A CNN accelerator configuration method, system and device

Abstract

The present application discloses a CNN accelerator configuration method, which includes: acquiring the data requirement range of the current system mode; acquiring the data state of the CNN accelerator corresponding to the current seed data stream; judging whether the current data state meets the current data requirement range; if not, replacing The current seed data stream is used to dynamically configure the PE part in the CNN accelerator until the current data state meets the current data demand range. The configuration method in this application enables the PE part of the CNN accelerator to be dynamically configured according to different seed data streams. With the functional requirements of different system modes, the performance of the CNN accelerator can be dynamically adjusted, with strong compatibility and a wider application market. Correspondingly, the present application also discloses a CNN accelerator configuration system and device with the same beneficial effects.

Description

technical field [0001] The present invention relates to the field of CNN accelerators, in particular to a CNN accelerator configuration method, system and device. Background technique [0002] Currently, a technology for implementing a CNN (Convolutional Neural Network, convolutional neural network) accelerator based on an FPGA (Field Programmable Gate Array, field programmable gate array) has become mature. see figure 1 As shown, the basic composition of the FPGA-based CNN accelerator includes input buffer, PE (Processing Element, processing unit), output buffer and external storage, wherein PE is the basic calculation unit of convolution, including adder and multiplier. The PE part of the CNN accelerator is a multi-layer convolutional network formed by multiple PE units, including convolutional layers and fully connected layers. [0003] In the prior art, the CNN accelerator mostly uses a CPU (Central Processing Unit, central processing unit) or GPU (Graphics Processing ...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, CNN accelerators mostly use CPU (Central Processing Unit, central processing unit) or GPU (Graphics Processing Unit, graphics processing unit) to train convolutional neural networks, and then obtain optimal setting parameters, and FPGA is only used for CNN accelerators The execution inference of the CNN accelerator is fixed, and the performance is single, which cannot meet the power consumption or performance requirements in a variety of specific environments.

Images