Neural network accelerator suitable for edge equipment and neural network acceleration calculation method

Abstract

The invention discloses a neural network accelerator suitable for edge equipment and a neural network acceleration calculation method, and relates to the technical field of neural networks. The network accelerator comprises a configuration unit, a data buffer unit, a processing matrix component (PMs) and a post-processing unit, and a main controller writes feature parameters of different types ofnetwork layers into a register of the configuration unit to control the mapping of different network layer operation logics to the processing matrix hardware, so as to realize the multiplexing of theprocessing matrix component, i.e., the operation acceleration of different types of network layers in the neural network is realized by using one hardware circuit without additional hardware resources; and the different types of network layers comprise a standard convolution layer and a pooling network layer. The multiplexing accelerator provided by the invention not only ensures the realization of the same function, but also has the advantages of less hardware resource consumption, higher hardware multiplexing rate, lower power consumption, high concurrency, high multiplexing characteristic and strong structural expansibility.

Description

technical field [0001] The invention belongs to the technical field of neural networks, and in particular relates to a neural network accelerator applicable to edge devices and a neural network acceleration calculation method applicable to edge devices. Background technique [0002] As a computation-intensive application, neural network inference has the characteristics of complex computing mechanism, huge amount of computation, and high computing delay. Therefore, some dedicated neural network accelerators have been developed to accelerate the process of neural network inference. Most of the current neural network accelerators use the direct mapping method to complete the operation acceleration, that is, the operation logic of various types of network layers in the neural network is directly mapped to specific functional circuits, such as the specific function used to accelerate the standard convolutional network layer. Functional circuits, specific functional circuits for ...

AI Technical Summary

Problems solved by technology

[0003] Although this accelerator structure using multiple specific function circuits improves the computing efficiency of the neural network, it consumes more hardware resources and consumes more power.

Images