基于AXI总线复用的DMA数据传输结构设计
2023年电子技术应用第8期
阮翔,任涛,毛佳佳,张虎
(中国电子科技集团公司第52研究所,浙江 杭州 311100)
摘要:常规多通道DMA数据传输结构应用在多传感器接入式人工智能平台时,随着传感器类型和数量的增加,在通道协议转换、AXI总线扩展过程中会消耗大量的FPGA逻辑和存储资源,容易产生逻辑拥塞,增加工具布线难度。与此同时,封闭式的AXI系统缺乏对通道差异控制的灵活性,难以适应人工智能平台多模式数据传输需求。因此,设计了一种AXI总线复用方式的DMA数据传输结构,该设计可以极大地缩减AXI总线数量,降低FPGA资源消耗和工具布线用时,方便地引入附加逻辑实现多模式DMA数据传输,为人工智能平台提供灵活高效的多源数据获取机制。
中图分类号:TP274 文献标志码:A DOI: 10.16157/j.issn.0258-7998.223646
中文引用格式:阮翔,任涛,毛佳佳,等. 基于AXI总线复用的DMA数据传输结构设计[J]. 电子技术应用,2023,49(8):125-129.
英文引用格式:Ruan Xiang,Ren Tao,Mao Jiajia,et al. Design of DMA data transmission structure based on AXI bus multiplexing[J]. Application of Electronic Technique,2023,49(8):125-129.
中文引用格式:阮翔,任涛,毛佳佳,等. 基于AXI总线复用的DMA数据传输结构设计[J]. 电子技术应用,2023,49(8):125-129.
英文引用格式:Ruan Xiang,Ren Tao,Mao Jiajia,et al. Design of DMA data transmission structure based on AXI bus multiplexing[J]. Application of Electronic Technique,2023,49(8):125-129.
Design of DMA data transmission structure based on AXI bus multiplexing
Ruan Xiang,Ren Tao,Mao Jiajia,Zhang Hu
(The 52th Research Institute of China Electronics Technology Group Corporation, Hangzhou 311100, China)
Abstract:When the conventional multi-channel DMA data transmission structure is applied to the multi-sensor connected artificial intelligence platform, with the increase of sensor type and quantity, a lot of FPGA logic and storage resources will be consumed in the process of channel protocol conversion and AXI bus extension, which will easily lead to logic congestion and increase the difficulty of tool routing. At the same time, the closed AXI system lacks the flexibility of channel differential control, and it is difficult to adapt to the multi-mode data transmission requirements of artificial intelligence platform. Therefore, a DMA data transmission structure with AXI bus multiplexing mode is designed, which can greatly reduce the number of AXI buses, reduce FPGA resource consumption and tool routing time, conveniently fit additional logic to realize multi-mode DMA data transmission, and provide a flexible and efficient multi-source data acquisition mechanism for artificial intelligence platform.
Key words :channel;DMA;transmission;AXI;FPGA
0 引言
近年来,支持多传感器接入的人工智能平台已经在各个领域获得广泛应用。利用嵌入式人工智能(Artificial Intelligence,AI)处理器和现场可编程逻辑门阵列(Field Programmable Gate Array,FPGA)进行直接内存访问(Direct Memory Access,DMA)交互的系统架构往往成为这类人工智能平台的最优实现方案。平台内,FPGA承担了数据的采集、缓存及DMA任务。常规方式是把每个数据通道封装成一路AXI总线,使用AXI交换结构将数据通道与缓存控制器、DMA控制器互联,形成一个封闭的AXI数据传输系统。然而,随着应用场景复杂度和平台智能化程度的提升,传感器的种类和数量持续增长。常规传输结构逐渐表现出扩展不便、优化困难、灵活性差等问题。为简化AXI交换拓扑、方便通道扩展、实现灵活的DMA参数化配置,本文设计了一种以AXI总线复用方式实现的DMA数据传输结构,以满足平台对多路、多类型传感器通道扩展和数据灵活处理的需求。
本文详细内容请下载:https://www.chinaaet.com/resource/share/2000005490
作者信息:
阮翔,任涛,毛佳佳,张虎
(中国电子科技集团公司第52研究所,浙江 杭州 311100)
此内容为AET网站原创,未经授权禁止转载。