Dynamic extensible convolutional neural network accelerator

Abstract

The invention discloses a dynamic extensible convolutional neural network accelerator, and belongs to the technical field of calculation, calculation and counting. The accelerator comprises an adaptive data storage module and an efficient computing array scheduling module. The adaptive data storage module comprises a hierarchical storage module and an external two-dimensional data conversion customization interface module. The efficient computing array scheduling module comprises a neuron processing unit array data scheduling module based on multiply-add logic and a neuron processing unit array data scheduling module based on a lookup table. The whole convolutional neural network accelerator masks the data delay of external memory access by designing a reasonable multi-level storage structure. Data scheduling is carried out on the computing array according to network layer characteristics and task requirements, so that repeated utilization of the data can be realized, the access parallelism degree of a lookup table of the computing array is improved, the operation speed is increased, and the accelerator can adapt to various complex computing tasks.

Description

technical field [0001] The invention discloses a dynamically expandable convolutional neural network accelerator, relates to the physical realization of neural networks, and belongs to the technical field of calculation, calculation and counting. Background technique [0002] With the advancement of computer and communication technology, Internet data has exploded. The processing of massive data has become a great challenge, and traditional methods can no longer cope with the current situation. Deep learning has emerged as a viable approach for big data processing. Deep learning is an important part of artificial intelligence, which can more realistically simulate the working mechanism of the human brain to achieve better results. Among them, the convolutional neural network in deep learning has made remarkable achievements in the field of image processing. [0003] Convolutional neural networks can be deployed on the cloud, but localized operation of convolutional neural...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the shortcomings of the above-mentioned background technology, and propose a dynamically scalable convolutional neural network accelerator to improve the computing efficiency of the convolutional neural network, realize data multiplexing, reduce neural network operation delay, and reduce bandwidth. Solve the technical problem that the existing neural network accelerators cannot meet the task requirements with low latency and less occupied bandwidth in high-performance application scenarios

Images