A Calculation Method for Deep Convolutional Neural Network Suitable for Hardware Design and Implementation

Abstract

The invention provides a deep convolutional neural network computing method applicable to hardware design implementation. The deep convolutional neural network computing method puts forward that a deep convolutional neural network computing structure is readjusted in advance through relevant adjustment parameters and breaks through the constraint that a computing window structure is fixed in a traditional convolutional neural network, so that data, involved in computation, in every computing layer can reach firstly, and computing parallelism in the deep convolutional neural network and streamlining among the computing layers are fully exploited to reduce storage of a great number of intermediate results effectively. The deep convolutional neural network computing method applicable to hardware design implementation has the advantages that a deep convolutional neural network computing structure adjusted by the method is more beneficial to implementation of efficient parallel streamlining in terms of special hardware design, and the problems of resource waste and effective computing delay due to various filling operations during computation are solved effectively, so that system power consumption can be reduced effectively and computing and processing speed can be increased greatly.

Description

technical field [0001] The invention belongs to a complex algorithm acceleration method, and in particular relates to a calculation method of a deep convolutional neural network suitable for hardware design and realization. Background technique [0002] With the new wave of machine learning brought about by deep learning, deep convolutional neural networks have been widely used in different large-scale machine learning problems such as speech recognition, image recognition, and natural speech processing, and have achieved a series of breakthrough research results , its powerful feature learning and classification ability has attracted widespread attention, and has important analysis and research value. [0003] The deep convolutional neural network model has the characteristics of high model depth, complex hierarchy, large data magnitude, high parallelism, intensive calculation and storage intensive, etc., and a large number of convolution operations and pooling operations o...

AI Technical Summary

Problems solved by technology

[0003] The deep convolutional neural network model has the characteristics of high model depth, complex hierarchy, large data magnitude, high parallelism, intensive calculation and storage intensive, etc., and a large number of convolution operations and pooling operations often make it a part of the application process. Large computing bottlenecks and the storage of a large number of intermediate results also put forward higher requirements on the computer storage structure, which is very unfavorable for application scenarios with strong real-time performance and limited investment costs

[0004] The two commonly used accelerators are CPU and GPU. The CPU cannot ideally meet the requirements in terms of computing performance based on its serial execution structural characteristics. Although the GPU has obvious advantages in computing performance, it cannot break through the power consumption just like the CPU. barriers, and both CPU and GPU have serious limitations in scalability

Considering factors such as the above, more and more people have begun to design dedicated hardware systems to complete the acceleration of deep convolutional neural networks, but how to fully tap the parallelism of deep convolutional neural network computing models by combining the characteristics of hardware chips and platform advantages As well as streamlining, it is still a problem to be solved to make full use of limited hardware resources to complete the design reasonably and efficiently.

Images