GPU-based method and device for calculating binary neural network convolution

Abstract

Embodiments of the invention provide a GPU-based method and device for calculating binary neural network convolution. The method comprises the following steps of obtaining a calculation request for executing convolution operation according to a binary neural network; starting at least one thread block on a GPU according to the calculation request, wherein each thread block comprises a plurality of threads; determining a calculation area range of each thread block on the basis of a two-stage blocking strategy, and determining calculation area ranges of the threads included by each thread block; executing a calculation process by each thread in each thread block of the at least one thread block so as to obtain calculation results; and determining output results of corresponding thread blocks according to the calculation result of each thread in each thread block. According to the method, the two-stage blocking strategy on the basis of the GPU thread block is designed, and the access characteristics of the GPU are fully utilized, so that binary neural network convolution calculation can be realized on GPU equipment, the calculation speed is enhanced and the internal memory consumption is decreased.

Description

technical field [0001] The present invention relates to the field of computer vision, and more specifically relates to a GPU-based method and device for calculating binary neural network convolution. Background technique [0002] The concept of deep learning originated from the research of artificial neural networks. A multi-layer perceptron with multiple hidden layers is a deep learning structure. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover distributed feature representations of data. In computer vision and related fields, emerging deep learning methods have made great progress over traditional methods of the past. [0003] Convolutional neural networks (CNNs for short) is a machine learning model under deep supervised learning, which is the core operation of deep learning. It performs a convolution operation between the convolution kernel (Kernel) and the original image input to ob...

AI Technical Summary

Problems solved by technology

Generally speaking, the convolution operation is the part with the largest amount of calculation and the most memory overhead in a deep learning model. For example, the convolution operation in the current CNN will take up more than 70% of the calculation time, so it is necessary to optimize the convolution operation of

Images