An adaptive and reconfigurable deep convolutional neural network computing method and device

Abstract

The invention relates to an adaptive and reconfigurable deep convolutional neural network computing method and device, the method comprising: determining the program execution flow of the computing device according to the control signal; performing basic computing primitives according to the scale parameter of the deep neural convolutional network Dynamic reconfiguration determines the combination level and parallelism of the operation unit; loads the corresponding processing data according to different reconfiguration situations, performs corresponding calculations on the convolutional neural network layers with different attributes, and finally obtains the connection output results of the group of neurons . The invention solves the problem of low flexibility of proprietary hardware, and can reconstruct the design parameters of the computing unit to achieve the purpose of supporting deep convolutional neural networks of different scales; the invention can satisfy the parallel operation of convolution kernels of the same scale, It can also realize parallel operations of convolution kernels of different scales, and the dynamically reconfigurable computing unit greatly improves the parallelism of deep convolutional neural network operations and improves computing performance.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an adaptive and reconfigurable deep convolutional neural network calculation method and device. Background technique [0002] This section introduces readers to background technologies that may be related to various aspects of the present invention, and it is believed that useful background information can be provided to readers, thereby helping readers to better understand various aspects of the present invention. Accordingly, it is to be understood that the descriptions in this section are for the purposes stated above and do not constitute admissions of prior art. [0003] Deep neural networks have produced excellent results in many current application fields, such as face recognition, object detection, automatic driving, speech recognition, etc., and have been widely used. With the improvement of the accuracy of the algorithm, the depth of the neural network is increasing,...

AI Technical Summary

Problems solved by technology

The computing primitives with a fixed design can only calculate these convolution operations of different scales in series, and the degree of parallelism is low, which is not enough to meet the computing performance requirements of practical applications.

Images