Based on High Level Synthesis (HLS) design methodology of FPGA
this paper implements a convolutional neural network accelerator on ZYNQ-7020. The design method of cyclic unroll and pipelinling is used to optimize the convolution kernel operation
and the occupied logic resources and operation efficiency are balanced to achieve the optimal performance of the accelerator. The performance of the accelerator is tested by the MINST dataset at 100MHz working frequency. The results show that:the accelerator can achieve 3.77 times acceleration compared to the general platform ARM A9for a single picture
and the streaming processing of thousands of pictures can achieve up to 6.14 times acceleration.
关键词
Keywords
references
范秋香. FPGA高级开发技术的研究[D].北京: 北京理工大学, 2015.
ZHANG C, LI P, SUN G, et al. Optimi-zing fpgabased accelerator design for deep convolutional neural networks[C]// Acm/sigda International Symposium on Field-programmable Gate Arrays. ACM, 2015.
LI H, FAN X, JIAO L, et al.A high pe-rformance FPGA-based accelerator for large-scale convolutional neural netwo-rks[C]// 201626th International Conf-erence on Field Programmable Logic and Applications (FPL). IEEE, 2016.