Integrated circuit, method, system and computer program product for processing and recording network data

By integrating the integrated circuits of processors and coprocessors in the network system, the visibility problem of the network system in the design and modeling stages is solved, efficient network information recording and storage is realized, digital twin technology is supported, and the system is improved. Simulation and modeling capabilities.

CN115211087BActive Publication Date: 2024-11-29HUAWEI TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202080098139.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-03-25
Publication Date
2024-11-29
Estimated Expiration
2040-03-25

AI Technical Summary

Technical Problem

现有网络系统在设计和建模阶段缺乏足够的可见性和可观察性,导致维护和发展困难,尤其是在复杂网络应用程序中,传统的网络信息记录方案缺乏小型化、可定制性和灵活 性,难以实现实时分析。

Method used

An integrated circuit is provided, including a first processor for processing network data and a coprocessor for recording network data. By embedding a coprocessor in a single integrated circuit, high-performance and flexible network information recording is achieved, and the Real-time data recording and storage, and can be combined with analog devices to realize digital twin technology.

Benefits of technology

Through the design of integrated circuits, efficient recording and storage of network information is achieved, sufficient visibility and flexibility are provided, virtual model development of complex physical systems is supported, simulation and modeling capabilities of network systems are improved, and applicable to multiple Actual use cases for the industry.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115211087B_ABST
    Figure CN115211087B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of computer networks and network data recording. Therefore, the present invention provides an integrated circuit (100) for processing and recording network data, wherein the integrated circuit (100) comprises: a first processor (101) for processing a plurality of network data packets (102) obtained from one or more input ports (103) of the integrated circuit (100) and forwarding the plurality of network data packets (102) to one or more output ports (104) of the integrated circuit (100); a coprocessor (105) separate from the first processor (101) for obtaining a copy (106) of the plurality of network data packets (102) from the first processor (101) and / or from the integrated circuit (100), and aggregating a network information record (107) based on the copy (106) of the plurality of network data packets (102), wherein the network information record (107) comprises information (108) about the plurality of network data packets (102).
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of network systems and network data recording. Specifically, an integrated circuit is provided, the integrated circuit comprising a first processor for conventionally processing network data and a coprocessor for recording network data, the coprocessor being separate from the first processor. In addition, a system is provided, the system comprising an integrated circuit and an analog device, wherein the analog device implements a digital twin technology for processing network information records obtained from the integrated circuit. Background Art

[0002] Currently, the task of developing and configuring network systems is a huge challenge, especially when complex network applications are part of the network system. One of the main reasons is the lack of sufficient visibility and observability of network system properties in the early design and modeling stages, as well as in the later verification and validation stages (e.g., due to lack of proper network information logging). This creates troubles for the maintenance and development of such network systems. Therefore, the lack of said visibility persists throughout the life cycle of the network system.

[0003] Taking the automotive industry as an example, the current trend is for networked systems to become a core part of the vehicle, bringing features such as modularity, scalability, and configurability into the backbone of the vehicle. However, the growth of networked systems is not only in the automotive or transportation sectors, but also across all industries. Typically, these networked systems are implemented by electronic control units (ECUs) or integrated hardware. Therefore, simulating networked systems for any type of use case becomes an important aspect of the design and modeling phase.

[0004] In order to develop precise dynamic models that can accurately simulate physical systems (such as the network systems in a vehicle), the simulation or model needs to have access to sufficient data (such as data obtained through network information logging). Often, the lack of such data is a major obstacle to the implementation of dynamic models. This problem is not limited to automotive use cases and generally applies to the simulation of various network systems.

[0005] The traditional solution for recording the network information required for simulation and modeling is to use independent and expensive test and measurement equipment (such as data loggers, digital oscilloscopes, etc.) to monitor the network system under test. However, these traditional solutions involve the following disadvantages: lack of miniaturization, lack of customizability and flexibility, lack of memory space or computing performance for real-time analysis. In other words, in the prior art, there is a lack of a network information recording solution that is small in size, high in performance, and can be flexibly integrated into other devices. Summary of the invention

[0006] In view of the above problems, the embodiments of the present invention aim to improve the traditional network information recording solution.

[0007] Said object is achieved by the embodiments of the invention described in the attached independent claims. Advantageous implementations of the embodiments of the invention are further defined in the dependent claims.

[0008] A first aspect of the present invention provides an integrated circuit for processing and recording network data, wherein the integrated circuit includes: a first processor, for processing multiple network data packets obtained from one or more input ports of the integrated circuit, and forwarding the multiple network data packets to one or more output ports of the integrated circuit; a coprocessor separate from the first processor, for obtaining copies of the multiple network data packets from the first processor and / or from the integrated circuit, and aggregating network information records based on the copies of the multiple network data packets, wherein the network information records include information about the multiple network data packets.

[0009] This is advantageous because conventional network processing devices (e.g., switches, routers, etc.) are extended with embedded co-processing capabilities that can be dedicated to aggregate network information logging. Specifically, this is achieved by providing an integrated circuit with a processor for network processing and a separate processor for network information logging. By doing so, sufficient network information visibility can be obtained, and core features such as high performance, flexible integration into other devices, and small size can be achieved.

[0010] This is also advantageous because of the compactness and miniaturization aspects achieved by providing a solution for network information recording in a single integrated circuit.

[0011] By making the data flowing through network systems accessible, virtual models / simulations or digital twins of complex physical systems can be developed, which are becoming increasingly important in many real-world use cases in the industry. The implementation of digital twins can be related not only to any functionality or application distributed across multiple entities or devices interconnected by a communication network, but also to the inherent functionality of the network itself, i.e. a network digital twin is understood as a simulation model of a communication network, its operating environment and the application traffic it carries, thereby modeling the performance characteristics of physical network devices (such as bridges, switches or routers).

[0012] According to some embodiments, the integrated circuit may be a system on a chip (SoC).

[0013] According to some embodiments, the copy of the network data packet may be any information representing the network data packet and its contents.

[0014] According to some embodiments, the first processor may be implemented by a first processing core. Specifically, the coprocessor is implemented by a separate processing core. According to some embodiments, the power of the coprocessor and the power of the first processor may be equal. According to some embodiments, the power of the coprocessor may be different from the power of the first processor. For example, the power of the coprocessor is less than or greater than the power of the first processor.

[0015] According to some embodiments, the first processor may be a primary processor, a main processor, or a central processor.

[0016] According to some embodiments, the first processor may be used for at least one of the following: network data switching, network data routing, network data bridging, and network data forwarding.

[0017] According to some embodiments, network information records may be aggregated based on the content of each copy of the network data packet.

[0018] According to some embodiments, the copy obtained by the coprocessor may be a copy of the network data packet obtained by the first processor. In other words, the first processor may receive the network data packet as part of the network traffic received by the integrated circuit. The first processor copies the received network data packet and forwards the copy to the coprocessor for network data recording. Alternatively, the copying is performed directly by the coprocessor based on a single or multiple network data packets received by the first processor and / or by the integrated circuit. To this end, the first processor may provide information about each network data packet to the coprocessor. In either case, conventional network switching (including forwarding, routing, or bridging) is then applied to the network data packet originally received by the first processor.

[0019] According to some embodiments, a co-processor may be a computer processor used to supplement the functionality of a first processor.

[0020] According to some embodiments, a co-processor may be used to implement network data logging at the hardware level.

[0021] According to some embodiments, a network information record may include information about each of a single or multiple network data packets.

[0022] According to some embodiments, the network data packet and / or the replica may be a data packet at the data link layer (e.g., OSI layer 2). Alternatively, the network data packet and / or the replica may be a data packet at one of the following layers: network layer (e.g., OSI layer 3), transport layer (e.g., OSI layer 4), session layer (e.g., OSI layer 5), presentation layer (e.g., OSI layer 6), application layer (e.g., OSI layer 7).

[0023] According to some embodiments, the network data packet and / or the replica may be an Ethernet frame, or a message in a controller area network (CAN) bus, or a message in a local interconnect network (LIN) bus, or a message in a FlexRay bus, or a message in a peripheral component interconnect express (PCIe) bus.

[0024] This is advantageous because a separate processor can be provided to the first processor. The coprocessor can use its computing power exclusively for network data recording, thereby making network data recording more effective and efficient. In particular, the coprocessor ensures that network data is recorded in real time and instantaneously. More specifically, the power of the main processor (e.g. network switching or routing) is not affected by the coprocessor. This is also advantageous because the first processor and the coprocessor can be provided as a single unit, i.e. as an integrated circuit.

[0025] In an implementation manner of the first aspect, the coprocessor is used to specifically implement network data logging.

[0026] This is advantageous because the processing power of one coprocessor can be dedicated to network data logging. The coprocessor can, for example, implement the network data logging functionality in hardware.

[0027] In another implementation of the first aspect, the coprocessor is configured to add a timestamp to each of the copies to aggregate the network information record.

[0028] This ensures that network traffic scenarios recorded by the integrated circuit can be reconstructed, for example, during testing or simulation, thereby guaranteeing time-invariant characteristics.

[0029] In another implementation of the first aspect, the coprocessor is used to compress each of the copies to aggregate the network information record.

[0030] This ensures that the network information record can be stored in an efficient manner. This helps to protect storage capacity when storing the network information record, or protect bandwidth when providing the network information record to an external device via a network connection.

[0031] According to some embodiments, the coprocessor may be further configured to reshape the frame format of each of the replicas to aggregate the network information record. The reshaping of the frame format is implemented, for example, by a predefined protocol.

[0032] In another implementation of the first aspect, the coprocessor is used to encrypt each of the copies to aggregate the network information record.

[0033] This ensures the security of the network information records in internal data storage and external data transmission scenarios.

[0034] In another implementation of the first aspect, the coprocessor is used to configure a header and / or a tail of each of the replicas to aggregate the network information record.

[0035] According to some embodiments, the tail of each of the replicas may be used to aggregate data packet redundancy information for reliability and integrity checking of the corresponding replica.

[0036] This enables pre-processing of copies of the network data packets forming the network information record. Thus, the network information record can be post-processed more efficiently.

[0037] In another implementation of the first aspect, the replicas are associated with multiple input ports of the integrated circuit, and the coprocessor is used to arrange the replicas in a time order and / or sequence order corresponding to the input ports to aggregate the network information records.

[0038] According to some embodiments, the temporal order and / or sequential order is obtained based on timestamps added to the replicas.

[0039] According to some embodiments, the copies of the data packet may be arranged in a temporal order and / or a sequential order based on a timestamp in each copy of the data packet. The timestamp may be obtained, for example, as described above. Specifically, the plural number of copies (written as one or more copies) means greater than or equal to 2.

[0040] This ensures that the integrated circuit can be used when information from a plurality of input ports has to be processed. Specifically, the input ports are ingress ports.

[0041] In another implementation of the first aspect, the integrated circuit includes a memory, wherein the coprocessor is configured to provide the network information record to the memory.

[0042] This is advantageous because the integrated circuit can provide the network information record to the memory if no other entity is present for receiving the network information record.

[0043] In another implementation of the first aspect, the memory includes a volatile memory for queuing and / or buffering the network information record and / or a non-volatile memory for storing the network information record.

[0044] This is advantageous because, for example, if an external device for receiving the network information record is temporarily unavailable, for example, due to overload, the integrated circuit can queue the network information record and / or buffer the network information record. This is advantageous because, for example, if the network information record is to be analyzed later, for example in a laboratory environment, the integrated circuit can store the network information record. In particular, the integrated circuit includes a volatile memory and a non-volatile memory. This ensures that the integrated circuit can implement queues and / or buffering as well as storage.

[0045] In another implementation of the first aspect, the coprocessor is used to provide the network information record to the external entity.

[0046] According to some embodiments, the coprocessor may be used to read the network information record from the memory to provide the network information record to the external entity. According to some embodiments, the coprocessor may be used to provide the network information record to the external entity directly after aggregating the network information record. That is, the network information record may be provided directly and immediately after obtaining it, and / or the network information record may be stored in a volatile memory and / or a non-volatile memory and provided to the external entity from the volatile memory and / or the non-volatile memory. According to some embodiments, the network information record may be provided to the external entity via one or more monitoring ports of the integrated circuit. According to some embodiments, the network information record may be provided to the external entity via one or more output ports of the integrated circuit.

[0047] In another implementation of the first aspect, the coprocessor and / or the processor is further used to create a new network data packet and / or inject a new network data packet into the one or more output ports, wherein the coprocessor is further used to aggregate the network information record based on the new network data packet.

[0048] According to some embodiments, the new network data packet and / or its format may be configured by a user. Specifically, such a new data injection task performed by the coprocessor or the processor is user-selectable / configurable.

[0049] This is advantageous because by activating / enabling this new network packet injection functionality, the integrated circuit is no longer a passive agent in the network, but an active agent capable of modifying the entire network activity with new network packets.

[0050] A second aspect of the present invention provides a method for processing and recording network data, wherein the method includes the following steps: a first processor of an integrated circuit processes multiple network data packets obtained from one or more input ports of the integrated circuit; the first processor forwards the multiple data packets to one or more output ports of the integrated circuit; a coprocessor of the integrated circuit obtains copies of the multiple network data packets from the first processor and / or from the integrated circuit, wherein the coprocessor is separate from the first processor; the coprocessor aggregates network information records based on the copies of the multiple network data packets, wherein the network information records include information about the multiple network data packets.

[0051] In an implementation manner of the second aspect, the method further includes: the coprocessor specifically implements network data logging.

[0052] In another implementation of the second aspect, the method further includes: the coprocessor adding a timestamp to each of the copies to aggregate the network information record.

[0053] In another implementation of the second aspect, the method further includes: the coprocessor compressing each of the copies to aggregate the network information record.

[0054] In another implementation of the second aspect, the method further includes: the coprocessor encrypting each of the copies to aggregate the network information record.

[0055] In another implementation of the second aspect, the method also includes: the coprocessor configures the header of each of the replicas to aggregate the network information record, and configures the tail of each of the replicas to aggregate data packet redundant information, for performing reliability and integrity checks on the obtained replica data packets with aggregated network information records.

[0056] In another implementation of the second aspect, the replicas are associated with a plurality of input ports of the integrated circuit, and the method further comprises: the coprocessor arranging the replicas in a sequence order corresponding to the input ports to aggregate the network information records.

[0057] In another implementation of the second aspect, the integrated circuit includes a memory, wherein the method further includes: the coprocessor providing the network information record to the memory.

[0058] In another implementation of the second aspect, the memory includes a volatile memory for queuing or buffering the network information record and / or a non-volatile memory for storing the network information record.

[0059] In another implementation of the second aspect, the method further includes: the coprocessor providing the network information record to an external entity.

[0060] In another implementation of the second aspect, the method further includes: the coprocessor and / or the processor creates a new network data packet and / or injects a new network data packet into the one or more output ports; the coprocessor also aggregates the network information record based on the new network data packet.

[0061] The second aspect and its implementations include the same advantages as the first aspect and its corresponding implementations.

[0062] A third aspect of the present invention provides a computer program product, comprising instructions, which, when executed by a computer, cause the computer to perform the steps of the method according to the second aspect or any implementation thereof.

[0063] The third aspect and its implementations include the same advantages as the second aspect and its corresponding implementations.

[0064] A fourth aspect of the present invention provides a non-transitory computer-readable storage medium, comprising instructions, which, when executed by a computer, cause the computer to perform the steps of the method according to the second aspect or any implementation thereof.

[0065] The fourth aspect and its implementations include the same advantages as the second aspect and its corresponding implementations.

[0066] The fifth aspect of the present invention provides a system, comprising an integrated circuit and an analog device according to the first aspect or any one of its implementations, wherein the integrated circuit is used to provide the network information record to the analog device, and wherein the analog device implements digital twin technology for processing the network information record.

[0067] This ensures that through digital twin technology, mathematical models that fully describe the dynamic behavior of real physical systems can be applied to network information recording.

[0068] The fifth aspect and its implementations include the same advantages as the first aspect and its corresponding implementations.

[0069] The sixth aspect of the present invention provides a method, comprising the following steps: the integrated circuit according to the first aspect or any implementation method thereof provides network information records to an analog device; the analog device implements digital twin technology to process the network information records.

[0070] The sixth aspect and its implementations include the same advantages as the fifth aspect and its respective implementations.

[0071] A seventh aspect of the present invention provides a computer program product comprising instructions which, when executed by a computer, cause the computer to perform the steps according to the sixth aspect.

[0072] The seventh aspect and its implementations include the same advantages as the sixth aspect and its respective implementations.

[0073] An eighth aspect of the present invention provides a non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to perform the steps of the method described in the sixth aspect.

[0074] The eighth aspect and its implementation include the same advantages as the sixth aspect and its corresponding implementation.

[0075] It should be noted that all devices, elements, units and modules described in this application can be implemented by software or hardware elements or any type of combination thereof. All steps performed by various entities described in this application and the functions to be performed by various entities described are intended to refer to the corresponding entities for performing the corresponding steps and functions. Although in the description of the following specific embodiments, the specific functions or steps performed by external entities are not reflected in the description of the specific detailed elements of the entities performing the specific steps or functions, it should be clear to the technician that these methods and functions can be implemented by corresponding hardware or software elements or any combination thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The above aspects and implementations of the present invention are described in the following description of specific embodiments in conjunction with the accompanying drawings, in which:

[0077] Figure 1 A schematic diagram of an integrated circuit provided by an embodiment of the present invention is shown.

[0078] Figure 2 The schematic diagram of the integrated circuit provided by the embodiment of the present invention is shown in more detail.

[0079] Figure 3 A schematic diagram showing an operation scenario provided by the present invention.

[0080] Figure 4 A schematic diagram of an integrated circuit provided by the present invention is shown.

[0081] Figure 5 Another schematic diagram of the integrated circuit provided by the present invention is shown.

[0082] Figure 6 Another schematic diagram of the integrated circuit provided by the present invention is shown.

[0083] Figure 7 A schematic diagram of a method provided by an embodiment of the present invention is shown.

[0084] Figure 8 A schematic diagram of a system provided by an embodiment of the present invention is shown.

[0085] Fig. 9 A schematic diagram of a method provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0086] Figure 1 Schematic diagram of an integrated circuit 100 provided by an embodiment of the present invention is shown. The integrated circuit 100 is used to process and record network data, and includes two separate processors, a first processor 101 and a coprocessor 105. The integrated circuit 100 may be, for example, an ECU or a system on a chip (SoC). For example, the first processor 101 is implemented by a first processing core, and the coprocessor 105 is implemented by a separate processing core.

[0087] The first processor 101 is used to process a plurality of network packets 102 obtained from one or more input ports 103 of the integrated circuit 100, and forward a plurality of network packets 109 to one or more output ports 104 of the integrated circuit 100. The plurality of network packets 109 are a plurality of network packets 102 that have optionally been processed and / or modified by the first processor 101. In other words, the first processor 101 implements conventional network processing (e.g., performed in a switch, router, bridge, etc.). Although Figure 1 Only one input port 103 is shown in the figure, but the integrated circuit 100 may have any number of input ports 103. Figure 1 Only one output port 104 is shown in FIG. 1 , but the integrated circuit 100 may have any number of output ports 104 .

[0088] To extend conventional network processing (implemented by the first processor 101 ), the coprocessor 105 is separate from the first processor 101 and is configured to obtain a copy 106 of the plurality of network data packets 102 from the first processor 101 and / or from the integrated circuit 100 .

[0089] The first processor 101 may forward the selected replica 106 to the coprocessor 105 , or the coprocessor 105 may obtain the replica 106 itself, for example running in a parallel data path of the integrated circuit 100 (without interfering with the behavior of the first processor 101 ).

[0090] The coprocessor 105 is further configured to aggregate a network information record 107 based on the copies 106 of the plurality of network packets 102, wherein the network information record 107 includes information 108 about the plurality of network packets 102. That is, by aggregation, the information about each network packet 102 is stored in a single information fragment (i.e., a network information record).

[0091] The first processor 101 and the coprocessor 105 are integrated in the same electronic chip. In other words, the on-chip data recording function is embedded in the network switching chip (or routing chip or bridge chip). The network switching function and the recording function are seamlessly interconnected to improve the performance of network information recording.

[0092] Both the switching function and the recording function can be configured by the user, that is, the user can define what type of network packets 102, 109 can be switched from an input port 103 to an output port 104. For the recording function, the user can define what type of network packets 102 can be captured for recording. This can be managed by configurable parameters of the integrated circuit 100.

[0093] To meet real-time constraints and performance requirements, coprocessor 105 may perform the logging functions directly in hardware (e.g., via a custom processing core synthesized in logic units and exploiting parallelism and pipelining) rather than in software (e.g., a sequence of instructions executed on a processor).

[0094] The integrated circuit 100 may optionally process the network data packet 102 at layer 2 or higher (layer 3 to layer 7) of the OSI model. The network data packet 102 may be an Ethernet frame forwarded through different ports of an Ethernet switch or router, or other messages, such as in a CAN bus or LIN bus in a vehicle.

[0095] The integrated circuit 100 may optionally be a standardized hardware solution that can be used in SoC devices across many network application fields (eg, automotive, smart manufacturing, information technology, aerospace, military, or health equipment).

[0096] The first processor 101 and / or the coprocessor 105 may optionally implement an open and standardized software architecture for an automotive ECU, for example for defining software components, libraries or application programming interfaces.

[0097] In other words, the integrated circuit 100 enables aggregation of network information records 107 (e.g., log reports) to evaluate the status and functional behavior of the network system. In addition, by using the network information records 107 as an input stimulus for the digital functional twin of the network system, verification, validation, and predictive maintenance of the network system can be performed.

[0098] Optionally, the coprocessor 105 is used to implement network data logging exclusively, so as to clearly separate the network logging function from the traditional network processing in the first processor 101 .

[0099] Figure 2 The schematic diagram of the integrated circuit 100 provided by the embodiment of the present invention is shown in more detail. Figure 2 The integrated circuit 100 shown includes Figure 1 All features and functions of integrated circuit 100, as well as the following optional features.

[0100] like Figure 2 As shown, the integrated circuit 100 may also include a memory 201, and the coprocessor 105 may provide the network information record 107 to the memory 201. The memory 201 may include, for example, a volatile memory 201a for queuing or buffering the network information record 107 and / or a non-volatile memory 201b for storing the network information record 107. The network information record 107 may then be provided to an external entity from the memory 201. Furthermore, in general, the memory may be on-chip or off-chip, and may be within or outside the system, such as a hard drive memory or a pen drive that may be plugged into the system or the integrated circuit 100.

[0101] However, the network information record 107 can also be sent directly to an external device (outside the integrated circuit 100) according to predefined traffic shaping, scheduling and adaptation rules. Thus, a transmission speed according to the requirements of the receiver or the state of the network (for example, if the receiver or the network is overloaded, the transmission rate is reduced to prevent packet loss) can be achieved.

[0102] In any of the above cases, the external entity can optionally restore / decompress the network information record 107 to obtain the original network data packet 102 captured by the integrated circuit 100. In this way, the recording process is transparent and the external entity can synthesize a non-intrusive digital twin.

[0103] Also like Figure 2 As shown in , the coprocessor 105 and / or the processor 101 can optionally be used to create a new network data packet 202 and / or inject the new network data packet 202 into one or more output ports 104, and the coprocessor 105 can be used to aggregate the network information record 107 also based on the new network data packet 202.

[0104] Figure 3 A schematic diagram showing an operating scenario of the integrated circuit 100 is shown. Figure 3 As shown, the functions of the integrated circuit 100 may be grouped into three blocks 301 , 302 , 303 .

[0105] The first block 301 involves real-time and immediate processing of network data packets 102, 106, and their copies arriving at the integrated circuit 100. For example, the coprocessor 105 may optionally be used to add a timestamp to each of the copies 106 to aggregate the network information record 107.

[0106] The second block 302 involves formatting the copies 106 of the data packets 102 according to a set of rules and storing / queuing / buffering them in memory or forwarding them directly to one or more recording ports.

[0107] For example, coprocessor 105 may optionally be used to compress each of replicas 106 to aggregate network information record 107. Compression may be configured by a user of integrated circuit 100. This includes optional reshaping of the frame format of replicas 106 according to a predefined protocol.

[0108] According to another example, the coprocessor 105 may optionally be used to encrypt each of the copies 106 to aggregate the network information record 107. The encryption may be configurable by a user of the integrated circuit 100.

[0109] According to another example, the coprocessor 105 can optionally be used to configure the header and / or tail of each of the replicas 106 to aggregate the network information record 107. The tail of each of the replicas 106 can be used to aggregate data packet redundancy information for reliability and integrity checking of such obtained replicas.

[0110] Specifically, various information related to interpreting the replica 106 or the corresponding network data packet 102 is placed in the header of each replica 106. All information placed in the header is configurable according to a set of system parameters that the user may have previously configured during the setup of the integrated circuit 100.

[0111] According to another example, the coprocessor 105 may optionally be used to apply packetization to each of the replicas 106 to aggregate the network information record 107 .

[0112] Packetization refers to the information associated with one or more replicas 106 being formatted, shaped, or stored in a predefined format. For example, if two frames have the same source address and destination address, the two frames can be grouped into one frame. These aspects can be configured by the user during the setup process.

[0113] The third block 303 relates to output data processing, for example, to which output port 104 the network data packet 109 will be provided, or a new data packet 202 may be created and injected into the output port 104 .

[0114] The functions defined in blocks 301, 302, and 303 are implemented by the first processor 101 and / or the coprocessor 105 at a hardware level in the integrated circuit 100, for example by exploiting parallelism and pipeline design techniques, thereby achieving a high level of performance. Distributing network data processing to the first processor 101 and distributing network data logging to the coprocessor 105 also ensures that normal operation or quality of service (QoS) of the integrated circuit 100 is not affected by the aggregate logging information 107.

[0115] Figure 4 FIG. 1 is a schematic diagram of an integrated circuit 100 provided by the present invention, which is implemented as an automotive vehicle network chip, for example. Figure 4 As shown, the integrated circuit 100 uses a system bus / network on chip that is accessible by both the first processor 101 and the coprocessor 105 .

[0116] Figure 5 Another schematic diagram of the integrated circuit 100 provided by the present invention is shown. More specifically, Figure 5 A multi-port Ethernet local area network (LAN) switch (also referred to as a "LSW") is shown, which uses an integrated circuit 100 and, for example, consists of several ports and operates, for example, on Ethernet frames at layer 2 (but optionally also any other network data packets 102 mentioned herein).

[0117] exist Figure 5 In the integrated circuit shown, the coprocessor 105 is shown as a dedicated peripheral device or intellectual property (IP) core (labeled as "data recorder and digital twin core") inside the LSW. The IP core is responsible for capturing at least one ingress port ( Figure 5 The input port 103 on the left labeled "PHY" and at least one output port ( Figure 5 At least one network data packet 102 flowing between the output port 104 (labeled as "PHY" on the right), formatting (e.g., packetization, compression, line-speed encryption) and storing them in a storage unit (e.g., memory 201), such as DDR4 memory, and finally transmitting them to the outside, for example through a dedicated recording port 501, which follows specific traffic shaping rules that can be configured by the user.

[0118] Figure 6Another schematic diagram of the integrated circuit 100 provided by the present invention is shown. In order to improve the performance of the recording process (for example, to establish a low-latency data path or data storage space optimization), optionally, a copy 106 of the network data packet 102 can be temporarily stored and can also be packetized, compressed and / or encrypted on the fly before the copy is written as a network information record 107 to the memory 201, and can then be depacketized, decompressed and decrypted when the network information record 107 is read from the memory 201 or even later when the recorded network data packet 109 arrives at the external analog or digital twin device 801, as shown below with reference to Figure 8 As described in.

[0119] To this end, the integrated circuit 100 may perform the following optional steps:

[0120] 1. A network packet 102 arrives at an input port 103 of the integrated circuit 100. A copy 106 of the network packet 102 is obtained by the first processor 101, the coprocessor 105 or the integrated circuit 100.

[0121] 2. Time stamp the replicas 106 instantly so that the replicas 106 are marked and / or tracked in real time and queued through the on-chip input buffer / FIFO memory according to the corresponding input port 103 .

[0122] 3. The optional input port arbiter of the integrated circuit 100 is responsible for multiplexing the replicas 106 corresponding to the N input ports 103 according to a predefined priority rule, for example, converting the data flow from parallel to serial. In other words, the replicas 106 are associated with multiple input ports 103 of the integrated circuit 100, and the coprocessor 105 arranges the replicas 106 in a serial order (for example, corresponding to the time order of arrival of network data packets in the input ports 103).

[0123] 4. The serialized incoming copy 106 is formatted (e.g., compressed, encrypted, has its header information added / edited, etc.) before being stored in the memory 201 or forwarded to an external entity (as an aggregated network information record 107). Figure 6 In FIG. 1 , the external memory is shown to be outside the integrated circuit 100. However, a memory 201 having the same function may also exist within the integrated circuit 100.

[0124] 5. Aggregate network information record 107 based on copy 106 of network data packet 102 through steps 1 to 4.

[0125] 6. An optional scheduler in the integrated circuit 100 is responsible for moving the network packet 102 or copy 106 to the next stage in the data path when necessary, optionally based on predefined traffic shaping rules.

[0126] 7. For example, the aggregated network information record 107 is provided to a specific egress record port (eg, port 501) and sent to the outside of the switch. This ensures a sufficient level of quality of service (thus complying with time performance factors such as delay or jitter).

[0127] It is important to note that all of these steps are performed without affecting the normal behavior of network data processing (i.e., the traditional operation of switches or routers).

[0128] In the following, three exemplary use cases in which the integrated circuit 100 may be used will be described:

[0129] Data recorder function: Through the network data recording function provided by the integrated circuit 100, visibility can be provided to the network data packets 102 flowing through the different input ports 103 and output ports 104 of the switch. That is, each electronic system equipped with the integrated circuit provides excellent network traffic visibility and observability to develop network applications based thereon. The integrated circuit 100 equipped with this technology enables network engineers to visualize communications in a user-friendly environment at any time.

[0130] Digital twin functionality: Developing a product with a switching chipset using the integrated circuit 100 enables virtualization of the functionality of the product through a digital twin, because the integrated circuit 100 can record network data packets 102 flowing through its input ports 103 (e.g., ingress ports) and output ports 104 (e.g., egress ports) in real time. The network data recording and digital twin functionality provide a basis for building virtualized and digital models of any product or functionality, such as simulations of network systems, such as in vehicles.

[0131] Event data recording capability: Similar to the mandatory presence of black boxes (i.e., flight data recorders) in aircraft, it is planned to mandate the installation of such information recording systems in autonomous vehicles (e.g., Level 3 to Level 5 autonomous driving) to help determine liability in the event of an accident. All types of vehicles (including trucks, buses, vans, utility vehicles, boats, drones, helicopters, airplanes) can be equipped with event data recorders using integrated circuit 100.

[0132] Figure 7 Schematic diagram of a method 700 provided by an embodiment of the present invention is shown. The method 700 is used for network data processing and network data recording, and thus comprises the following first step: a first processor 101 of an integrated circuit 100 processes (701) a plurality of network data packets 102 obtained from one or more input ports 103 of the integrated circuit 100, and the first processor 101 forwards the plurality of data packets 102 to one or more output ports 104 of the integrated circuit 100.

[0133] The method 700 comprises a second step in which a coprocessor 105 of the integrated circuit 100 obtains ( 702 ) the copies 106 of the plurality of network data packets 102 from the first processor 101 and / or the integrated circuit 100 , wherein the coprocessor 105 is separate from the first processor 101 .

[0134] The method 700 includes the following third step: the coprocessor 105 aggregates ( 703 ) the network information record 107 based on the copies 106 of the plurality of network data packets 102 , wherein the network information record 107 includes the information 108 about the plurality of network data packets 102 .

[0135] Figure 8 A schematic diagram of a system 800 provided by an embodiment of the present invention is shown. The system 800 is used to simulate a network system, specifically through digital twin technology. Therefore, the system 800 includes an integrated circuit 100 and an analog device 801 as described in any of the above embodiments. In order to simulate the network system, the integrated circuit 100 is used to provide a network information record 107 to the analog device 801. The analog device 801 is also used to implement the digital twin technology for processing the network information record 107.

[0136] By processing the digital twin technology of the network information record 107, the simulation device or computer can simulate and predict the behavior of the integrated circuit 100 itself or the network system in real time. This implementation method can also be called a network digital twin. In addition to the network digital twin, based on the information transmitted in the recorded network data packet 102, a mainly application-oriented digital twin can be provided. For example, based on the data related to temperature, voltage and current provided in the recorded data frame, the behavior of the battery (charge state, health state) in the vehicle is simulated.

[0137] In addition, the system 800 can restore or decompress the network information record 107 to extract and recover the original network data packet 102. For example, in the case of implementing a digital twin, the digital twin utilizes the same network data packet 102 processed in real time in the integrated circuit. The digital twin is completely non-intrusive and provides real-time information related to the network data packet 102 through a timestamp field attached to the header of each network data packet 102.

[0138] Fig. 9 The method 900 comprises the following first step: the integrated circuit 100 provides (901) network information 107 to the analog device 801, as described with reference to any of the above figures.

[0139] The method 900 includes the following second step: the simulation device 801 implements ( 902 ) the digital twin technology for processing the network information record 107 .

[0140] According to certain embodiments, in order for the simulated device 801 and / or the digital twin to utilize the network data packet 102, the aggregation step (also referred to as the formatting step) performed by the coprocessor 105 can be restored to obtain the network data packet 102 from the network information record 107 (e.g., by restoring the formatting and / or by decompressing, and / or by decrypting and / or by removing the timestamp of the network information record 107 to restore the original network data packet 102). Once this pre-processing step is performed to obtain the original data, the simulation or digital twin can be run.

[0141] The invention has been described in conjunction with various embodiments and implementations as examples. However, other variations will be understood and implemented by those skilled in the art in practicing the claimed invention, based on a study of the drawings, the present invention and the independent claims. In the claims and in the specification, the word "comprising" does not exclude other elements or steps, and "a" does not exclude a plurality. A single element or other unit may fulfil the functions of several entities or items described in the claims. The listing of certain measures in mutually different dependent claims does not indicate that a combination of these measures cannot be effectively used.

Claims

1. An integrated circuit (100) for processing and recording network data, characterized in that: The integrated circuit (100) comprises: A first processor (101) is configured to process a plurality of network data packets (102) obtained from one or more input ports (103) of the integrated circuit (100), and forward the plurality of network data packets (102) to one or more output ports (104) of the integrated circuit (100), a coprocessor (105) separate from the first processor (101), configured to obtain a copy (106) of the plurality of network packets (102) from the first processor (101) and / or from the integrated circuit (100), and to aggregate a network information record (107) based on the copy (106) of the plurality of network packets (102), wherein the network information record (107) includes information (108) about the plurality of network packets (102); The copy (106) is directly copied by the coprocessor (105) based on a single or multiple network data packets (102) received by the first processor (101) and / or the integrated circuit (100).

2. The integrated circuit (100) according to claim 1, characterized in that The coprocessor (105) is used to specifically implement network data recording.

3. The integrated circuit (100) according to claim 1 or 2, characterized in that: The coprocessor (105) is further configured to add a timestamp to each of the replicas (106) to aggregate the network information record (107).

4. The integrated circuit (100) according to claim 1 or 2, characterized in that: The coprocessor (105) is further configured to compress each of the copies (106) to aggregate the network information record (107).

5. The integrated circuit (100) according to claim 1 or 2, characterized in that: The coprocessor (105) is further configured to encrypt each of the copies (106) to aggregate the network information record (107).

6. The integrated circuit (100) according to claim 1 or 2, characterized in that: The coprocessor (105) is further configured to configure the head and / or tail of each of the replicas (106) to aggregate the network information record (107).

7. The integrated circuit (100) according to claim 1 or 2, characterized in that: The replicas (106) are associated with a plurality of input ports (103) of the integrated circuit (100), and wherein the coprocessor (105) is further configured to arrange the replicas in a temporal and / or sequential order to aggregate the network information record (107).

8. The integrated circuit (100) according to claim 1 or 2, characterized in that: It also includes a memory (201), wherein the coprocessor (105) is further configured to provide the network information record (107) to the memory (201).

9. The integrated circuit (100) according to claim 8, characterized in that The memory (201) includes a volatile memory (201a) for queuing and / or buffering the network information record (107) and / or a non-volatile memory (201b) for storing the network information record (107).

10. The integrated circuit (100) according to claim 1 or 2, characterized in that: The coprocessor (105) is used to provide the network information record (107) to an external entity.

11. The integrated circuit (100) according to claim 1 or 2, characterized in that: The coprocessor (105) is further configured to create a new network data packet and / or inject the new network data packet into the one or more output ports, and to aggregate the network information record (107) based on the new network data packet.

12. A method (700) for processing and recording network data, characterized in that: The method comprises the following steps: A first processor of an integrated circuit (100) processes a plurality of network data packets (102) obtained from one or more input ports (103) of the integrated circuit (100), and the first processor (101) forwards the plurality of network data packets (102) to one or more output ports (104) of the integrated circuit (100), A coprocessor (105) of the integrated circuit (100) obtains (702) a copy (106) of the plurality of network data packets (102) from the first processor (101) and / or from the integrated circuit (100), wherein the coprocessor (105) is separate from the first processor (101), The coprocessor (105) aggregates (703) a network information record (107) based on the copies (106) of the plurality of network data packets (102), wherein the network information record (107) includes information (108) about the plurality of network data packets (102); The copy (106) is directly copied by the coprocessor (105) based on a single or multiple network data packets (102) received by the first processor (101) and / or the integrated circuit (100).

13. A computer program product, characterized in that The method comprises instructions which, when executed by a computer, cause the computer to perform the steps of the method (700) according to claim 12.

14. A system (800) for processing and recording network data, characterized in that: It comprises an integrated circuit (100) and an analog device (801) according to any one of claims 1 to 11, wherein the integrated circuit (100) is used to provide the network information record (107) to the analog device (801), and the analog device (801) is used to implement digital twin technology for processing the network information record (107).

15. A method (900) for processing and recording network data, characterized in that: The following steps are involved: The integrated circuit (100) according to any one of claims 1 to 11, providing (901) a network information record (107) to an analog device (801), The simulation device (801) implements (902) digital twin technology to process the network information record (107).

16. A computer program product, characterized in that The method comprises instructions which, when executed by a computer, cause the computer to perform the steps of the method (900) according to claim 15.

Citation Information

Patent Citations

  • Packet capture

    US20140355613A1