天津职业技术师范大学学报

为解决多片FPGA之间的多时钟同步问题,提出了多时钟硬件同步的思想。对多片FPGA芯片之间的时钟同步方法进行研究,实现了由4片FPGA芯片搭建的多FPGA神经元网络仿真平台。利用3层的FHN(Fitz Hugh-Nagumo)模型对多FPGA神经元网络仿真平台进行验证。结果表明:相对于市场现有的FPGA仿真平台,多FPGA神经元网络仿真平台具有计算速度快、可靠性强、配置灵活、易于扩展、适用于大规模神经网络仿真等优点,能够应用于各种神经元网络的仿真与分析。

In order to solve the problem of multi-clock synchronization between multiple FPGA, this study proposes the idea of multi-clock hardware synchronization, analyses the method of clock synchronization between multi-FPGA, and designs a simulation platform of multi-FPGA based on neural network, which is set up by 4 FPGA chips. The simulation platform of multi-FPGA neural network is verified by the three layer Fitz Hugh-Nagumo(FHN) model. The verification results show that, compared with the existing FPGA platform, the multi-FPGA neural network simulation platform has the advantages of high computational efficiency, high reliability, flexible configuration, easy to expand, suitable for large-scale neural network simulation and so on. The proposed design can be widely applied in fields such as the artificial intelligence or the dynamical characteristics investigation of the neural networks.