集成电路与嵌入式系统2025，Vol.25Issue(12)：8-17,10.DOI:10.20193/j.ices2097-4191.2025.0057
基于国产智能可重构平台的AI加速软硬件设计
AI acceleration software and hardware design based on domestic intelligent reconfigurable platform
GUO Tao 1ZHOU Haiyang 1YU Yuxin 1FAN Xiaochang 1WANG Shuo 2ZHANG Yanlong 3CHEN Lei1
作者信息
- 1. Beijing Microelectronics Technology Institute,Beijing 100076,China
- 2. Beijing Microelectronics Technology Institute,Beijing 100076,China||Northwestern Polytechnical University,Xi'an 710072,China
- 3. Beijing Aerospace Microsystem and Information Technology Institute,Beijing 100094,China||Tsinghua University,Beijing 100084,China
- 折叠
摘要
Abstract
In response to the demand for intelligent equipment electronic systems,this article designs a neural network accelerator soft core and supporting quantitative compilation software based on the programmable logic on the"Hongxin"intelligent reconfigurable plat-form.It realizes the unified quantitative compilation and deployment of neural network models for self-developed accelerator soft cores,and expands the functions of the"Hongtu"embedded real-time operating system,achieving support for hardware accelerated operation of neural networks.Through experimental testing,the performance of the neural network accelerator soft core is comparable to that of the AMD Xilinx DPU soft core.The"Hongtu"embedded real-time operating system running ResNetl8 and ResNet50 delivers four times higher performance than the AMD Xilinx PetaLinux environment.These results enhance the artificial intelligence capabilities of the"Hongxin"intelligent reconfigurable platform.关键词
智能可重构平台/神经网络加速器/神经网络量化编译软件/嵌入式实时操作系统Key words
intelligent reconfigurable platform/neural network accelerator/neural network quantitative compilation software/embedded real-time operating system分类
信息技术与安全科学引用本文复制引用
GUO Tao,ZHOU Haiyang,YU Yuxin,FAN Xiaochang,WANG Shuo,ZHANG Yanlong,CHEN Lei..基于国产智能可重构平台的AI加速软硬件设计[J].集成电路与嵌入式系统,2025,25(12):8-17,10.
