Configurable convolutional array accelerator structure based on Winograd

Abstract

The invention discloses a configurable convolutional array accelerator structure based on Winograd. The structure comprises an activation value caching module, a weight caching module, an output caching module, a controller, a weight preprocessing module, an activation value preprocessing module, a weight conversion module, an activation value matrix conversion module, a dot multiplication module, a result matrix conversion module, an accumulation module, a pooling module and an activation module. According to the configurable convolutional array accelerator structure based on the Winograd, the convolutional array accelerator with the configurable bit width is designed according to the operation characteristics of a Winograd convolution algorithm of a fixed normal form, and the requirements of different neural networks and different convolutional layers for the bit widths are flexibly met. In addition, a special multiplier unit with configurable data bit width is also designed, so that the calculation efficiency of the neural network convolution operation is improved, and the calculation power consumption is reduced.

Description

technical field [0001] The invention relates to a configurable convolution array accelerator structure. In particular, it relates to a Winograd-based configurable convolutional array accelerator structure. Background technique [0002] Neural networks perform well in many fields, especially image-related tasks, such as image classification, image semantic segmentation, image retrieval, object detection and other computer vision problems. They have begun to replace most traditional algorithms and are gradually deployed on terminal devices. [0003] However, the amount of calculation of the neural network is very huge, so there are problems such as slow processing speed of the neural network and high power consumption. A neural network mainly includes a training phase and an inference phase. In order to obtain high-precision processing results, weight data needs to be obtained through repeated iterative calculations from massive data during training. In the neural network r...

AI Technical Summary

Problems solved by technology

However, the convolution data bit width in the existing fixed-point neural network is fixed and cannot be flexibly configured, which reduces the applicability

Images