Convolutional neural network processor for edge calculation

Abstract

The invention discloses a convolutional neural network processor for edge calculation. A simple control instruction for the convolutional neural network is provided, convolutional neural network basicoperations such as a convolutional layer, a pooling layer, a ReLU activation function and a full connection layer can be realized, and the applicability of the accelerator for the convolutional neural network is realized through combination sorting of the instructions. The accelerator realizes a high-efficiency pulsation calculation array, so that the reusability of data can be increased to the maximum extent in a data reading process, and the access frequency of the pulsation calculation array to a data cache unit is reduced. The accelerator supports the calculation of two data precisions of16-bit fixed point number and 8-bit fixed point number at the same time, and can realize the calculation of the mixing precision of different layers of the same network, thereby greatly reducing thepower consumption of the accelerator. According to the accelerator, the minimum scheduling frequency of data in a cache part is guaranteed, power consumption is reduced. Meanwhile, convolution layer calculation and full connection layer calculation share the same pulsation calculation array, and the resource utilization rate is greatly increased.

Description

technical field [0001] The invention relates to a convolutional neural network processor. In particular, it relates to a convolutional neural network processor for edge computing. Background technique [0002] In recent years, cloud computing has become an increasingly mainstream trend. Cloud computing enables companies to store and process data (and other computing tasks) through a network of remote servers (commonly known as the "cloud") outside of their own physical hardware. The consolidated and centralized nature of cloud computing has proven cost-effective and flexible, but the rise of the Internet of Things and mobile computing is putting pressure on network bandwidth. Ultimately, not all smart devices need to leverage cloud computing to function. In some cases, this round trip of data needs to be minimized or avoided. At the same time, with the vigorous development of IoT (Internet of Things) and the popularization of wireless networks, the number of network edge...

AI Technical Summary

Problems solved by technology

In this case, the centralized processing mode based on the cloud computing model will not be able to efficiently process the data generated by the edge devices

In the context of the Internet of Everything, the centralized cloud computing processing model (traditional cloud computing) mainly has four shortcomings: poor real-time performance, insufficient bandwidth, high energy consumption, and not conducive to data security and privacy[2-4]

In this scenario, any delay may be fatal. Considering that it may take a few seconds for the central server to transmit data back and forth, all of these data cannot be uploaded to the cloud processor and need to be stored and computed in the edge computing node.

Images