessor, processing system and processing method

Abstract

The invention discloses a neural network acceleration coprocessor, a processing system and a processing method. The system comprises a coprocessor, a main processor and a memory, wherein the main processor is used for sending an expansion instruction; the memory is used for storing data; the coprocessor is used for receiving the expansion instruction sent by the main processor, reading the input data from the memory according to the received expansion instruction, performing neural network calculation on the input data to obtain output data, and storing the output data into the memory; whereinthe coprocessor is used for processing time-consuming operation in the convolutional neural network, the main processor controls the coprocessor to perform neural network calculation on the input data through the expansion instruction, the utilization rate of the CPU is reduced, and compared with pure software, convolution operation efficiency is improved by more than 20 times.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and chip design, in particular to a neural network acceleration coprocessor, a processing system and a processing method. Background technique [0002] The convolutional layer is the core computing module in the convolutional neural network. Usually, the calculation amount of the convolutional layer accounts for more than 90% of the calculation of the entire convolutional network. figure 1 It shows the process of convoluting an output feature map. Each input feature map corresponds to a convolution kernel. The dotted boxes of different colors in the input map correspond to different outputs. Each output is composed of different input maps with the same position and The convolution kernel is obtained by multiplying and accumulating. Each output is the result of local information processing of the input, which reflects the local feature information. The same input feature map uses the same c...

AI Technical Summary

Problems solved by technology

[0007] The embodiment of the present invention provides a neural network acceleration coprocessor, a processing system and a processing method, which are used to solve the problem that the calculation efficiency of the convolutional layer calculation is very low currently through pure software.

Images