CN115296741A - Cross-platform optical fiber transmission system - Google Patents

Abstract

The invention provides a cross-platform optical fiber transmission system, which comprises: the optical fiber communication switching unit and the serial-parallel communication unit are connected; the optical fiber communication switching unit and the serial-parallel communication unit are both provided with optical fiber communication modules as communication interfaces, and data communication is carried out between the optical fiber communication switching unit and the serial-parallel communication unit through the optical fiber communication modules; PCIe is built based on a RIFFA reusable integrated framework between the optical fiber communication switching unit and the upper computer to carry out data transmission. The cross-platform optical fiber transmission system is high in system performance, and can realize cross-platform and multi-board communication.

Description

Translated fromChinese

跨平台光纤传输系统Cross-platform optical fiber transmission system

技术领域technical field

本发明涉及光纤通信技术领域，尤其涉及一种跨平台光纤传输系统。The invention relates to the technical field of optical fiber communication, in particular to a cross-platform optical fiber transmission system.

背景技术Background technique

超导设备是用于测量极端微弱信号，例如人体电磁场的微弱变化的设备。超导设备调试时需要记录的现场数据往往达到海量级数据，且要求数据能够实时地传输和处理，因此要求外部调试设备与主机高速数据传输。现有针对超导设备的调试装置通常采用PCIe总线和光纤通信技术相结合的数据传输系统，系统往往采用Aurora 8B/10B、SFP模块，单一平台与板卡上开发，使系统可达到的最高性能有限，不能满足海量级测试数据实时传输的要求；且现有调试设备往往不能实现跨平台应用，通用普适性差。Superconducting devices are those used to measure extremely weak signals, such as tiny changes in the body's electromagnetic field. The on-site data that needs to be recorded during superconducting equipment debugging often reaches massive data, and the data is required to be transmitted and processed in real time, so high-speed data transmission between external debugging equipment and the host is required. Existing debugging devices for superconducting equipment usually use a data transmission system combining PCIe bus and optical fiber communication technology. The system often uses Aurora 8B/10B and SFP modules, developed on a single platform and board, so that the system can achieve the highest performance Limited, unable to meet the requirements of real-time transmission of massive test data; and the existing debugging equipment often cannot realize cross-platform applications, and the general applicability is poor.

发明内容Contents of the invention

针对现有技术的不足，本发明提出一种跨平台光纤传输系统，系统性能高，能够实现跨平台、多板卡之间通信。Aiming at the deficiencies of the prior art, the present invention proposes a cross-platform optical fiber transmission system, which has high system performance and can realize cross-platform and multi-board communication.

为了实现上述目的，本发明一方面提供一种跨平台光纤传输系统，包括：光纤通信转接单元与串并通信单元；In order to achieve the above object, one aspect of the present invention provides a cross-platform optical fiber transmission system, including: an optical fiber communication conversion unit and a serial-parallel communication unit;

所述光纤通信转接单元与所述串并通信单元均配置有光纤通信模块作为通信接口，所述光纤通信转接单元与所述串并通信单元之间通过所述光纤通信模块进行数据通信；Both the optical fiber communication adapter unit and the serial-parallel communication unit are equipped with an optical fiber communication module as a communication interface, and data communication is performed between the optical fiber communication adapter unit and the serial-parallel communication unit through the optical fiber communication module;

所述光纤通信转接单元与上位机之间采用基于RIFFA可重用集成架构搭建PCIe进行数据传输。The PCIe based on the RIFFA reusable integrated architecture is used for data transmission between the optical fiber communication conversion unit and the host computer.

可选的，所述光纤通信转接单元包括：Optionally, the optical fiber communication conversion unit includes:

第一Aurora协议IP核模块，与所述光纤通信模块互联，用于高速串行数据和低速并行数据流之间的转换；The first Aurora protocol IP core module is interconnected with the optical fiber communication module for conversion between high-speed serial data and low-speed parallel data streams;

用户逻辑模块，配置为状态机，与所述第一Aurora协议IP核模块互联；The user logic module is configured as a state machine and is interconnected with the first Aurora protocol IP core module;

PCIe协议IP核模块，与所述用户逻辑模块互联，The PCIe protocol IP core module is interconnected with the user logic module,

所述光纤通信转接单元与上位机之间通过所述PCIe协议IP核模块进行连接；The optical fiber communication transfer unit and the host computer are connected through the PCIe protocol IP core module;

所述用户逻辑模块控制所述第一Aurora协议IP核模块处理后的数据流通过所述PCIe协议IP核模块传输至所述上位机，和/或The user logic module controls the data flow processed by the first Aurora protocol IP core module to be transmitted to the host computer through the PCIe protocol IP core module, and/or

控制从所述上位机采集的数据从所述PCIe协议IP核模块发送至所述第一Aurora协议IP核模块。Controlling that the data collected from the host computer is sent from the PCIe protocol IP core module to the first Aurora protocol IP core module.

可选的，所述第一Aurora协议IP核模块与所述用户逻辑模块之间还配置有：Optionally, there are also configured between the first Aurora protocol IP core module and the user logic module:

第一FIFO模块，同时与所述第一Aurora协议IP核模块、所述用户逻辑模块互联，用于缓存经过所述第一Aurora协议IP核模块或者所述用户逻辑模块处理后的数据流。The first FIFO module is interconnected with the first Aurora protocol IP core module and the user logic module at the same time, and is used for caching the data stream processed by the first Aurora protocol IP core module or the user logic module.

可选的，所述用户逻辑模块还用于：Optionally, the user logic module is also used for:

状态机在判断存在待接收数据需要接收时，进入接收状态进行数据接收，并将接收的数据写入所述第一FIFO模块缓存；When the state machine judges that there is data to be received that needs to be received, it enters the receiving state for data reception, and writes the received data into the first FIFO module cache;

数据接收完成后，状态机在判断所述第一FIFO模块存在待发送数据需要发送时，进入发送状态进行数据发送。After the data is received, the state machine enters the sending state to send data when it judges that there is data to be sent in the first FIFO module and needs to be sent.

可选的，所述光纤通信转接单元与上位机之间采用基于RIFFA可重用集成架构搭建PCIe进行数据传输，包括：Optionally, between the optical fiber communication conversion unit and the host computer, PCIe is built based on the RIFFA reusable integrated architecture for data transmission, including:

上位机端架构，用于提供上层驱动、协议库和用户使用端；The upper computer-side architecture is used to provide upper-layer drivers, protocol libraries and user terminals;

用户端架构，用于提供PCIe底层接口、数据发送接收接口、用户通道选择。The client architecture is used to provide PCIe underlying interface, data sending and receiving interface, and user channel selection.

可选的，根据Vendor ID与Device ID匹配所述光纤通信转接单元；Optionally, matching the optical fiber communication conversion unit according to the Vendor ID and the Device ID;

匹配成功后，初始化所述光纤通信转接单元；After the matching is successful, initialize the optical fiber communication conversion unit;

初始化成功后，在发送API接口与接收API接口配置PCIe的ID、传输通道、发送数组和数据长度。After the initialization is successful, configure the PCIe ID, transmission channel, sending array, and data length on the sending API interface and receiving API interface.

可选的，所述PCIe协议IP核模块配置为4通道。Optionally, the PCIe protocol IP core module is configured with 4 channels.

可选的，所述串并通信单元包括：Optionally, the serial-parallel communication unit includes:

第二Aurora协议IP核模块，与所述光纤通信模块互联，The second Aurora protocol IP core module is interconnected with the optical fiber communication module,

第二FIFO模块，与所述第二Aurora协议IP核模块互联，The second FIFO module is interconnected with the second Aurora protocol IP core module,

调用所述第二Aurora协议IP核模块，将高速串行数据转化为低速并行数据流后在所述第二FIFO模块进行缓存，或者Call the second Aurora protocol IP core module to convert the high-speed serial data into a low-speed parallel data stream and cache it in the second FIFO module, or

将所述第二FIFO模块缓存的低速并行数据流转换为高速串行数据流发送至所述光纤通信模块进行传输。The low-speed parallel data stream buffered by the second FIFO module is converted into a high-speed serial data stream and sent to the optical fiber communication module for transmission.

可选的，所述光纤通信模块采用SFP+光纤通信模块。Optionally, the optical fiber communication module is an SFP+ optical fiber communication module.

可选的，所述光纤通信转接单元与所述串并通信单元集成于FPGA开发板，并通过光纤互连。Optionally, the optical fiber communication conversion unit and the serial-parallel communication unit are integrated on an FPGA development board and interconnected through optical fibers.

由以上方案可知，本发明的优点在于：As can be seen from the above scheme, the present invention has the advantages of:

本发明提供的跨平台光纤传输系统的系统，光纤通信转接单元与串并通信单元基于Aurora IP核设置，均配置有光纤通信模块作为通信接口，通过调用能够与光纤通信模块数据无缝衔接的Aurora IP核，实现高速串行数据低速并行数据之间的转换；同时，系统采用基于RIFFA可重用集成架构搭建PCIe进行数据传输，实现多通道采集数据到上位机的实时传输通信，实现数据的跨平台、多板卡远距离稳定传输，超导设备海量测试数据的传输效率。In the system of the cross-platform optical fiber transmission system provided by the present invention, the optical fiber communication transfer unit and the serial-parallel communication unit are set based on the Aurora IP core, and both are equipped with an optical fiber communication module as a communication interface, which can seamlessly connect with the optical fiber communication module data by calling The Aurora IP core realizes the conversion between high-speed serial data and low-speed parallel data; at the same time, the system adopts PCIe based on the RIFFA reusable integrated architecture for data transmission, realizes real-time transmission and communication of multi-channel collected data to the host computer, and realizes data cross-connection Platform, multi-board long-distance stable transmission, transmission efficiency of massive test data of superconducting equipment.

附图说明Description of drawings

图1为本发明实施例提供的跨平台光纤传输系统的系统架构图；1 is a system architecture diagram of a cross-platform optical fiber transmission system provided by an embodiment of the present invention;

图2为光纤通信转接单元结构框图；Fig. 2 is a structural block diagram of the optical fiber communication transfer unit;

图3为用户逻辑模块状态机的控制逻辑；Fig. 3 is the control logic of user logic module state machine;

图4为串并通信单元结构框图；Fig. 4 is a structural block diagram of the serial-parallel communication unit;

其中：in:

1-光纤通信转接单元；1- Optical fiber communication transfer unit;

11-第一Aurora协议IP核模块；11-The first Aurora protocol IP core module;

12-用户逻辑模块；12 - user logic module;

13-PCIe协议IP核模块；13-PCIe protocol IP core module;

14-第一FIFO模块；14-the first FIFO module;

2-所述串并通信单元；2 - the serial-parallel communication unit;

21-第二Aurora协议IP核模块；21-The second Aurora protocol IP core module;

22-第二FIFO模块；22 - the second FIFO module;

3-光纤通信模块；3- Optical fiber communication module;

4-上位机。4- Host computer.

具体实施方式Detailed ways

为让本发明的上述特征和效果能阐述的更明确易懂，下文特举实施例，并配合说明书附图作详细说明如下。In order to make the above-mentioned features and effects of the present invention more clear and understandable, the following specific examples are given together with the accompanying drawings for detailed description as follows.

PCIe是一种采用点到点互联方式的串行总线，因其具有先进的系统架构、灵活的扩展性和超高的带宽，同时大大减少了制作成本，极其适应高速及实时性要求比较高场合。光纤通信因其可以实现百米级甚至千米级的数据传输，而且支持数吉比特的传输带宽，被广泛应用于PC与外设的高速通信中，目前的光模块速率已经达到10Gbps及以上。本发明实施例基于超导调试设备，研制跨平台光纤传输系统，系统基于FPGA平台的接口板卡，在FPGA平台上利用PCIe、Aurora协议和SFP光模块实现高速的数据传输。PCIe is a serial bus using point-to-point interconnection. Because of its advanced system architecture, flexible scalability and ultra-high bandwidth, it greatly reduces production costs and is extremely suitable for high-speed and real-time requirements. . Optical fiber communication is widely used in high-speed communication between PCs and peripherals because it can realize data transmission at the level of hundreds of meters or even kilometers, and supports transmission bandwidth of several gigabits. The current optical module rate has reached 10Gbps and above. The embodiment of the present invention develops a cross-platform optical fiber transmission system based on superconducting debugging equipment. The system is based on the interface board of the FPGA platform, and uses PCIe, Aurora protocol and SFP optical module to realize high-speed data transmission on the FPGA platform.

具体的，参考图1所示，图1示出了本发明实施例提供的跨平台光纤传输系统的系统结构图。Specifically, refer to FIG. 1 , which shows a system structure diagram of a cross-platform optical fiber transmission system provided by an embodiment of the present invention.

一种跨平台光纤传输系统，包括：光纤通信转接单元1与串并通信单元2；A cross-platform optical fiber transmission system, comprising: an optical fibercommunication conversion unit 1 and a serial-parallel communication unit 2;

所述光纤通信转接单元1与所述串并通信单元2均配置有光纤通信模块3作为通信接口，所述光纤通信转接单元1与所述串并通信单元2之间通过所述光纤通信模块3进行数据通信；Both the optical fibercommunication adapter unit 1 and the serial-parallel communication unit 2 are equipped with an opticalfiber communication module 3 as a communication interface, and the optical fibercommunication adapter unit 1 and the serial-parallel communication unit 2 communicate through theoptical fiber Module 3 for data communication;

所述光纤通信转接单元1与上位机4之间采用基于RIFFA可重用集成架构搭建PCIe进行数据传输。The optical fibercommunication adapter unit 1 and thehost computer 4 adopt PCIe based on the RIFFA reusable integrated architecture for data transmission.

在具体实现中，对于光纤通信转接单元1结构，如图2中所示，所述光纤通信转接单元1具体包括第一Aurora协议IP核模块11、用户逻辑模块12、PCIe协议IP核模块13等，其中第一Aurora协议IP核模块11与光纤通信模块3互联，用于高速串行数据和低速并行数据流之间的转换；用户逻辑模块12配置为状态机，与所述第一Aurora协议IP核模块11互联；PCIe协议IP核模块13与所述用户逻辑模块12互联。所述光纤通信转接单元1与上位机之间通过所述PCIe协议IP核模块13进行连接。所述用户逻辑模块12控制所述第一Aurora协议IP核模块11处理后的数据流通过所述PCIe协议IP核模块13传输至所述上位机，和/或控制从所述上位机采集的数据从所述PCIe协议IP核模块13发送至所述第一Aurora协议IP核模块11。In a specific implementation, for the structure of the optical fibercommunication transition unit 1, as shown in Figure 2, the optical fibercommunication transition unit 1 specifically includes a first Aurora protocolIP core module 11, auser logic module 12, and a PCIe protocolIP core module 13, etc., wherein the first Aurora protocolIP core module 11 is interconnected with the opticalfiber communication module 3 for conversion between high-speed serial data and low-speed parallel data flow; theuser logic module 12 is configured as a state machine, and the first Aurora The protocolIP core module 11 is interconnected; the PCIe protocolIP core module 13 is interconnected with theuser logic module 12 . The optical fibercommunication adapter unit 1 is connected to the host computer through the PCIe protocolIP core module 13 . Theuser logic module 12 controls the data flow processed by the first Aurora protocolIP core module 11 to be transmitted to the host computer through the PCIe protocolIP core module 13, and/or controls the data collected from the host computer From the PCIe protocolIP core module 13 to the first Aurora protocolIP core module 11.

此外，所述第一Aurora协议IP核模块11与所述用户逻辑模块12之间还配置有第一FIFO模块14，第一FIFO模块14同时与所述第一Aurora协议IP核模块、所述用户逻辑模块互联，用于缓存经过所述第一Aurora协议IP核模块或者所述用户逻辑模块处理后的数据流。本实施例中，使用FIFO作为PCIe IP核和Aurora IP核之间的数据存储以及数据跨时钟的传输，FIFO利用IP核实现，大大降低开发难度。In addition, afirst FIFO module 14 is also configured between the first Aurora protocolIP core module 11 and theuser logic module 12, and thefirst FIFO module 14 is simultaneously connected with the first Aurora protocol IP core module and theuser logic module 12. The logic modules are interconnected, and are used for caching the data flow processed by the first Aurora protocol IP core module or the user logic module. In this embodiment, FIFO is used as the data storage between the PCIe IP core and the Aurora IP core and the transmission of data across clocks, and the FIFO is realized by the IP core, which greatly reduces the difficulty of development.

此外，用户逻辑模块12配置为状态机，通过状态机控制PCIe协议IP核模块和第一Aurora协议IP核模块11之间的数据交互，保证数据时序的正确，实现数据稳定、可靠的传输。状态机在判断存在待接收数据需要接收时，进入接收状态进行数据接收，并将接收的数据写入所述第一FIFO模块缓存；数据接收完成后，状态机在判断所述第一FIFO模块存在待发送数据需要发送时，进入发送状态进行数据发送，直到传输完成，回到初始状态。例如，在与上位机交互过程中，在接收上位机数据时，状态机在判断存在上位机发送的待接收数据需要接收的情况下，进入接收状态进行数据接收，并将接收的数据写入所述FIFO模块缓存；在向上位机发送数据的过程中，状态机在判断所述FIFO模块存在待发送数据需要发送至上位机的情况下，进入发送状态进行数据发送，直到传输完成，回到初始状态。如图3中所示，图3示出了用户逻辑模块状态机的控制逻辑，下面将说明各个状态的实现功能。其中，状态st0：初始状态，当通道中有数据传输来时，触发CHNL_RX信号，CHNL_RX＝1时进入状态st1。状态st1：接收数据并将数据全部存入第一FIFO模块，接收完成后，即RXFinish＝1时，进入状态st2。状态st2：判断第一FIFO模块中是否有数据，当tx_tvalid＝1即第一FIFO模块中有数据时，进入状态st3。状态st3：接收第一FIFO模块中的数据并发送，TXFinish＝1时将数据在状态st3中全部发送，完成后返回状态st0，等待下一次传输。In addition, theuser logic module 12 is configured as a state machine, and the data interaction between the PCIe protocol IP core module and the first Aurora protocolIP core module 11 is controlled by the state machine to ensure the correct timing of data and realize stable and reliable data transmission. When judging that there is data to be received that needs to be received, the state machine enters the receiving state for data reception, and writes the received data into the cache of the first FIFO module; after the data reception is completed, the state machine judges that the first FIFO module exists When the data to be sent needs to be sent, enter the sending state to send data, until the transmission is completed, and return to the initial state. For example, in the process of interacting with the upper computer, when receiving data from the upper computer, the state machine enters the receiving state to receive data when it judges that there is data to be received sent by the upper computer, and writes the received data into the The FIFO module cache; in the process of sending data to the upper computer, the state machine enters the sending state to send data when it judges that the FIFO module has data to be sent to the upper computer, and returns to the initial state until the transmission is completed. state. As shown in FIG. 3, FIG. 3 shows the control logic of the state machine of the user logic module, and the implementation functions of each state will be described below. Among them, the state st0: the initial state, when there is data transmission in the channel, the CHNL_RX signal is triggered, and the state st1 is entered when CHNL_RX=1. State st1: receive data and store all the data in the first FIFO module, and enter state st2 after receiving is completed, that is, when RXFinish=1. State st2: judge whether there is data in the first FIFO module, and enter state st3 when tx_tvalid=1, that is, there is data in the first FIFO module. State st3: receive and send the data in the first FIFO module, when TXFinish=1, send all the data in state st3, return to state st0 after completion, and wait for the next transmission.

此外，在具体实现中，所述PCIe协议IP核模块可以配置为4通道，实现向上位机的高速数据传输。PCIe协议IP核模块使用4通道，根据每路通道最大传输速率5GT/s，本发明设计的PCIe协议IP核模块最大传输速率可达到20GT/s。AXI接口位宽为64位，和第一Aurora协议IP核模块11接口匹配。In addition, in a specific implementation, the PCIe protocol IP core module can be configured as 4 channels to realize high-speed data transmission to the host computer. The PCIe protocol IP core module uses 4 channels, and according to the maximum transmission rate of each channel of 5GT/s, the maximum transmission rate of the PCIe protocol IP core module designed by the present invention can reach 20GT/s. The bit width of the AXI interface is 64 bits, which matches the interface of the first Aurora protocolIP core module 11 .

此外，所述光纤通信转接单元与上位机之间采用基于RIFFA可重用集成架构搭建PCIe进行数据传输，RIFFA架构分为上位机端与用户端两部分，其中上位机端架构用于提供上层驱动、协议库和用户使用端；用户端架构用于提供PCIe底层接口、数据发送接收接口、用户通道选择。在光纤通信转接单元工作时，首先将所述光纤通信转接单元的板卡插在上位机端的PCIe x8插槽中，再次打开主机电源，通过PCIe驱动，根据Vendor ID和Device ID与需要查找的光纤通信转接单元的Vendor ID和Device ID进行比对，如果相等，则匹配成功；匹配成功后，初始化光纤通信转接单元的板卡的基地址寄存器存储空间BAR0，初始化成功后，上位机端主机将会分配数据缓冲区，在主机执行相应的用户程序进行数据传输，在发送API接口与接收API接口配置PCIe的ID、传输通道、发送数组和数据长度。此外，通过RX/TXDMA Engine模块采用分散收集地址信息的方法实现数据传输，带宽利用率更加接近理论值。In addition, between the optical fiber communication conversion unit and the host computer, PCIe is built based on the RIFFA reusable integrated architecture for data transmission. The RIFFA architecture is divided into two parts: the host computer end and the user end. , a protocol library, and a user terminal; the client architecture is used to provide PCIe underlying interfaces, data sending and receiving interfaces, and user channel selection. When the optical fiber communication conversion unit is working, first insert the board card of the optical fiber communication conversion unit into the PCIe x8 slot of the host computer, turn on the power of the host computer again, and use the PCIe driver to search according to the Vendor ID and Device ID and the needs Compare the Vendor ID and Device ID of the optical fiber communication adapter unit. If they are equal, the match is successful; after the match is successful, initialize the base address register storage space BAR0 of the board card of the optical fiber communication adapter unit. The end host will allocate a data buffer, execute the corresponding user program on the host for data transmission, and configure the PCIe ID, transmission channel, sending array, and data length on the sending API interface and receiving API interface. In addition, the RX/TXDMA Engine module adopts the method of collecting address information dispersedly to realize data transmission, and the bandwidth utilization is closer to the theoretical value.

在具体设计中，可以直接采用封装好的PCIe通信框架，通过调用框架预留出的数据接收发送端口，实现对数据读写的控制。本实施例中，基于RIFFA可重用集成框架搭建PCIe数据传输，其实现多通道采集数据到上位机的实时传输通信。RIFFA是一个通过PCIe总线实现CPU和FPGA数据通信的简单架构，其工作时需要一个支持PCIe的工作台和一个带有PCIe连接器的FPGA板卡。RIFFA不依赖PCIe Bridge，因此不受桥连接的速率和通道数的限制；并且使用直接存储器访问传输方式(DMA)和中断模式传输数据。因此可以实现PCIe链路的高带宽，运行速率可以达到PCIe链路的饱和点。RIFFA架构简化了用户操作，在用户端留有独立的数据发送接口和数据接收端口，对于发送和接收端口的操作只需要用户编写相应的控制逻辑可实现FPGA的通信。In the specific design, the packaged PCIe communication framework can be used directly, and the control of data reading and writing can be realized by calling the data receiving and sending ports reserved by the framework. In this embodiment, PCIe data transmission is built based on the RIFFA reusable integration framework, which realizes real-time transmission and communication of multi-channel data collection to the host computer. RIFFA is a simple architecture that realizes data communication between CPU and FPGA through PCIe bus. It needs a workbench that supports PCIe and an FPGA board with PCIe connector for its operation. RIFFA does not rely on PCIe Bridge, so it is not limited by the speed and number of channels connected by the bridge; and uses direct memory access transfer (DMA) and interrupt mode to transfer data. Therefore, the high bandwidth of the PCIe link can be realized, and the operating speed can reach the saturation point of the PCIe link. The RIFFA architecture simplifies user operations. There are independent data sending interfaces and data receiving ports on the user side. For the operation of sending and receiving ports, users only need to write corresponding control logic to realize FPGA communication.

对于串并通信单元2的结构，如图4中所示，串并通信单元2具体包括第二Aurora协议IP核模块21、第二FIFO模块22，第二Aurora协议IP核模块21与光纤通信模块3互联，第二FIFO模块22与所述第二Aurora IP核模块21互联，调用所述第二Aurora协议IP核模块21，用于高速串行数据和低速并行数据流之间的转换，将高速串行数据转化为低速并行数据流后在所述第二FIFO模块22进行缓存，或者将所述第二FIFO模块22缓存的低速并行数据流转换为高速串行数据流发送至光纤通信模块3进行传输。For the structure of the serial-parallel communication unit 2, as shown in FIG. 3 interconnection, thesecond FIFO module 22 is interconnected with the second AuroraIP core module 21, and calls the second Aurora protocolIP core module 21 for conversion between high-speed serial data and low-speed parallel data streams, and high-speed After the serial data is converted into a low-speed parallel data stream, it is buffered in thesecond FIFO module 22, or the low-speed parallel data stream buffered by thesecond FIFO module 22 is converted into a high-speed serial data stream and sent to the opticalfiber communication module 3 for further processing. transmission.

本实施例中，在外部的串并通信单元的板卡上实现光纤通信模块以及能够与光纤通信模块通信接口数据无缝衔接的第二Aurora协议IP核模块21。In this embodiment, the optical fiber communication module and the second Aurora protocolIP core module 21 that can seamlessly connect with the communication interface data of the optical fiber communication module are implemented on the board of the external serial-parallel communication unit.

此外，针对传统上应用较为广泛的SFP光纤通信接口最大传输速率在4Gbps的限制，本实施例的所述光纤通信模块采用SFP+光纤通信模块作为设备高速互联的接口通信电路，最高速率可达10Gbps，从而有效提高数据传输速率。同时，SFP+光纤通信模块把用于时钟和数据恢复的电路从芯片中转移到线卡上，把线卡的密度从XFP的每块16个提高到24个，做到了真正的降低成本。光纤通信转接单元与串并通信单元组成互联系统，可通过1路光纤通道，实现了最大数据传输速率为10Gbps级的高速光纤数据采集与传输，系统最多可配置为16通道，达到板卡间160Gbps级的传输速率。In addition, in view of the limitation of the maximum transmission rate of the traditionally widely used SFP optical fiber communication interface at 4Gbps, the optical fiber communication module of this embodiment uses the SFP+ optical fiber communication module as the interface communication circuit for high-speed interconnection of devices, and the maximum rate can reach 10Gbps. Thereby effectively improving the data transmission rate. At the same time, the SFP+ optical fiber communication module transfers the circuit used for clock and data recovery from the chip to the line card, and increases the density of the line card from 16 per XFP block to 24, thus achieving a real cost reduction. The optical fiber communication conversion unit and the serial-parallel communication unit form an interconnection system, which can realize high-speed optical fiber data acquisition and transmission with a maximum data transmission rate of 10Gbps through one optical fiber channel. 160Gbps level transmission rate.

此外，本实施例中，将所述光纤通信转接单元与所述串并通信单元集成于FPGA开发板，并通过光纤互连，从而实现外部串并通信单元与上位机主机的高速数据传输。外部串并通信单元和超导设备进行数据的交互，对超导设备进行调试，实现数据的跨平台、多板卡远距离稳定传输。In addition, in this embodiment, the optical fiber communication adapter unit and the serial-parallel communication unit are integrated into the FPGA development board and interconnected through optical fibers, so as to realize high-speed data transmission between the external serial-parallel communication unit and the host computer. The external serial-parallel communication unit interacts with the superconducting equipment for data, debugs the superconducting equipment, and realizes cross-platform, multi-board long-distance stable transmission of data.

综上，本实施例提供的跨平台光纤传输系统的系统，跨平台光纤传输系统的系统，光纤通信转接单元与串并通信单元基于Aurora IP核设置，均配置有光纤通信模块作为通信接口，通过调用能够与光纤通信模块数据无缝衔接的Aurora IP核，实现高速串行数据和低速并行数据之间的转换；同时，系统采用基于RIFFA可重用集成架构搭建PCIe进行数据传输，实现多通道采集数据到上位机的实时传输通信，实现数据的跨平台、多板卡远距离稳定传输。同时，光纤通信模块采用SFP+光纤通信模块，实现了最大数据传输速率为10Gbps级的高速光纤数据采集与传输系统，最多可配置为16通道，达到板卡间160Gbps级的传输速率，提高了超导设备海量测试数据的传输效率。To sum up, the system of the cross-platform optical fiber transmission system provided by this embodiment, the system of the cross-platform optical fiber transmission system, the optical fiber communication conversion unit and the serial-parallel communication unit are set based on the Aurora IP core, and are all equipped with an optical fiber communication module as a communication interface. The conversion between high-speed serial data and low-speed parallel data is realized by calling the Aurora IP core, which can be seamlessly connected with the data of the optical fiber communication module; at the same time, the system adopts PCIe based on the RIFFA reusable integrated architecture for data transmission, and realizes multi-channel acquisition The real-time transmission and communication of data to the host computer realizes the cross-platform and multi-board long-distance stable transmission of data. At the same time, the optical fiber communication module adopts SFP+ optical fiber communication module, which realizes a high-speed optical fiber data acquisition and transmission system with a maximum data transmission rate of 10Gbps. The transmission efficiency of massive test data of equipment.

需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不同于所描述的次序来执行所描述的方法，并且还可以施加、省去、或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本申请的保护之内。The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementations. The above-mentioned specific implementations are only illustrative and not restrictive. Those of ordinary skill in the art will Under the inspiration of this application, without departing from the purpose of this application and the scope of protection of the claims, many forms can also be made, all of which belong to the protection of this application.

Claims (10)

Translated fromChinese

1.一种跨平台光纤传输系统，其特征在于，包括：光纤通信转接单元与串并通信单元；1. A cross-platform optical fiber transmission system, comprising: an optical fiber communication transfer unit and a serial-parallel communication unit;所述光纤通信转接单元与所述串并通信单元均配置有光纤通信模块作为通信接口，所述光纤通信转接单元与所述串并通信单元之间通过所述光纤通信模块进行数据通信；Both the optical fiber communication adapter unit and the serial-parallel communication unit are equipped with an optical fiber communication module as a communication interface, and data communication is performed between the optical fiber communication adapter unit and the serial-parallel communication unit through the optical fiber communication module;所述光纤通信转接单元与上位机之间采用基于RIFFA可重用集成架构搭建PCIe进行数据传输。The PCIe based on the RIFFA reusable integrated architecture is used for data transmission between the optical fiber communication conversion unit and the host computer.2.根据权利要求1所述的系统，其特征在于，所述光纤通信转接单元包括：2. The system according to claim 1, wherein the optical fiber communication conversion unit comprises:第一Aurora协议IP核模块，与所述光纤通信模块互联，用于高速串行数据和低速并行数据流之间的转换；The first Aurora protocol IP core module is interconnected with the optical fiber communication module for conversion between high-speed serial data and low-speed parallel data streams;用户逻辑模块，配置为状态机，与所述第一Aurora协议IP核模块互联；The user logic module is configured as a state machine and is interconnected with the first Aurora protocol IP core module;PCIe协议IP核模块，与所述用户逻辑模块互联，The PCIe protocol IP core module is interconnected with the user logic module,所述光纤通信转接单元与上位机之间通过所述PCIe协议IP核模块进行连接；The optical fiber communication transfer unit and the host computer are connected through the PCIe protocol IP core module;所述用户逻辑模块控制所述第一Aurora协议IP核模块处理后的数据流通过所述PCIe协议IP核模块传输至所述上位机，和/或The user logic module controls the data flow processed by the first Aurora protocol IP core module to be transmitted to the host computer through the PCIe protocol IP core module, and/or控制从所述上位机采集的数据从所述PCIe协议IP核模块发送至所述第一Aurora协议IP核模块。Controlling that the data collected from the host computer is sent from the PCIe protocol IP core module to the first Aurora protocol IP core module.3.根据权利要求2所述的系统，其特征在于，所述第一Aurora协议IP核模块与所述用户逻辑模块之间还配置有：3. The system according to claim 2, wherein, between the first Aurora protocol IP core module and the user logic module, there are:第一FIFO模块，同时与所述第一Aurora协议IP核模块、所述用户逻辑模块互联，用于缓存经过所述第一Aurora协议IP核模块或者所述用户逻辑模块处理后的数据流。The first FIFO module is interconnected with the first Aurora protocol IP core module and the user logic module at the same time, and is used for caching the data stream processed by the first Aurora protocol IP core module or the user logic module.4.根据权利要求3所述的系统，其特征在于，所述用户逻辑模块还用于：4. The system according to claim 3, wherein the user logic module is also used for:状态机在判断存在待接收数据需要接收时，进入接收状态进行数据接收，并将接收的数据写入所述第一FIFO模块缓存；When the state machine judges that there is data to be received that needs to be received, it enters the receiving state for data reception, and writes the received data into the first FIFO module cache;数据接收完成后，状态机在判断所述第一FIFO模块存在待发送数据需要发送时，进入发送状态进行数据发送。After the data is received, the state machine enters the sending state to send data when it judges that there is data to be sent in the first FIFO module and needs to be sent.5.根据权利要求2所述的系统，其特征在于，5. The system of claim 2, wherein:所述光纤通信转接单元与上位机之间采用基于RIFFA可重用集成架构搭建PCIe进行数据传输，包括：The PCIe based on the RIFFA reusable integrated architecture is used for data transmission between the optical fiber communication transfer unit and the host computer, including:上位机端架构，用于提供上层驱动、协议库和用户使用端；The upper computer-side architecture is used to provide upper-layer drivers, protocol libraries and user terminals;用户端架构，用于提供PCIe底层接口、数据发送接收接口、用户通道选择。The client architecture is used to provide PCIe underlying interface, data sending and receiving interface, and user channel selection.6.根据权利要求5所述的系统，其特征在于，6. The system of claim 5, wherein:根据Vendor ID和Device ID匹配所述光纤通信转接单元；matching the optical fiber communication transition unit according to Vendor ID and Device ID;匹配成功后，初始化所述光纤通信转接单元；After the matching is successful, initialize the optical fiber communication conversion unit;初始化成功后，在发送API接口与接收API接口配置PCIe的ID、传输通道、发送数组和数据长度。After the initialization is successful, configure the PCIe ID, transmission channel, sending array, and data length on the sending API interface and receiving API interface.7.根据权利要求5所述的系统，其特征在于，7. The system of claim 5, wherein:所述PCIe协议IP核模块配置为4通道。The PCIe protocol IP core module is configured as 4 channels.8.根据权利要求1所述的系统，其特征在于，所述串并通信单元包括：8. The system according to claim 1, wherein the serial-parallel communication unit comprises:第二Aurora协议IP核模块，与所述光纤通信模块互联，The second Aurora protocol IP core module is interconnected with the optical fiber communication module,第二FIFO模块，与所述第二Aurora协议IP核模块互联，The second FIFO module is interconnected with the second Aurora protocol IP core module,调用所述第二Aurora协议IP核模块，将高速串行数据转化为低速并行数据流后在所述第二FIFO模块进行缓存，或者Call the second Aurora protocol IP core module to convert the high-speed serial data into a low-speed parallel data stream and cache it in the second FIFO module, or将所述第二FIFO模块缓存的低速并行数据流转换为高速串行数据流发送至所述光纤通信模块进行传输。The low-speed parallel data stream buffered by the second FIFO module is converted into a high-speed serial data stream and sent to the optical fiber communication module for transmission.9.根据权利要求1所述的系统，其特征在于，9. The system of claim 1, wherein:所述光纤通信模块采用SFP+光纤通信模块。The optical fiber communication module adopts SFP+ optical fiber communication module.10.根据权利要求1所述的系统，其特征在于，10. The system of claim 1, wherein:所述光纤通信转接单元与所述串并通信单元集成于FPGA开发板，并通过光纤互连。The optical fiber communication conversion unit and the serial-parallel communication unit are integrated on the FPGA development board and interconnected through optical fibers.

Images