Convolution calculation method and convolution operation circuit

Abstract

The invention relates to a convolution calculation method and a convolution operation circuit, and belongs to the technical field of circuit design. The method is applied to a convolution operation circuit. The convolution operation circuit comprises an electric chip, a first DA conversion unit, a second DA conversion unit, an AD conversion unit and a photon artificial intelligence chip. The method comprises the steps that an electric chip converts a weight in a target convolution kernel into a first optical signal through a first DA conversion unit and sends the first optical signal to a photon artificial intelligence chip; the electric chip sequentially converts the numerical values in the to-be-calculated sub-matrixes into second optical signals through a second DA conversion unit and sends the second optical signals to the photon artificial intelligence chip; and the photon artificial intelligence chip performs matrix operation on the first optical signal and each second optical signal, converts the optical signals after matrix operation through the AD conversion unit and outputs the converted optical signals. In the embodiment of the invention, the matrix multiplication realized by the photon artificial intelligence chip is organically combined into the convolution calculation, so that the calculation efficiency of the convolution operation is improved.

Description

technical field [0001] The application belongs to the technical field of circuit design, and in particular relates to a convolution calculation method and a convolution calculation circuit. Background technique [0002] The concept of convolution is often involved in image processing. The convolution operation on digital images is actually to use the convolution kernel (convolution template) to slide on the image, multiply the pixel gray value on the image point with the value on the corresponding convolution kernel, and then multiply all The value of is added as the gray value of the pixel on the image corresponding to the middle pixel of the convolution kernel, and finally the process of sliding all the images. [0003] In terms of existing artificial intelligence computing, it mainly uses a graphics processing unit (Graphics Processing Unit, GPU), a central processing unit (Central Processing Unit, CPU), a field programmable gate array (Field Programmable Gate Array, FPG...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present application is to provide a convolution calculation method and a convolution operation circuit to improve the problems of low calculation efficiency and high power consumption existing in the existing convolution calculation method

Images