Remote communication method, device and system, medium and computer program product

By using optical fiber connections in the field programmable gate array group, remote high-speed communication between peripheral components interconnection and fast bus devices is achieved, which solves the problems of slow transmission rates and complex structures in the prior art, improves data transmission rates and simplifies structure.

CN119070911APending Publication Date: 2024-12-03SHANDONG YUNHAI GUOCHUANG CLOUD COMPUTING EQUIP IND INNOVATION CENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411161504.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-12-03

Smart Images

  • Figure CN119070911A_ABST
    Figure CN119070911A_ABST
Patent Text Reader

Abstract

The invention discloses a remote communication method, device and system, a medium and a computer program product, and relates to the technical field of communication, the method is applied to a first field-programmable gate array in a field-programmable gate array group, the field-programmable gate array group comprises N field-programmable gate arrays, N is greater than or equal to 2, and N is greater than or equal to 1. The field programmable gate arrays are connected through optical fibers. The field-programmable gate array acquires a data packet of the external component interconnection fast bus equipment connected with the field-programmable gate array, and finally transmits the data packet to another field-programmable gate array connected with the external component interconnection fast bus equipment through an optical fiber; and the other field programmable gate array finally sends the data packet to the external component interconnection fast bus equipment connected with the field programmable gate array, so that remote communication between the external component interconnection fast bus equipment is realized, and the remote data transmission rate of the external component interconnection fast bus equipment can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a remote communication method, device, system, medium, and computer program product. Background Technology

[0002] PCIe (Peripheral Component Interconnect Express) is a high-speed serial computer expansion bus standard. PCIe devices, or Peripheral Component Interconnect Express devices, refer to devices that use the PCIe interface for data transmission. For long-distance communication between Peripheral Component Interconnect Express devices, the devices are first connected to a server or mainframe computer via a PCIe slot, and then communication is established via Ethernet or similar methods. However, the transmission rate of the above-mentioned scheme for long-distance communication between Peripheral Component Interconnect Express devices is relatively slow, typically ranging from tens to hundreds of Mb / s, and the overall structure is complex. Therefore, providing a solution for achieving high-speed remote communication between Peripheral Component Interconnect Express devices has become a technical problem urgently needing to be solved by those skilled in the art. Summary of the Invention

[0003] The purpose of this application is to provide a remote communication method, device, system, medium, and computer program product that enables high-speed remote communication between peripheral component interconnection bus devices.

[0004] To address the aforementioned technical problems, this application provides a remote communication method applied to a first field-programmable gate array (FPGA) in a field-programmable gate array (FPGA) group. The FPGA group comprises N FPGAs, where N is greater than or equal to 2, and the FPGAs are interconnected via optical fibers. The first FPGA is connected to a first peripheral component interconnect (PCIe) fast bus device. The method includes:

[0005] Obtain the data packet from the first peripheral component interconnect fast bus device;

[0006] Data packets from the first peripheral component interconnect fast bus device are transmitted via optical fiber between field-programmable gate arrays to a second field-programmable gate array connected to the second peripheral component interconnect fast bus device, so that data packets from the first peripheral component interconnect fast bus device can be sent to the second peripheral component interconnect fast bus device through the second field-programmable gate array;

[0007] Receive data packets from the second peripheral component interconnect fast bus device transmitted by the second field-programmable gate array through the optical fiber between the field-programmable gate arrays;

[0008] The data packets of the second peripheral component interconnect fast bus device are sent to the first peripheral component interconnect fast bus device.

[0009] In some embodiments, it also includes:

[0010] Receive the program file sent by the host computer via Ethernet, and burn the program file to a non-volatile storage device.

[0011] In some embodiments, it also includes:

[0012] The program file is transmitted to other field-programmable gate arrays (FPGAs) via optical fiber, so that the other FPGAs can burn the program file to their own non-volatile storage devices.

[0013] In some embodiments, it also includes:

[0014] The system displays the operating status of the first field-programmable gate array, the current amount of data received and transmitted, and reported error information.

[0015] In some embodiments, it also includes:

[0016] It receives program files transmitted by other field-programmable gate arrays via optical fiber and burns the program files to a non-volatile storage device.

[0017] In some embodiments, it also includes:

[0018] The data packets are subjected to data packet verification, parallel-to-serial conversion, and encoding / decoding processing.

[0019] In some embodiments, the first field programmable gate array includes a processor, a peripheral component interconnect fast bus control module, a data cache module, and a data transceiver control module; the peripheral component interconnect fast bus control module is used to read data packets from the first peripheral component interconnect fast bus device and store the read data packets into the data cache module; the processor is used to send the data in the data cache module to the data transceiver control module; the data transceiver control module is used to output the data through the optical fiber.

[0020] In some embodiments, the processor is configured to send data in the data cache module to the data transceiver control module via an Advanced Scalable Interface Bus.

[0021] In some embodiments, it also includes:

[0022] The data transceiver control module is initialized and waits to establish a communication link with other field-programmable gate arrays.

[0023] In some embodiments, it also includes:

[0024] The peripheral component interconnection fast bus control module is initialized.

[0025] In some embodiments, the processor is a hard-core processor that integrates the peripheral component interconnect fast bus control module and the data cache module.

[0026] In some embodiments, the first field-programmable gate array is a ZYNQ UltraScale+ series field-programmable gate array.

[0027] In some embodiments, the processor is a soft-core processor, and the soft-core processor is independent of the peripheral component interconnection fast bus control module and the data cache module.

[0028] In some embodiments, the first field-programmable gate array is a Virtex UltraScale+ series field-programmable gate array.

[0029] In some embodiments, the first field programmable gate array includes a processor, a peripheral component interconnect fast bus control module, a data cache module, a data transceiver control module and an Ethernet control module; the peripheral component interconnect fast bus control module is used to read data packets from the first peripheral component interconnect fast bus device and store the read data packets into the data cache module; the processor is used to send data in the data cache module to the data transceiver control module; the data transceiver control module is used to output data through the optical fiber, and the Ethernet control module is used to receive program files sent by the host computer via Ethernet.

[0030] In some embodiments, the Ethernet control module is further configured to display the operating status of the first field-programmable gate array itself, the current amount of data received and transmitted, and report error information.

[0031] To solve the above technical problems, the present application further provides a remote communication device, which is applied to a first field programmable gate array in a field programmable gate array group, wherein the field programmable gate array group includes N field programmable gate arrays, where N is greater than or equal to 2, and the field programmable gate arrays are connected to each other via optical fibers, and the first field programmable gate array is connected to a first peripheral component interconnection fast bus device, comprising:

[0032] The acquisition unit is used to acquire data packets from the first peripheral component interconnect fast bus device;

[0033] The transmission unit is used to transmit data packets of the first peripheral component interconnect fast bus device to a second field-programmable gate array connected to the second peripheral component interconnect fast bus device through an optical fiber between field-programmable gate arrays, so as to send data packets of the first peripheral component interconnect fast bus device to the second peripheral component interconnect fast bus device through the second field-programmable gate array;

[0034] a receiving unit, configured to receive a data packet of the second peripheral component interconnect fast bus device sent by the second field programmable gate array through an optical fiber between field programmable gate arrays;

[0035] A sending unit is configured to send a data packet of the second peripheral component interconnect fast bus device to the first peripheral component interconnect fast bus device.

[0036] To address the aforementioned technical problems, this application also provides a remote communication system, comprising: a field-programmable gate array (FPGA) group; the FPGA group includes N FPGAs, where N is greater than or equal to 2, and the FPGAs are connected to each other via optical fibers; a first FPGA is connected to a first peripheral component interconnect (PCI) fast bus device, and a second FPGA is connected to a second PCI fast bus device; the first FPGA is used to: acquire data packets from the first PCI fast bus device; transmit the data packets from the first PCI fast bus device to the second FPGA connected to the second PCI fast bus device via the optical fibers between the FPGAs, so as to send the data packets from the first PCI fast bus device to the second PCI fast bus device via the second FPGA; receive data packets from the second PCI fast bus device transmitted by the second FPGA via the optical fibers between the FPGAs; and send the data packets from the second PCI fast bus device to the first PCI fast bus device.

[0037] In order to solve the above technical problems, the present application also provides a medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0038] To solve the above technical problems, the present application also provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned remote communication method when executed by a processor.

[0039] The remote communication method provided in this application includes: a first field-programmable gate array (FPGA) applied in a group of FPGAs, wherein the FPGA group includes N FPGAs, N being greater than or equal to 2, and the FPGAs are connected to each other via optical fibers. The first FPGA is connected to a first peripheral component interconnect (PCIe) bus device. The method includes: acquiring data packets from the first PCIe; transmitting the data packets from the first PCIe to the second FPGA connected to a second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the second PCIe to the first PCIe to the second ...

[0040] As can be seen, unlike schemes that transmit data from Peripheral Component Interconnect (PCI) Fast Bus (PCB) devices via Ethernet, the remote communication method provided in this application connects the PCI device to a Field-Programmable Gate Array (FPGA). One FPGA connected to the PCI device acquires data packets from the PCI device and transmits them via optical fiber to another FPGA connected to the PCI device. The other FPGA then sends the data packets back to its connected PCI device, thus achieving remote communication between PCI devices. The use of FPGAs and optical fibers effectively improves the data transmission rate of PCI devices remotely. Furthermore, this method is highly flexible and adaptable to various application scenarios. In scenarios with large data transmission volumes, multiple optical fiber channels can be used for simultaneous transmission; in scenarios with small data transmission volumes, the number of optical fiber channels can be reduced, thus reducing the consumption of logic resources.

[0041] The remote communication device, system, medium, and computer program products provided in this application all have the aforementioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the prior art and embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1A flowchart illustrating a remote communication method provided in an embodiment of this application;

[0044] Figure 2 A schematic diagram of a field-programmable gate array provided in an embodiment of this application;

[0045] Figure 3 This is a schematic diagram illustrating a specific remote communication scheme provided in an embodiment of this application;

[0046] Figure 4 A schematic diagram illustrating another specific remote communication scheme provided in an embodiment of this application;

[0047] Figure 5 This is a schematic diagram of a remote communication device provided in an embodiment of this application. DETAILED DESCRIPTION

[0048] The core of this application is to provide a remote communication method, device, system, medium, and computer program product that enables high-speed remote communication between peripheral component interconnection bus devices.

[0049] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a remote communication method provided in an embodiment of this application. The method is applied to a first field-programmable gate array (FPGA) in a group of FPGAs. The FPGA group includes N FPGAs, where N is greater than or equal to 2. The FPGAs are connected to each other via optical fiber. The first FPGA is connected to a first peripheral component interconnect (PCIe) bus device. (Refer to...) Figure 1 As shown, the method includes:

[0051] S101: Obtain the data packet from the first peripheral component interconnect fast bus device;

[0052] S102: Transmit the data packets of the first peripheral component interconnect fast bus device to the second field-programmable gate array connected to the second peripheral component interconnect fast bus device through the optical fiber between the field-programmable gate arrays, so as to send the data packets of the first peripheral component interconnect fast bus device to the second peripheral component interconnect fast bus device through the second field-programmable gate array;

[0053] S103: Receive data packets from the second peripheral component interconnect fast bus device transmitted by the second field-programmable gate array through the optical fiber between the field-programmable gate arrays;

[0054] S104: Send the data packet of the second peripheral component interconnect fast bus device to the first peripheral component interconnect fast bus device.

[0055] The field programmable gate array group includes at least two field programmable gate arrays, and the field programmable gate arrays are connected in series through optical fibers so that data packets of one peripheral component interconnection fast bus device are transmitted to another peripheral component interconnection fast bus device through each field programmable gate array using optical fiber transmission, thereby realizing remote high-speed communication between the peripheral component interconnection fast bus devices.

[0056] If the FPGA group includes two FPGAs, each of the two FPGAs is connected to a PCI Express bus device via a PCIe socket. One of the FPGAs is referred to as a first FPGA, and the other is referred to as a second FPGA. The PCI Express bus device connected to the first FPGA is referred to as a first PCI Express bus device, and the PCI Express bus device connected to the second FPGA is referred to as a second PCI Express bus device.

[0057] If a FPGA group includes three or more FPGAs, two of the FPGAs are connected to a PCI Express bus device via PCIe sockets. One of the FPGAs connected to the PCI Express bus device is referred to as a first FPGA, and the other is referred to as a second FPGA. The PCI Express bus device connected to the first FPGA is referred to as a first PCI Express bus device, and the PCI Express bus device connected to the second FPGA is referred to as a second PCI Express bus device. One or more FPGAs are connected in series between the first and second FPGAs. The primary function of the FPGAs connected in series between the first and second FPGAs is to transmit data packets to the next FPGA via optical fiber.

[0058] It should be noted that the descriptions of "first" and "second" in the above text are only used to distinguish between different field-programmable gate arrays and different peripheral component interconnection fast bus devices, and are not used as limitations on size, order, etc.

[0059] The following uses a field-programmable gate array (FPGA) group consisting of two FPGAs as an example to illustrate the remote communication method provided in this application. It is clear that this remote communication method is also applicable to cases where the FPGA group consists of three or more FPGAs.

[0060] The first field-programmable gate array (FPGA) reads data packets from the first peripheral component interconnect (PCI) fast bus device it is connected to, and transmits the data packets to the second FPGA via a fiber optic converter module and optical fiber. The second FPGA then sends the received data packets to the second PCI fast bus device it is connected to, thus completing the process of data packet transmission from the first PCI fast bus device to the second PCI fast bus device.

[0061] Conversely, when data packets are transmitted from the second Peripheral Component Interconnect (PCI) Fast Bus (PCB) device to the first PCI Fast Bus (PCB) device, the second PCB reads the data packets from the connected second PCI Fast Bus device and transmits them to the first PCB via a fiber optic converter and optical fiber. The first PCB then sends the received data packets to the connected first PCI Fast Bus device.

[0062] In some embodiments, the method further includes performing packet verification, parallel-to-serial conversion, and encoding / decoding processing on the data packet.

[0063] The first field-programmable gate array (FPGA) reads data packets from the first peripheral component interconnect (PCIe) bus device it is connected to, performs data packet verification, parallel-to-serial conversion, and encoding / decoding on the data packets, and then transmits the processed data packets to the second FPGA via a fiber optic converter module and optical fiber. The second FPGA performs data packet verification, parallel-to-serial conversion, and encoding / decoding on the received data packets, and then sends the processed data packets to the second PCIe (PCIe) bus device it is connected to, thus completing the process of data packet transmission from the first PCIe (PCIe) bus device to the second PCIe (PCIe) bus device.

[0064] Conversely, when data packets are transmitted from the second Peripheral Component Interconnect (PCI) Fast Bus (PCB) device to the first PCI Fast Bus (PCB) device, the second PCB reads the data packets from the connected second PCI Fast Bus device and performs data packet verification, parallel-to-serial conversion, and encoding / decoding processing. The processed data packets are then transmitted to the first PCB via a fiber optic converter module and optical fiber. The first PCB performs data packet verification, parallel-to-serial conversion, and encoding / decoding processing on the received data packets and sends the processed data packets to the connected first PCI Fast Bus device.

[0065] Different data packets can be processed in other ways. For example, video data packets can be processed by adjusting resolution, compressing, and decompressing.

[0066] In some embodiments, it also includes:

[0067] Receive the program file sent by the host computer via Ethernet, and burn the program file to a non-volatile storage device.

[0068] When a remote upgrade or update of the first field-programmable gate array is required, the host computer sends the program file to the first field-programmable gate array via Ethernet. The first field-programmable gate array burns the program file to a non-volatile storage device, and then the power is turned off and restarted to complete the upgrade and update.

[0069] In some embodiments, it also includes:

[0070] The program file is transmitted to other field-programmable gate arrays (FPGAs) via optical fiber, so that the other FPGAs can burn the program file to their own non-volatile storage devices.

[0071] The first field-programmable gate array (FPGA) receives the program file sent by the host computer and then transmits the program file to other FPGAs via fiber optic cable. The other FPGAs then burn the program file into their own non-volatile storage devices, and then power off and restart to complete the upgrade and update.

[0072] In a field-programmable gate array (FPGA) group consisting of two FPGAs, the first FPGA receives a program file sent by the host computer and transmits the program file directly to the second FPGA via optical fiber. The second FPGA then burns the program file into its own non-volatile storage device, and then restarts after a power outage to achieve the upgrade and update.

[0073] In a field-programmable gate array (FPGA) group comprising three or more FPGAs, the first FPGA receives a program file from the host computer and transmits it via fiber optic cable to its connected FPGA. This FPGA then forwards the program file to the next FPGA, and so on, until the program file is sent to the second FPGA. Each FPGA that receives the program file burns it to its own non-volatile storage device, then powers off and restarts to perform the upgrade and update.

[0074] In some embodiments, it also includes:

[0075] The system displays the operating status of the first field-programmable gate array, the current amount of data received and transmitted, and reported error information.

[0076] The first field programmable gate array can display its own working status, the current amount of data received and transmitted, and report error information in real time.

[0077] In some embodiments, it also includes:

[0078] It receives program files transmitted by other field-programmable gate arrays via optical fiber and burns the program files to a non-volatile storage device.

[0079] In this embodiment, the host computer sends the program file to other field-programmable gate arrays in the field-programmable gate array group via Ethernet. The other field-programmable gate arrays send the program file to the first field-programmable gate array via optical fiber. Then, the first field-programmable gate array burns the program file to its own non-volatile storage device, and then restarts after power failure to achieve the upgrade and update.

[0080] In some embodiments, the first field programmable gate array includes a processor, a peripheral component interconnect fast bus control module, a data cache module, and a data transceiver control module; the peripheral component interconnect fast bus control module is used to read data packets from the first peripheral component interconnect fast bus device and store the read data packets into the data cache module; the processor is used to send the data in the data cache module to the data transceiver control module; the data transceiver control module is used to output the data through the optical fiber.

[0081] refer to Figure 2 As shown, in this embodiment, the first field-programmable gate array (i.e., Figure 2 The FPGA device 1 shown includes a processor, a peripheral component interconnection fast bus control module (i.e., Figure 2 The PCIe control module, data cache module, and data transceiver control module shown are shown in the diagram. Figure 2 The high-speed transceiver control module shown in the diagram. The peripheral component interconnect fast bus control module receives data from the first peripheral component interconnect fast bus device (i.e., Figure 2 The PCIe device 1) shown reads data packets and stores them in the data cache module. The processor sends the data in the data cache module to the data transceiver control module. The data transceiver control module outputs the data through the photoelectric conversion module and the optical fiber. Figure 2 The FPGA device 2 shown is a second field-programmable gate array, and the PCIe device 2 is a second peripheral component interconnect fast bus device.

[0082] In some embodiments, the processor is used to send data in the data cache module to the data transceiver control module via an Advanced Scalable Interface (ASI) bus.

[0083] The Peripheral Component Interconnect Fast Bus (PCI) control module reads data packets from the first PCI device and stores the read data packets in the data buffer module. The processor transmits the data from the data buffer module to the data transceiver control module via the AXI (Advanced eXtensible Interface) bus. The data transceiver control module outputs the data through the photoelectric conversion module and the optical fiber. If the first field-programmable gate array also performs data packet verification, parallel-to-serial conversion, and encoding / decoding processing, this process can be performed by the data transceiver control module.

[0084] The peripheral component interconnection fast bus control module, data cache module, and data transceiver control module can all use free and open-source IP cores from AMD Xilinx. The project setup process may include:

[0085] Use Vivado to build a hardware platform project, add Aurora and other IP cores and configure them, write RTL code, connect modules, perform electrical consistency checks, perform pin constraints, synthesis, implementation, generate bitstream files, and export the hardware platform xx.xsa file.

[0086] Use Vitis to create an embedded software project, import the xx.xsa file, write the processor control logic in C language, compile it to generate the xx.elf file. You can choose whether to embed the program into flash memory.

[0087] The two FPGAs are connected by optical fiber, and the host computer is connected to FPGA device 1 by a network cable. After power is turned on and each module is initialized and the Aurora link is established, the communication between the FPGAs can be controlled by the host computer.

[0088] In some embodiments, it also includes:

[0089] The processor initializes the data transceiver control module and waits to establish a communication link with other field-programmable gate arrays.

[0090] In some embodiments, it also includes:

[0091] The processor initializes the peripheral component interconnection fast bus control module.

[0092] After the first and second field-programmable gate arrays (FPGAs) boot from their respective non-volatile storage devices, they initialize their respective data transceiver control modules, with one set as the master and the other as the slave, awaiting the establishment of a communication link. For example, the first FPGA is set as the master and the second as the slave. The first and second FPGAs initialize their respective peripheral component interconnect (PCI) fast bus control modules via their respective processors. After completing these operations, the PCI fast bus control module of the first FPGA reads data packets from the first PCI fast bus device and stores the read data packets in the data buffer module. The processor of the first FPGA sends the data in the data buffer module to the data transceiver control module. The data transceiver control module processes the data and outputs the processed data to the second FPGA via a photoelectric conversion module and the optical fiber. The data transceiver control module of the second FPGA processes the received data. The processor of the second FPGA stores the processed data in the data buffer module. The Peripheral Component Interconnect Fast Bus (PCB) control module of the second field-programmable gate array (FPGA) sends data from the data buffer module to the second PCB device.

[0093] In some embodiments, the first field programmable gate array includes a processor, a peripheral component interconnect fast bus control module, a data cache module, a data transceiver control module and an Ethernet control module; the peripheral component interconnect fast bus control module is used to read data packets from the first peripheral component interconnect fast bus device and store the read data packets into the data cache module; the processor is used to send data in the data cache module to the data transceiver control module; the data transceiver control module is used to output data through the optical fiber, and the Ethernet control module is used to receive program files sent by the host computer via Ethernet.

[0094] In addition to receiving program files sent by the host computer via Ethernet, the first field-programmable gate array is also equipped with an Ethernet control module, which receives program files sent by the host computer via Ethernet.

[0095] In some embodiments, the Ethernet control module is further configured to display the operating status of the first field-programmable gate array itself, the current amount of data received and transmitted, and report error information.

[0096] This embodiment shows the working status of the first field-programmable gate array itself. The current amount of data received and sent, as well as the reporting of error information, are executed by the Ethernet control module.

[0097] In some embodiments, the processor is a hard-core processor that integrates the peripheral component interconnect fast bus control module and the data cache module.

[0098] In this embodiment, the processor is a hard-core processor, and the hard-core processor integrates a peripheral component interconnection fast bus control module and a data cache module. The hard-core processor reads and caches data packets of the first peripheral component interconnection fast bus device.

[0099] In some embodiments, the first field-programmable gate array (FPGA) is a ZYNQ UltraScale+ series FPGA.

[0100] This series of field-programmable gate arrays comes with a built-in hard processor called ZYNQ UltraScale+ MPSoC, which includes a PCIe interface and control logic, greatly simplifying the engineering setup process.

[0101] This hard-core processor is configured via the ZYNQ UltraScale+ MPSoC IP core, with the PCIe interface selected and flash enabled. The processor itself integrates a peripheral component interconnect fast bus control module, primarily consisting of two sub-modules: Integrated Block for PCIE and AXI-PCIe Bridge. The Integrated Block for PCIE mainly implements the PCIE protocol. The AXI-PCIe Bridge's main function is to convert between PCIe and AXI protocols, as well as to translate entry / exit addresses, providing specific services for DMA and Root Port / Endpoint (RP / EP) mode switching. In the PCIe tab configuration interface, the device port type can be selected as Root Port or Endpoint based on the actual situation. The number of channels can be selected as 4, and the link rate can be selected as 5.0Gb / s, i.e., the PCIe gen2 standard. Other settings such as device ID, BAR quantity, type, size, and interrupt settings can be flexibly selected.

[0102] When configuring the AXI Chip2Chip Bridge IP core, select Master or Slave as the global configuration option. For the port physical layer (PHY), select Xilinx's Aurora 64B / 66B to convert chip2chip data to high-speed serial transceiver (GT) data.

[0103] When configuring the Aurora 64B66B IP core, the physical layer high-speed transceiver type should be selected based on the device model, and can be GTH. The line rate and number of channels can be selected according to requirements; the line rate can be 16Gbps, and the number of channels can be 4. Select stream mode for the link layer interface. Select full-duplex for the data stream mode.

[0104] Based on the ZYNQ UltraScale+ series field-programmable gate arrays described above, and using the above configuration, it can be applied to scenarios with a small amount of data transmission. For example, refer to... Figure 3 As shown, the first peripheral component interconnect (PCI) fast bus device is a video capture card, and the second PCI fast bus device is a hard disk. The first and second field-programmable gate arrays (FPGAs) are ZYNQ UltraScale+ series FPGAs, connected via fiber optic cable, and connected to the video capture card and hard disk respectively via PCIe interfaces. The first FPGA reads data packets from the video capture card and sends them to the second FPGA via fiber optic cable; the second FPGA then sends the data packets to the hard disk.

[0105] In some embodiments, the processor is a soft-core processor, and the soft-core processor is independent of the peripheral component interconnection fast bus control module and the data cache module.

[0106] In this embodiment, the processor is a soft-core processor, which does not integrate a peripheral component interconnection fast bus control module and a data cache module.

[0107] In some embodiments, the first field-programmable gate array is a Virtex UltraScale+ series field-programmable gate array.

[0108] The Virtex UltraScale+ series field programmable gate arrays do not have hard-core processors and can use the lightweight open source soft-core processor MicroBlaze.

[0109] The MicroBlaze IP core is used as a soft-core processor. The instruction and data interfaces on the Local Memory Bus are enabled. The bus type selected is AXI.

[0110] The DMA / Bridge Subsystem for PCI Express IP core serves as a fast bus control module for interconnecting peripheral components. Select AXI Bridge as the functional mode. Select Root Port or Endpoint as the device / port type based on the actual situation. The preferred maximum link rate is 16.0GT / s, i.e., PCIe gen 4. If the board device does not support this, select 8GT / s, i.e., PCIe gen 3. The number of channels is determined by data transmission requirements; 8 can be selected. Enable the AXI host interface to send data packets to chip2chip. Other detailed configurations, such as the PCIe ID setting, the number, type, and size of BARs, the number of user interrupt requests, and whether to enable the debug interface, can be flexibly adjusted based on the actual situation.

[0111] The data caching module uses the system cache IP core, which can alleviate potential mismatches between PCIe data exchange rates and processor operating speeds, as well as between PCIe and AXI transaction processing speeds. The host port consistency protocol is CCIX. The AXI control interface is preferably enabled. The data caching module primarily connects to the peripheral component interconnection fast bus control module via the AXI-stream interface and the CCIX protocol interface.

[0112] The AXI Interconnect IP acts as a bus router, responsible for connecting the processor to each module via the AXI bus and controlling each module. The number of channels is determined based on the actual situation.

[0113] The flash controller is an AXI QSPI flash IP core.

[0114] The data transmission and reception control module is written in Verilog HDL. Its main functions are to control the AURORA 64B66B and connect the data of the cache module to the AURORA 64B66B.

[0115] When configuring the Aurora 64B66B IP core, the physical layer high-speed transceiver type should be selected based on the device model; GTY is an option. The line rate and number of channels can be selected according to requirements; the line rate can be 25Gbps, and the number of channels can be 16. The link layer interface should be selected as stream mode. The data stream mode should be selected as full-duplex.

[0116] Interrupt signals from all modules are aggregated and connected to the processor's interrupt source.

[0117] When communicating with the host computer via Ethernet, the Ethernet controller is an AXI EthernetLite IP core, and the communication mode is full-duplex. The main functions of the Ethernet controller include real-time display of the field-programmable gate array's (FPGA) operating status, current data transmission and reception volume, error reporting, and remote updating of the FPGA's program.

[0118] Based on the above Virtex UltraScale+ series field programmable gate array and using the above configuration, it can be applied to scenarios with large amounts of data transmission. For example, refer to Figure 4 As shown, the first and second FPGAs are Virtex UltraScale+ series FPGAs, connected via optical fiber. They are also connected to the SSD and server, respectively, via PCIe interfaces. The first FPGA reads data packets from the SSD and sends them to the second FPGA via optical fiber. The second FPGA then sends the data packets to the server.

[0119] To remotely upgrade the first and second FPGAs, the host computer first accesses the first FPGA via Ethernet, burns the new binary program file into the flash memory using QSPI and chip2chip, and then power cycles the first FPGA to complete the upgrade. The first FPGA then sends the new binary program file to the second FPGA, which then burns the new binary program file into the flash memory. The second FPGA then power cycles to complete the upgrade.

[0120] In summary, the remote communication method provided by the present application is that the peripheral component interconnection fast bus device is connected to the field programmable gate array, the field programmable gate array connected to the peripheral component interconnection fast bus device at one end obtains the data packet of the peripheral component interconnection fast bus device, and finally transmits the data packet to the field programmable gate array connected to the peripheral component interconnection fast bus device at the other end through the optical fiber, and the field programmable gate array connected to the peripheral component interconnection fast bus device at the other end finally sends the data packet to the peripheral component interconnection fast bus device to which it is connected, thereby realizing remote communication between the peripheral component interconnection fast bus devices, and with the help of the field programmable gate array and the optical fiber, the rate of remote data transmission of the peripheral component interconnection fast bus device can be effectively improved. In addition, the method is highly flexible and can be adapted to a variety of application scenarios. In a scenario where a large amount of data is transmitted, multiple optical fiber channels can be used for simultaneous transmission. In a scenario where a small amount of data is transmitted, the optical fiber channels can be reduced, thereby reducing the occupation of logical resources.

[0121] This application also provides a remote communication device, which is described below and can be referred to in conjunction with the method described above. Please refer to... Figure 5 , Figure 5 This is a schematic diagram of a remote communication device provided in an embodiment of this application. The device is applied to a first field-programmable gate array (FPGA) in a field-programmable gate array (FPGA) group. The FPGA group includes N FPGAs, where N is greater than or equal to 2. The FPGAs are connected to each other via optical fibers. The first FPGA is connected to a first peripheral component interconnect (PCIe) fast bus device, including:

[0122] Acquisition unit 10 is used to acquire data packets from the first peripheral component interconnect fast bus device;

[0123] Transmission unit 20 is used to transmit data packets of the first peripheral component interconnect fast bus device to a second field programmable gate array connected to the second peripheral component interconnect fast bus device through optical fiber between field programmable gate arrays, so as to send data packets of the first peripheral component interconnect fast bus device to the second peripheral component interconnect fast bus device through the second field programmable gate array;

[0124] The receiving unit 30 is used to receive data packets from the second peripheral component interconnect fast bus device transmitted by the second field-programmable gate array through the optical fiber between the field-programmable gate arrays;

[0125] The sending unit 40 is used to send data packets from the second peripheral component interconnect fast bus device to the first peripheral component interconnect fast bus device.

[0126] Based on the above embodiments, as a specific implementation method, it further includes:

[0127] The first program receiving unit is used to receive the program file sent by the host computer via Ethernet and burn the program file to a non-volatile storage device.

[0128] Based on the above embodiments, as a specific implementation method, it further includes:

[0129] The program sending unit is used to send the program file to other field-programmable gate arrays via optical fiber, so that the other field-programmable gate arrays can burn the program file to their own non-volatile storage devices.

[0130] Based on the above embodiments, as a specific implementation method, it further includes:

[0131] The display unit is used to display the operating status of the first field-programmable gate array itself, the current amount of data received and transmitted, and reported error information.

[0132] Based on the above embodiments, as a specific implementation method, it further includes:

[0133] The second program receiving unit is used to receive program files sent by other field-programmable gate arrays via optical fiber and burn the program files to a non-volatile storage device.

[0134] Based on the above embodiments, as a specific implementation method, it further includes:

[0135] The processing unit is used to perform data packet verification, parallel-to-serial conversion, and encoding / decoding processing on the data packet.

[0136] Based on the above embodiments, as a specific implementation, the first field-programmable gate array includes a processor, a peripheral component interconnect (PCI) fast bus control module, a data cache module, and a data transceiver control module; the PCI fast bus control module is used to read data packets from the first PCI fast bus device and store the read data packets in the data cache module; the processor is used to send the data in the data cache module to the data transceiver control module; the data transceiver control module is used to output the data through the optical fiber.

[0137] Based on the above embodiment, as a specific implementation manner, the processor is configured to send the data in the data cache module to the data transceiver control module via an advanced extensible interface bus.

[0138] Based on the above embodiments, as a specific implementation method, it further includes:

[0139] The first initialization unit is used to perform initialization operations on the data transceiver control module and wait to establish a communication link with other field programmable gate arrays.

[0140] Based on the above embodiments, as a specific implementation method, it further includes:

[0141] The second initialization unit is used to initialize the peripheral component interconnection fast bus control module.

[0142] Based on the above embodiment, as a specific implementation method, the processor is a hard-core processor, and the hard-core processor integrates the peripheral component interconnect fast bus control module and the data cache module.

[0143] Based on the above embodiments, as a specific implementation method, the first field-programmable gate array is a ZYNQ UltraScale+ series field-programmable gate array.

[0144] Based on the above embodiments, as a specific implementation method, the processor is a soft-core processor, and the soft-core processor is independent of the peripheral component interconnection fast bus control module and the data cache module.

[0145] Based on the above embodiments, as a specific implementation method, the first field-programmable gate array is a Virtex UltraScale+ series field-programmable gate array.

[0146] Based on the above embodiments, as a specific implementation, the first field-programmable gate array includes a processor, a peripheral component interconnect (PCI) fast bus control module, a data cache module, a data transceiver control module, and an Ethernet control module; the PCI fast bus control module is used to read data packets from the first PCI fast bus device and store the read data packets in the data cache module; the processor is used to send the data in the data cache module to the data transceiver control module; the data transceiver control module is used to output the data through the optical fiber; and the Ethernet control module is used to receive program files sent by the host computer via Ethernet.

[0147] Based on the above embodiments, as a specific implementation method, the Ethernet control module is also used to display the working status of the first field-programmable gate array itself, the current amount of data received and sent, and report error information.

[0148] The remote communication device provided in this application connects a Peripheral Component Interconnect (PCI) Fast Bus (PCB) device to a Field-Programmable Gate Array (FPGA). One FPGA connected to the PCI acquires data packets from the PCI and transmits them via optical fiber to another FPGA connected to the PCI. The other FPGA then forwards the data packets to its connected PCI, enabling remote communication between PCI devices. The use of FPGAs and optical fiber effectively improves the data transmission rate of PCI devices. Furthermore, this device is highly flexible and adaptable to various application scenarios. In scenarios with large data transmission volumes, multiple optical fiber channels can transmit simultaneously; in scenarios with small data transmission volumes, the number of optical fiber channels can be reduced, thus minimizing logic resource consumption.

[0149] The present application also provides a remote communication system, including a field programmable gate array group; the field programmable gate array group includes N field programmable gate arrays, N is greater than or equal to 2, and each of the field programmable gate arrays is connected to each other through an optical fiber, the first field programmable gate array is connected to a first peripheral component interconnection rapid bus device, and the second field programmable gate array is connected to a second peripheral component interconnection rapid bus device; the first field programmable gate array is used to: obtain a data packet of the first peripheral component interconnection rapid bus device; transmit the data packet of the first peripheral component interconnection rapid bus device to the second field programmable gate array connected to the second peripheral component interconnection rapid bus device through the optical fiber between the field programmable gate arrays, so as to send the data packet of the first peripheral component interconnection rapid bus device to the second peripheral component interconnection rapid bus device through the second field programmable gate array; receive the data packet of the second peripheral component interconnection rapid bus device sent by the second field programmable gate array through the optical fiber between the field programmable gate arrays; and send the data packet of the second peripheral component interconnection rapid bus device to the first peripheral component interconnection rapid bus device.

[0150] For a description of the system provided in this application, please refer to the above method embodiments; further details will not be repeated here.

[0151] The remote communication system provided by the present application is that a peripheral component interconnection fast bus device is connected to a field programmable gate array, and the field programmable gate array connected to the peripheral component interconnection fast bus device at one end obtains a data packet of the peripheral component interconnection fast bus device, and finally transmits the data packet to the field programmable gate array connected to the peripheral component interconnection fast bus device at the other end through an optical fiber, and the field programmable gate array connected to the peripheral component interconnection fast bus device at the other end finally sends the data packet to the peripheral component interconnection fast bus device to which it is connected, thereby realizing remote communication between the peripheral component interconnection fast bus devices, and with the help of the field programmable gate array and the optical fiber, the rate of remote data transmission of the peripheral component interconnection fast bus device can be effectively improved. In addition, the system is highly flexible and can be adapted to a variety of application scenarios. In scenarios where a large amount of data is transmitted, multiple optical fiber channels can be used for simultaneous transmission. In scenarios where a small amount of data is transmitted, the number of optical fiber channels can be reduced, thereby reducing the occupation of logical resources.

[0152] This application also provides a medium storing a computer program, which, when executed by a processor, can perform the following steps:

[0153] Obtain the data packet from the first peripheral component interconnect fast bus device;

[0154] Data packets from the first peripheral component interconnect fast bus device are transmitted via optical fiber between field-programmable gate arrays to a second field-programmable gate array connected to the second peripheral component interconnect fast bus device, so that data packets from the first peripheral component interconnect fast bus device can be sent to the second peripheral component interconnect fast bus device through the second field-programmable gate array;

[0155] Receive data packets from the second peripheral component interconnect fast bus device transmitted by the second field-programmable gate array through the optical fiber between the field-programmable gate arrays;

[0156] The data packets of the second peripheral component interconnect fast bus device are sent to the first peripheral component interconnect fast bus device.

[0157] The medium can include various media that can store program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0158] For an introduction to the medium provided in this application, please refer to the above method embodiment, and this application will not go into details here.

[0159] The medium provided in this application connects a Peripheral Component Interconnect (PCI) Fast Bus (PCB) device to a Field-Programmable Gate Array (FPGA). One FPGA connected to the PCI acquires data packets from the PCI and transmits them via optical fiber to another FPGA connected to the PCI. The other FPGA then forwards the data packets to its connected PCI, enabling remote communication between PCI devices. The use of FPGAs and optical fiber effectively improves the data transmission rate of PCI devices remotely. Furthermore, this solution is highly flexible and adaptable to various application scenarios. In scenarios with large data transmission volumes, multiple optical fiber channels can be used for simultaneous transmission; in scenarios with small data transmission volumes, the number of optical fiber channels can be reduced, thus minimizing logic resource consumption.

[0160] The present invention also provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the following steps:

[0161] Obtain the data packet from the first peripheral component interconnect fast bus device;

[0162] Data packets from the first peripheral component interconnect fast bus device are transmitted via optical fiber between field-programmable gate arrays to a second field-programmable gate array connected to the second peripheral component interconnect fast bus device, so that data packets from the first peripheral component interconnect fast bus device can be sent to the second peripheral component interconnect fast bus device through the second field-programmable gate array;

[0163] Receive data packets from the second peripheral component interconnect fast bus device transmitted by the second field-programmable gate array through the optical fiber between the field-programmable gate arrays;

[0164] The data packets of the second peripheral component interconnect fast bus device are sent to the first peripheral component interconnect fast bus device.

[0165] The computer program product provided in this application connects a Peripheral Component Interconnect (PCI) Fast Bus (PCB) device to a Field-Programmable Gate Array (FPGA). One FPGA connected to the PCI acquires data packets from the PCI and transmits them via optical fiber to another FPGA connected to the PCI. The other FPGA then forwards the data packets to its connected PCI, enabling remote communication between PCI devices. The use of FPGAs and optical fiber effectively improves the data transmission rate of PCI devices remotely. Furthermore, this solution is highly flexible and adaptable to various application scenarios. In scenarios with large data transmission volumes, multiple optical fiber channels can be used for simultaneous transmission; in scenarios with small data transmission volumes, the number of optical fiber channels can be reduced, thus reducing logic resource consumption.

[0166] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatuses, devices, and media disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant details can be found in the method section.

[0167] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0168] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0169] The foregoing has provided a detailed description of the remote communication method, apparatus, system, medium, and computer program product provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A remote communication method, characterized in that: A first field programmable gate array in a field programmable gate array group, wherein the field programmable gate array group includes N field programmable gate arrays, where N is greater than or equal to 2, each of the field programmable gate arrays is connected via an optical fiber, and the first field programmable gate array is connected to a first peripheral component interconnection fast bus device, comprising: Acquire a data packet of the first peripheral component interconnection fast bus device; Transmitting the data packet of the first peripheral component interconnect fast bus device to the second field programmable gate array connected to the second peripheral component interconnect fast bus device through the optical fiber between the field programmable gate arrays, so as to send the data packet of the first peripheral component interconnect fast bus device to the second peripheral component interconnect fast bus device through the second field programmable gate array; receiving a data packet of the second peripheral component interconnect fast bus device sent by the second field programmable gate array through an optical fiber between field programmable gate arrays; The data packet of the second peripheral component interconnect fast bus device is sent to the first peripheral component interconnect fast bus device.

2. The remote communication method according to claim 1, characterized in that: Also includes: Receive the program file sent by the host computer through Ethernet, and burn the program file to the non-volatile storage device.

3. The remote communication method according to claim 2, characterized in that: Also includes: The program file is sent to other field programmable gate arrays through optical fibers so that other field programmable gate arrays can burn the program file into their own non-volatile storage devices.

4. The remote communication method according to claim 1, characterized in that: Also includes: Display the working status of the first field programmable gate array itself, the current amount of data received and sent, and report error information.

5. The remote communication method according to claim 1, characterized in that: Also includes: Receive program files sent by other field programmable gate arrays through optical fibers, and burn the program files into a non-volatile storage device.

6. The remote communication method according to claim 1, characterized in that: Also includes: The data packet is subjected to data packet verification, parallel-to-serial conversion, and encoding-decoding processing.

7. The remote communication method according to claim 1, characterized in that: The first field programmable gate array includes a processor, a peripheral component interconnect fast bus control module, a data cache module, and a data transceiver control module; the peripheral component interconnect fast bus control module is used to read data packets from the first peripheral component interconnect fast bus device and store the read data packets into the data cache module; the processor is used to send the data in the data cache module to the data transceiver control module; the data transceiver control module is used to output the data through the optical fiber.

8. The remote communication method according to claim 7, characterized in that: The processor is used to send the data in the data cache module to the data transceiver control module through the advanced extensible interface bus.

9. The remote communication method according to claim 7, characterized in that: Also includes: The data transceiver control module is initialized and waits for a communication link to be established with other field programmable gate arrays.

10. The remote communication method according to claim 7, characterized in that: Also includes: Initialize the peripheral component interconnect fast bus control module.

11. The remote communication method according to claim 7, characterized in that: The processor is a hard-core processor, and the hard-core processor integrates the peripheral component interconnect fast bus control module and the data cache module.

12. The remote communication method according to claim 11, characterized in that: The first field programmable gate array is a ZYNQ UltraScale+ series field programmable gate array.

13. The device remote communication method according to claim 2, characterized in that: The processor is a soft-core processor, and the soft-core processor is independent of the peripheral component interconnection fast bus control module and the data cache module.

14. The remote communication method according to claim 12, characterized in that: The first field programmable gate array is a Virtex UltraScale+ series field programmable gate array.

15. The remote communication method according to claim 2, characterized in that: The first field programmable gate array includes a processor, a peripheral component interconnect fast bus control module, a data cache module, a data transceiver control module and an Ethernet control module; the peripheral component interconnect fast bus control module is used to read data packets from the first peripheral component interconnect fast bus device and store the read data packets into the data cache module; the processor is used to send the data in the data cache module to the data transceiver control module; the data transceiver control module is used to output the data through the optical fiber, and the Ethernet control module is used to receive the program file sent by the host computer through Ethernet.

16. The remote communication method according to claim 15, characterized in that: The Ethernet control module is also used to display the working status of the first field programmable gate array itself, the current amount of data received and sent, and report error information.

17. A remote communication device, characterized in that: A first field programmable gate array in a field programmable gate array group, wherein the field programmable gate array group includes N field programmable gate arrays, where N is greater than or equal to 2, each of the field programmable gate arrays is connected via an optical fiber, and the first field programmable gate array is connected to a first peripheral component interconnection fast bus device, comprising: An acquisition unit, configured to acquire a data packet of the first peripheral component interconnection fast bus device; a transmission unit, configured to transmit the data packet of the first peripheral component interconnection fast bus device to a second field programmable gate array connected to a second peripheral component interconnection fast bus device through an optical fiber between field programmable gate arrays, so as to send the data packet of the first peripheral component interconnection fast bus device to the second peripheral component interconnection fast bus device through the second field programmable gate array; A receiving unit, configured to receive a data packet of the second peripheral component interconnect fast bus device sent by the second field programmable gate array through an optical fiber between field programmable gate arrays; The sending unit is used to send the data packet of the second peripheral component interconnect fast bus device to the first peripheral component interconnect fast bus device.

18. A remote communication system, characterized in that: Includes: a field programmable gate array group; The field programmable gate array group includes N field programmable gate arrays, N is greater than or equal to 2, and the field programmable gate arrays are connected to each other through optical fibers, the first field programmable gate array is connected to the first peripheral component interconnection fast bus device, and the second field programmable gate array is connected to the second peripheral component interconnection fast bus device; the first field programmable gate array is used to: obtain a data packet of the first peripheral component interconnection fast bus device; transmit the data packet of the first peripheral component interconnection fast bus device to the second field programmable gate array connected to the second peripheral component interconnection fast bus device through the optical fiber between the field programmable gate arrays, so as to send the data packet of the first peripheral component interconnection fast bus device to the second peripheral component interconnection fast bus device through the second field programmable gate array; receive the data packet of the second peripheral component interconnection fast bus device sent by the second field programmable gate array through the optical fiber between the field programmable gate arrays; and send the data packet of the second peripheral component interconnection fast bus device to the first peripheral component interconnection fast bus device.

19. A medium, characterized in that The medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 16.

20. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the remote communication method according to any one of claims 1 to 16 are implemented.