Hardware-based efficient data forwarding

Abstract

The invention relates to a transmission device for efficiently forwarding data in a motor vehicle, which transmission device enables data to be efficiently transmitted over a single physical channel, for example, 128 virtual data paths. The proposed invention creates unidirectional devices, and these devices can thus be provided with less technical effort due to reduced complexity. The invention concerns in particular the requirements of automobiles, in which weight reduction and high fault tolerance are necessary. Weight reduction is achieved by simplifying conventional units, where only a single physical path is required, but these devices can process 128 virtual data paths. According to the invention, fault robustness is achieved by making the structural component unidirectional, and therefore, the structural component can be particularly easily created without erroneous structural features. The invention further relates to an input device in the transmission direction, which is partially functionally opposite to the output device in the reception direction, and to a packet data processing device in the transmission direction and in the reception direction, and to a system arrangement comprising the proposed transmission device and the proposed reception device. Furthermore, a method and a computer program product comprising the steps of the method are proposed, which computer program product is suitable for providing a system arrangement or input and output devices in a production plant. Further, a computer readable medium comprising control commands is presented.

Description

[0001] The present invention relates to a transmitting device for efficiently forwarding data in a car, which enables data to be efficiently transmitted on a single physical channel, for example, 128 virtual data paths. The proposed invention creates unidirectional devices, and these devices can be provided with less technical effort due to reduced complexity. The present invention pays special attention to the requirements of automobiles, where weight reduction and high fault tolerance are necessary. Weight reduction is achieved by simplifying conventional units, where only a single physical path is required, but these devices can handle 128 virtual data paths. According to the present invention, fault robustness is achieved by making the structural components unidirectional, and therefore, structural components can be created particularly easily without error-prone structural features. The present invention further relates to an input device in the transmission direction that is partially functionally opposite to an output device in the reception direction, and a packet data processing device in the transmission direction and in the reception direction, and to a system arrangement comprising the proposed transmitting device and the proposed receiving device. In addition, a method and a computer program product comprising method steps are proposed, which are suitable for providing a system arrangement or an input device and an output device in a production plant. In addition, a computer-readable medium comprising control commands is proposed.

[0002] Various solutions for implementing data communication using software are known from the state of the art. To this end, various solutions from the state of the art have components implemented by software or hardware.

[0003] In particular, software implementations may result in increased workload and higher complexity of the underlying circuitry. For example, such applications target scenarios that require flexibility and implement dynamic packet switching.

[0004] State-of-the-art methods are often not suitable for use in cars, as they often use proprietary standards that were designed for high-performance computer networks but do not meet the requirements of cars. In cars, completely different requirements are imposed on real-time data transmission and error robustness. Methods related to video data transmission are often designed for end users who have powerful computer systems. In this application scenario, large hardware capacities are often available, and energy consumption is only secondary. In cars, on the other hand, it is necessary to reduce weight, provide high reliability, and save energy. In electric cars, higher energy consumption directly means lower range of the car. In this regard, in the state-of-the-art, it is necessary to create devices that create data with little technical effort and with high efficiency in many aspects.

[0005] All of these technologies listed as examples are optimized for the transfer of one data type (video, audio, SPI, Ethernet). "Bridging" from one interface (e.g., DisplayPort) to another interface (e.g., HDMI) with the same data type is not possible.

[0006] At the same time, electronic systems in vehicles have become increasingly complex, powerful, and “data-intensive” over the decades.

[0007] The efficient and fast networking of display units, actuators, sensors and processing units plays a central role here, if not a decisive role in the performance of the system.

[0008] Display units, sensors and actuators and the associated processing units are relatively far apart in the vehicle. If a separate communication solution between sensor / actuator and processing unit (GPU / CPU) is now implemented for each interface, as in a PC or mobile phone (state of the art mentioned above), this means laying a lot of cables (weight) and the performance is mostly limited due to the spatial distance.

[0009] In order to reduce the weight of cables and connectors, it is necessary to bundle the data connections on the same cable system. For the same type of data, these are classic SERDES solutions (state of the art). Systems for serial transmission of data at gigabit data rates.

[0010] The bundling of different data paths requires a solution that is generic rather than data type specific (video, audio, etc.) The multitude of existing and emerging data interfaces must be mapped to standardized generic interfaces to enable maximum possible reuse of complex data path logic.

[0011] It would therefore be desirable to create devices, system arrangements and processes which do not suffer from the disadvantages described above and which can be used in a particularly advantageous manner in a motor vehicle.

[0012] The object of the present invention is therefore to provide a transmitting device which can be implemented particularly efficiently and also saves hardware resources, in particular for use in a motor vehicle. It is also an object to provide a receiving device as opposed to a transmitting device, and a system arrangement which integrates all devices with one another. It is also an object of the present invention to provide a method for providing such a device and a computer program product with a computer-readable storage medium.

[0013] The problem is solved with the features of claim 1. Further advantageous embodiments are given in the dependent claims.

[0014] Therefore, an input device in a transmitting direction for efficiently transmitting data in a car is proposed, the input device comprising: an input interface device, the input interface device having a plurality of input interface units, the plurality of input interface units having a first group of input interface units and a second group of input interface units, the first group of input interface units being each configured in hardware to receive continuous data, the second group of input interface units being each configured in hardware to receive discontinuous data; a packetizing device, the packetizing device being arranged to segment the data and to enrich the data with forwarding information and data protection information; a packetizing device packet data processing device, the packetizing device packet data processing device being used to forward the data; and an output device arranged in the transmitting direction, the output device being used to provide the data to a physical transmission channel, wherein the input interface device, the packetizing device and the output device are unidirectionally communicatively coupled.

[0015] The proposed input device in the transmission direction is particularly efficient in data forwarding, because the structure of the input device is designed in such a way that data is only forwarded in one direction and the device is not designed in a two-way manner, as in the prior art. This simplicity of the input device makes it possible to provide the device particularly efficiently and only two types of input interfaces are required. These input interfaces are of different types and are optimized to receive continuous data or discontinuous data. In addition, the packetization device, which can also be referred to as a packet data processing device or a packet data processing device, can be controlled in a way that only one physical data channel is required. If several data paths are used, up to 128 virtual data paths can be set on this one physical data channel according to the present invention. This produces a particularly high level of fault tolerance and a reduction in weight, because it is not necessary to maintain many physical paths, but only a single physical data channel needs to be maintained.

[0016] The data are forwarded in such a way that the data are received at the input interface device and passed through the input device in the sending direction, multiplexed with the packet data from other input interface devices in the packet data processing device, and output at the output device in the sending direction. Multiplexing means that several signals or information streams are transmitted simultaneously on one line in the form of a single composite signal and then decomposed again into individual signals at the receiving end. Thus, according to the invention, packet data from several input interface devices are combined.

[0017] As the data passes, further processing steps may also be performed. In particular, the data may be extracted or processed in a packet data processing device. For example, the packet data processing device may be coupled to an input device that outputs a corresponding signal.

[0018] The input interface device has a large number of input interface units. This means that the input interface device can receive data for different virtual channels via several physical data channels, each of which is assigned to an input interface unit. Generally speaking, the input interface device or input interface unit is implemented in such a way that it is set to receive continuous data or receive discontinuous data. The technical differences between these interfaces are, for example, related to the size of the buffer memory or volatile memory provided. Generally speaking, there are therefore two groups of input interface units, one of which is intended to receive continuous data, and the second group is intended to receive discontinuous data. Generally speaking, all data are received via input interface units. For example, a continuous data stream can be video data, and discontinuous data can be control commands. According to one aspect of the present invention, two groups of input interface units can also be distinguished so that the first group provides a faster processing unit than the second group. This allows the use of a larger memory and / or a faster processing power than when processing discontinuous data to process continuous data.

[0019] Furthermore, a segmentation unit is provided, which is arranged to generate data packets, thereby providing data packet-specific information. This can be information related to addressing or routing, or also for protecting data packet-specific information. For example, data packet-specific information can be protected by means of a checksum. According to one aspect of the invention, data packetization is also controlled here. This means formatting the application data into packet data (data cells) and / or adjusting the bit width.

[0020] According to one aspect of the invention, a subsequent packet data processing unit (crossbar unit) supplements the data packet-specific information with forwarding information, which specifies the destination to which the data is to be forwarded. This can be a static route, which in turn is particularly efficient to implement. Dynamic routing would require too much technical effort and the input device could not be implemented efficiently.

[0021] Furthermore, according to one aspect of the invention, an output device (row coding and framer unit) is provided, which is arranged to provide data to a physical transmission channel. The output device receives data from a packet data processing unit (cross switch unit) and is then arranged in hardware to output the data. For example, the output can be transmitted to the proposed output device in the sending direction. For this purpose, the output device is provided with an input device in the sending direction. The output device is implemented in such a way that it processes packaged data, outputs packaged data and / or provides packaged data from the packet data processing unit (cross switch unit) to a physical transmission channel. The physical transmission channel can be a cable, and the output device also provides an interface for this.

[0022] The input interface device (burst data interface, stream data interface), the packetization device (segmentation unit), the packet data processing unit (crossbar unit) and the output device (row coding and framer unit) are connected in such a way that they forward unidirectional data, i.e. the input data from the input interface device is forwarded to the packetization device and the packet data processing device, and then the input data can be output using the output device. No reverse sequential data flow is provided. This makes it possible to implement the proposed input device particularly efficiently.

[0023] Among other advantages, the present invention provides the following advantages:

[0024] - Modular scalability with application interfaces without changing data path logic (compliance and compatibility with existing systems are still guaranteed);

[0025] - Use any physical device with different bandwidth without changing the data path logic (compliance and compatibility with existing systems are still guaranteed);

[0026] - Customized hardware solutions for any application interface reduce software workload and ensure high and efficient data throughput.

[0027] According to one aspect of the invention, the number of interface units is between 2 and 128 and / or there are up to 128 virtual data paths to the input interface units. This has the advantage that the hardware requirements can be minimized so that only a single physical interface needs to be provided and 128 virtual data paths can also be provided. The number of interface units can also vary, whereby there must be at least one input interface unit of the first group and one input interface unit of the second group. This ensures that both continuous and discontinuous data can be processed optimally.

[0028] According to another aspect of the invention, the input interface device, the packetization device, the packet data processing unit and / or the output device are implemented in hardware. This has the advantage that it is not necessary to implement complex circuits for storing and executing software commands. Instead, these devices can be hard-coded and can therefore operate efficiently. Because there is no need to handle dynamic processes, these devices can be provided with little technical effort. This means that all units can be provided as hard-wired. This also increases reliability and reduces energy requirements.

[0029] According to another aspect of the invention, all units and devices transmit data only in one direction. This has the advantage that the structural features can be equipped particularly efficiently. The unidirectional data transmission also ensures that no protection mechanisms need to be provided, since data can only flow in one direction. Therefore, faulty data cannot be transmitted in the opposite direction, which in turn implements simple protection mechanisms.

[0030] According to another aspect of the invention, continuous data is available as streaming data and discontinuous data is available as burst data. This has the advantage that the hardware can be adapted to the corresponding transmission concept and therefore optimized hardware can be provided. Therefore, the hardware can meet the special requirements of streaming data or burst data. Streaming data places high demands on real-time transmission in particular, because otherwise the video data will be delayed. It is also possible to implement a mechanism for ensuring that streaming data is transmitted continuously and burst data allows data transmission to be suspended. The buffer memory can then be set accordingly.

[0031] According to another aspect of the invention, continuous data may have frames that segment the continuous data (e.g., Hsync, Vsync, DE for video), and discontinuous data typically does not have frame information because these discontinuous data have an implicit start and end due to the bursty data structure. In turn, a particularly efficient circuit is implemented that provides logic implemented in hardware for continuous data that attaches frame information to the data packet. The same mechanism can optionally be used for discontinuous data to indicate the start / end of a burst.

[0032] According to another aspect of the invention, the interface unit for continuous data has a larger buffer memory than the interface unit for discontinuous data. This has the advantage that the memory does not have to be too large, and in particular the interface for discontinuous data can be designed to be correspondingly efficient. This in turn reduces the technical effort involved in providing the data.

[0033] According to another aspect of the invention, the packetizing device adapts the format of the data. This has the advantage that further information, such as addresses and / or checksums, can be provided to ensure the security of the data transmission.

[0034] According to another aspect of the invention, the input interface device, the packetization device and the output device comprise volatile memory. This has the advantage that an efficient memory can be created which does not need to store data permanently. Volatile memory is particularly easy to manufacture and also has a high operating speed.

[0035] According to another aspect of the invention, the number of interface units of the first and second groups is the same. This has the advantage that symmetrical processing is possible and thus specialized interface units can be created.

[0036] According to another aspect, however, the number of interface units in the first group and in the second group may also vary. This then enables corresponding application scenarios to be taken into account.

[0037] The problem is also solved by an output device in a receiving direction for efficiently forwarding data in a car, the output device comprising: an output interface device, the output interface device having a plurality of output interface units, the output interface units having a first group of output interface units and a second group of input interface units, the first group of input interface units being each configured in hardware for transmission of continuous data, the second group of output interface units being each configured in hardware for transmission of discontinuous data; a reassembly unit, the reassembly unit being configured for recovering application data from packet data, forwarding information and data protection information; a cross switch unit and an input device in a receiving direction, the cross switch unit and the input device being configured for receiving data on a physical transmission channel, wherein the output interface device in the receiving direction, the reassembly unit, the packet data processing unit and the input device in the receiving direction are coupled in a unidirectional communication manner.

[0038] According to one aspect of the invention, the output device in the receiving direction is similar to the input device in the transmitting direction, but has the opposite function. Therefore, this means that the output device in the receiving direction provides the opposite function, and the output of the input device in the transmitting direction becomes the input of the output device in the receiving direction. Therefore, the packaged data of the input device in the transmitting direction is unpacked in the output device in the receiving direction and output in the opposite direction. In this regard, all aspects of the input device in the transmitting direction also affect the aspects of the output device in the receiving direction. Data processing or data forwarding is performed in the output device, opposite to the direction of the input device.

[0039] The problem is also solved by a system arrangement comprising a transmitting device and a receiving device communicatively coupled by means of a serial data connection.The system arrangement may be integrally molded, or the transmitting device and the receiving device may be implemented separately.

[0040] According to another aspect of the invention, static routing and / or hard wiring is provided between all devices, equipment and units. This has the advantage that architectural features can be designed efficiently and better runtime behavior is achieved.

[0041] According to another aspect of the invention, the system arrangement is integrally molded. This has the advantage of creating a compact and non-destructive design. In this context, integral means that the components cannot be separated in a non-destructive manner. This makes it possible to connect or wire components of input devices and output devices, in particular input interface devices and output interface devices, efficiently and with little technical effort.

[0042] According to another aspect of the invention, the input interface device and the output interface device have a direct hardwired communication coupling to each other. This has the advantage that a feedback loop is formed without destroying the unidirectionality. This allows functional testing without a great deal of technical effort.

[0043] According to another aspect of the present invention, a functional test can be performed in such a way that the same data is input and then output by means of direct data communication between an input interface device and an output interface device. This has the advantage that the function of the device can be tested in a simple manner. If a data stream is input at an input interface device, it can be directly output at an output interface device via direct coupling, i.e., it does not have to pass through other devices. This makes it possible to check whether the data has been correctly passed. Alternatively, the same data is not expected as output, but processed input data is expected to check whether the processing before the component has been performed according to the specification. This produces a simple functional test that excludes other components coupled in series in the data communication performed by means of a short feedback loop according to a longer data communication.

[0044] The problem is also solved by providing a method for an input device for efficiently forwarding data on a virtual data path, the method comprising providing an input interface device, the input interface device comprising: a plurality of input interface units, the plurality of input interface units having a first group of input interface units and a second group of input interface units, the first group of input interface units each being configured in hardware to receive continuous data, the second group of output interface units each being configured in hardware to receive discontinuous data; providing a packetization device and a packet data processing unit, the packetization device and the packet data processing unit being arranged to enrich the data with forwarding information and data protection information; and providing an output device, the output device being arranged to provide the data to a physical transmission channel, wherein the input interface device, the packetization device, the packet data processing unit and the output device are unidirectionally communicatively coupled.

[0045] One aspect of the present invention is to bundle several data streams (video, audio and data) in a transmission frame and transmit the data streams serially. Different data formats have not only different bandwidth requirements, but also different delay and bit error rate requirements. In particular, the transmission of today's video data formats requires not only the transmission of pure video data and its frame information, but also the support of encryption methods such as HDCP. All of this requires many different data channels with a wide range of bandwidth, delay and bit error rate and bit error detection requirements. In addition to this, a more complex network architecture than a simple transmitter / receiver architecture is required. An architecture with several repeaters (where the data path can start and end), branches (Y), and the possibility of reintegrating the data path into a link is advantageous.

[0046] According to one aspect of the invention, the technology follows the basic idea of ​​bundling data of different services, but offers completely new possibilities regarding network architecture and allows new approaches in implementing today's video interfaces. In addition, it can be used as a universal data transport system, for example for transmitting Ethernet or camera data or any type of sensor data.

[0047] Regarding the virtual path in the present invention, all data packets or cells take the same path, which is contrary to IP, in which a packet can reach its destination via a different path from the previous and subsequent packets. Therefore, the delay on the virtual path is constant.

[0048] Packet or cell based virtual paths also have the advantage that they can be used as a multiplexing layer for different services (video, audio, Ethernet).

[0049] Virtual paths consume bandwidth only when data is actually being transferred.

[0050] The concept of virtual paths implemented here also enables complex and far-reaching diagnostic and network configuration functions to be implemented at runtime with separate (virtual) data channels.

[0051] According to one aspect of the present invention, an input device in a sending direction, a packet data processing device in a sending direction, an output device in a sending direction, an input device in a receiving direction, a packet data processing device in a receiving direction, and an output device in a receiving direction are implemented between a physical serial interface and various application data interfaces.

[0052] According to one aspect of the invention, these devices are used to multiplex various virtual data paths and support more complex architectures with repeaters and branches. This is mainly done in packet data processing equipment.

[0053] Another aspect of the invention is an input device in the transmitting direction and an output device in the receiving direction, which performs the conversion of video (stream) or, for example, Ethernet (packet) data into cells (data packets). The input device in the transmitting direction and the output device in the receiving direction also include OAM functions for network diagnosis and management.

[0054] According to one aspect of the invention, the technology could be the basis for transmitting a variety of data formats via serial connections in cars (and elsewhere). As such, it forms the basis for a new generation of devices.

[0055] High serial bandwidths make it necessary to define architectures, cell formats and interfaces that enable flexible internal data bus widths in order to adapt the speed of the internal clock system to the possibilities of the chip technology.

[0056] The present invention includes an input device in the transmission direction and an output device in the receiving direction, which performs the conversion of video (stream) or, for example, Ethernet (packet) data into or out of cells (data packets). The present invention also includes a packet data processing device in the transmission and reception directions, which processes data packets (cells), supplements them, multiplexes or demultiplexes them with other cells, and thus controls the flow of cells. The present invention further includes an output device in the transmission direction and an input device in the receiving direction, which advantageously encodes or decodes data packets (cells) for serial transmission, packs them into or unpacks them from transmission frames, and serializes or deserializes the transmission frames. Serial connections are essentially bidirectional. In theory, this connection can be implemented via a variety of media. In practice, two serial differential GBps connections are used.

[0057] In the packet data processing device, the segmented data (cell payload data) of the application interface is assembled into a complete cell together with the header, VP identifier and CRC or the cell is CRC-checked, and the payload is forwarded to the output device in the receiving direction. This is also the case when multiplexing different cell streams of the input device in the sending direction or distributing the cell payload to the output device in the receiving direction according to the VP identifier. (Feed-in / Feed-out)

[0058] According to one aspect of the invention, multiplexing and demultiplexing (forwarding) of cell streams in repeaters and splitters also occurs in the packet data processing equipment.

[0059] According to one aspect of the invention, the task of the input device in the transmitting direction is to adapt the data of the application interface to the format of the user data field of the message cell and to transmit control information to the opposite side, or to transmit control information of the opposite side for use adaptation (clock recovery, frame formation).

[0060] According to one aspect of the invention, all virtual data paths are unidirectional, ie, they start at an initiator at an application interface and end at one or more targets at the application interface.

[0061] A virtual data path starts with an initiator and ends with one or more targets. It is implemented by a packet data processing device and performs the following functions on the virtual path:

[0062] - Multiplexing and demultiplexing of cells, i.e. adding or removing cells from a cell stream

[0063] -VP Conversion

[0064] The method may be used to control a machine providing an input device, providing an output device, providing a packet data processing device and / or providing a system arrangement.

[0065] The object is also achieved by a computer program product having control commands for carrying out the proposed method or for operating the proposed device.

[0066] Further advantages, features and details of the invention are shown in the following description, in which various aspects of the invention are described in detail with reference to the accompanying drawings. The features mentioned in the claims and the description may each be essential to the invention individually or in any combination. Likewise, the features mentioned above and the features further described herein may be used individually or in any combination. Functionally similar or identical parts or components sometimes have the same figure numbers. The terms "left", "right", "top" and "bottom" used in the description of the embodiments refer to the drawings in an orientation with a generally clear figure name or a generally clear figure number. The embodiments shown and described should not be understood as conclusive, but are exemplary in nature for the purpose of explaining the invention. The detailed description of the information is provided for reference by those skilled in the art, and therefore known circuits, structures and methods are not shown or explained in detail in the description so as not to hinder the understanding of the description. The drawings show:

[0067] Figure 1 is a schematic flow chart of a method of providing an input device according to one aspect of the present invention;

[0068] Figure 2 is a schematic block diagram of a transmitting device for efficiently forwarding data according to another aspect of the present invention;

[0069] is a schematic block diagram of a receiving device for efficiently forwarding data according to another aspect of the present invention; and

[0070] Figure 3 According to another aspect of the invention is a system arrangement comprising the proposed transmitting device and the proposed receiving device.

[0071] Some of these figures have parameters with English names familiar to those skilled in the art, which are used as parameters and cannot be translated in this way.

[0072] Figure 1 In a schematic flow chart, a method for providing an input device for efficiently forwarding data on a virtual data path is shown, the method comprising: providing 100 an input interface device, the input interface device comprising a plurality of input interface units, the plurality of input interface units having a first group of input interface units and a second group of input interface units, the first group of input interface units being each configured in hardware to receive continuous data, the second group of input interface units being each configured in hardware to receive discontinuous data; providing 101 a packetization device, the packetization device being arranged to enrich the data with forwarding information and data protection information; and providing 102 an output device, the output device being arranged to provide the data to a physical transmission channel, wherein the input interface device, the packetization device and the output device are unidirectionally communicatively coupled.

[0073] Figure 2 Shown is a schematic block diagram of a transmitting device for efficiently forwarding data. An input interface device 10a with different input interface units (e.g., the first group on the left and the second group on the right) is shown at the bottom. At the bottom, 6 input arrows are shown, representing up to 128 input arrows describing virtual paths. The input at the bottom is actually implemented via a physical channel. This also applies to the output arrows on the upper side, which can also be implemented as a physical channel. The maximum 128 virtual paths on the lower side are processed in input device 10a, packet unit 20a and packet data processing equipment 31a, and then output with output device 32a on the upper side. Further process steps or functions can be implemented here. The input interface device 10a forwards data to the packetization unit 20a. Then, these data are output via the output device 30a in the sending direction.

[0074] Figure 2 The receiving device is shown with Figure 2Similar, but functionally opposite mode is used for the schematic block diagram of efficient output data.On the lower side, output interface device 10b is shown, and this output interface device has different output interface units, for example, the output interface units of the first group on the left and the second group on the right.At the bottom, 6 output arrows representing up to 128 output arrows describing virtual paths are shown.The output at the bottom is actually implemented via physical channel.This is also applicable to the input arrows on the upper side, which can also be implemented as physical channels.128 virtual paths at most on the lower side are processed in output device 10b, unpacking unit 20b and packet data processing equipment 31b after being received from the upper side by input device 32b.Further process steps or functions can be implemented here.For example, output interface device 10b receives data from unpacking unit 20b.These data are received by input device 30b in receiving direction.

[0075] Figure 3 The system arrangement is shown with a transmitting device at the top, which consists of an input device (also called input interface device 10a) at the upper left in the transmitting direction, a packet data processing device (also called packetization device 20a) at the upper middle in the transmitting direction, and an output device (also called output device 30a) at the upper right in the transmitting direction. Figure 3 As can be seen, other functions or structural features can be implemented in each device. Figure 3 It can also be seen that data is forwarded strictly in one direction. This creates a universal modular high-capacity data transmission system.

[0076] The burst data interface on the left may represent an input interface unit for receiving discontinuous data. The stream data interface may represent an input interface for receiving continuous data. In one aspect of the invention, the segmentation unit corresponds to the packetization unit. In one aspect of the invention, the crossbar switch unit corresponds to a packet data processing device.

[0077] Another unit below shows a receiving device, which consists of an input device at the lower right in the receiving direction, a packet data processing device at the lower center in the receiving direction, and an output device at the lower left in the receiving direction.

[0078] At the right edge, a serial data link connects the transmitting device to the receiving device, which can be implemented as an electrical cable or a fiber-optic cable.

[0079] The top three blocks are the devices of the transmitting device, and the bottom three blocks are the devices of the receiving device. The units and devices of the transmitting device are followed by the units and devices of the receiving device via the arrows on the right. Here, data is again forwarded unidirectionally and output on the left via up to 128 virtual data channels.

[0080] exist Figure 3 , a direct coupling between an input interface device and an output interface device is shown by means of a filled black arrow. The input interface device at the top and the output interface device at the bottom have a direct hardwired communication coupling to each other. This shortens the communication path and the path can be used in a test mode. Thus, the components on the right are decoupled from the communication path and the signal is efficiently output by means of the output interface device with or alternatively without processing in the input interface device or the output interface device. This can be a direct hardwired communication coupling. This can be implemented efficiently, especially in the case where the system arrangement is integrally molded.

[0081] The structural features shown can be described as follows:

[0082] According to one aspect of the invention, the invention provides a generic hardware (burst / stream) solution for providing data from any application interface for transmission using the same data cells. Based on the data cells, the transmission system implements a virtual data path between the application interfaces via a serial link. It also provides the option of directly accessing the virtual data path via a cell interface for "relaying" (forwarding the data of the data path without changing the data / cells).

[0083] The present invention comprises:

[0084] a)Burst data interface input

[0085] a. Application data buffer for bursty data (PCI, SPI, I2C). Buffer bursty data to achieve seamless packing of data cells in segment units.

[0086] b. Format the application data to fit the cell data bit width.

[0087] c. Transition from application cycle system to cell cycle system

[0088] d. Provide a general mechanism for marking data packets to synchronize data and control signals (e.g. burst start / end) of the application interface

[0089] b)Burst data interface output

[0090] a. Application data buffer for bursty data (PCI, SPI, I2C). Buffers cell data to achieve gapless data bursts at the application interface.

[0091] b. Format the cell data to fit the application data bit width.

[0092] c. Transition from a cell cycle system to an application cycle system, with the option to generate application cycles.

[0093] d. Provide a general mechanism for evaluating the marking of data packets for synchronizing data and control signals (e.g. burst start / end) of the application interface

[0094] c) Stream data interface input

[0095] a. Application data buffer for continuous data (video, audio). Video data is buffered to achieve seamless packing of data cells in segment units.

[0096] b. Format the application data to fit the cell data bit width.

[0097] c. Transition from application cycle system to cell cycle system

[0098] d. Provide a general mechanism for marking data packets for synchronizing data and frame signals (e.g. Hsync, Vsync, DE) of the application interface

[0099] d) Stream data interface output

[0100] a. Application data buffer for continuous data (video, audio). Buffers cell data to achieve uninterrupted continuous data flow at the application interface.

[0101] b. Format the cell data to fit the application data bit width.

[0102] c. Transition from a cell clock system to a source synchronous clock system for continuous data, with the option to generate an application clock.

[0103] d. Provide a general mechanism for evaluating the marking of data packets for synchronizing the data and frame signals (e.g. Hsync, Vsync, DE) of the application interface

[0104] e) Staging Unit / Packaging Facilities

[0105] a. Generate data cells with cell-specific information data for cell routing and cell data protection. Control cell packing. (Format application data into cell data; bit width adjustment)

[0106] f) Reassembly unit / unpacking equipment

[0107] a. Recover application data from data cells based on cell-specific information data for cell routing and cell data protection. Control cell unpacking (formatting cell data into application data; bit width adjustment)

[0108] g) Crossbar switch unit for cell merging

[0109] a. Receive data cells from different ports (burst data interface, stream data interface, cell interface) and assign routing information to the cells based on the source (port).

[0110] b. Multiplex all received cells to one output (to the line coding and framer unit)

[0111] c. Control the latency of cell flows via a configurable priority-based arbitration mechanism.

[0112] h) Crossbar switch unit for cell separation

[0113] a. Output data cells to various ports (burst data interface, stream data interface, cell interface) based on the cell's routing information.

[0114] b. Demultiplex all received cells (from row decoding and deframer units) to many outputs.

[0115] i) Line coding and framer unit

[0116] a. Adapt the cell data rate to the link data rate by inserting null cells.

[0117] b. Encoding data for serial data transmission

[0118] j) Line decoding and de-framing unit

[0119] a. Decode serial data

[0120] b. Remove empty cells.

[0121] k)Tx physical layer interface

[0122] a. Convert parallel data to serial data.

[0123] b. Convert serial data bits into electrical or optical signals.

[0124] l)Rx physical layer interface

[0125] a. Convert electrical or optical signals into serial data bits.

[0126] b. Convert serial data into parallel data.

[0127] A data memory or a computer-readable medium with a computer program product comprising control commands for implementing the proposed method or operating the proposed system arrangement is not shown here.

[0128] Physical layer interface (Tx and Rx)

[0129] Purpose and Function

[0130] The physical layer interface implements the electrical connection to the physical transmission medium. The primary transmission medium is differential 100 ohm lines. However, optical transmission media can also be considered as an option.

[0131] The physical transmission format depends on the data rate and is either NRZ for low data rates or PAM4 for high data rates.

[0132] The physical layer interface functional block implements serialization of M-bit parallel line-coded data (M = original serializer bit width) on the transmitting side and recovery of the serial clock and bit-serial data on the receiving side and deserialization into M-bit parallel line-coded words. Serial data transmission is based on the concept of "embedded clock", that is, no time is transmitted, only serial data is transmitted, which achieves time recovery due to line coding.

[0133] The cell clock frequency is primarily determined by the SERDES's "native bit width" M. For example, at 30 GBps and a native bit width of M = 128, this yields a core clock frequency of 234.375 MHz.

[0134] Interface with physical media

[0135] In the direction of the transmission medium, the physical layer interface functional block according to one aspect of the present invention implements two unidirectional, differential, bit serial 100 ohm interfaces. One transmit interface and one receive interface. The physical medium includes differential forward lines and differential return lines throughout. This arrangement also enables optional operation of optical media without major adaptation circuits.

[0136] For the physical medium, the emphasis is on twisted pair cable, as the insertion loss of coaxial cable at higher frequencies is equal to that of twisted pair cable. If you take into account the 6dB attenuation of single-ended transmission compared to differential transmission, coaxial cable has absolutely no advantage.

[0137] The maximum cable length depends on the data rate (and cable diameter).

[0138] According to one aspect of the invention, a bit clock system for serializing data is generated in the transmit direction by means of a PLL. The data / symbols are transmitted together with this bit clock. The bit clock forms the basis of the Tx clock system. The direction of the Tx data path is opposite to this clock system. (Target is synchronized)

[0139] In the receive direction, a CDR is used to recover the bit clock used to serialize the data from the received serial data stream. This bit clock forms the basis of the Rx clock system. The direction of the Rx data path is the same as this timing system (synchronization source).

[0140] The core clock frequency may be determined primarily by the "raw bit width" M of the SERDES. For example, at 30 GBps and a raw bit width of M = 128, this yields a core clock frequency of 234.375 MHz. Since the SERDES technology may vary, M will also vary. Therefore, the cell format and cell data interface between various functional units or devices must support flexible SERDES bit widths, or the cell format must be decoupled from the cell row data width.

[0141] Line encoding and framer equipment and line decoding and deframer equipment

[0142] Purpose and Function

[0143] According to one aspect of the present invention, an output device in the transmitting direction or an input device in the receiving direction generates M-bit wide symbols of a row code for a SERDES interface from an N-bit wide transmission frame in the transmitting direction (see: 7. Transmission frame and symbol format), and generates an N-bit wide transmission frame again from the M-bit symbols of the SERDES interface in the receiving direction.

[0144] The main function of the output device in the transmitting direction and the input device in the receiving direction is to assemble the transmission frames from the cells in the transmitting direction and, conversely, to disassemble the transmission frames into cells in the receiving direction.

[0145] In order to adapt the data rate of the cell stream to the data rate of the serial transmission, according to one aspect of the invention, these devices can insert empty cells in the transmission direction (from the application interface to the serializer). The availability of cells depends on the total bandwidth requirements of all application interfaces. Therefore, according to one aspect of the invention, when processing (collecting, assembling and merging) cells with the system clock, the cells do not form a continuous cell stream.

[0146] In the receive direction (from the deserializer to the application interface), null cells are discarded here. Cells are extracted from the serial frame. Since the cell data rate is lower than the bandwidth associated with the system clock, as in the transmit direction, these cells are forwarded along with the data validity signal.

[0147] The packet data processing equipment processes the cell stream. In addition to generating the cell header and CRC or extracting data from the cell and performing a CRC check, a so-called add / drop multiplexer function is also implemented here.

[0148] This means that in the send direction, cells are collected by the various service functions, provided with a VP identifier, cell headers and footers are generated and collected by the peer interface and then multiplexed into a common cell stream (add functionality).

[0149] In the receive direction, according to one aspect of the invention, the cell stream is distributed from the input device in the receive direction to various service functions and peer interfaces based on the VP identifier. The data for the service function is unpacked and CRC-checked (discard function). All cells whose VP identifier does not belong to the service function are forwarded to the peer interface (forward function).

[0150] Input devices in the transmitting direction and output devices in the receiving direction

[0151] Purpose and Function

[0152] Here, the cell-based virtual data paths are converted back into physical data paths. These paths are connected to various application interfaces via generic service interfaces for streaming or bursty data.

[0153] For example, the application interface type is stream data for video and audio data and burst data for almost all types of data packets. The way stream and / or burst data is packed into or unpacked from cells is not encoded in the cells. Instead, it is configured between the two endpoints or negotiated based on the virtual connection.

[0154] In the transmit direction, according to one aspect of the invention, the input device together with the dedicated interface implements the start of a cell-based virtual data path.

[0155] In the receive direction, the output device together with the dedicated interface implements the end point of the cell-based virtual data path.

[0156] One of the main tasks of these devices (and dedicated interfaces) is to implement the conversion of streaming or burst data formats with any bit width (bit width) into an N-bit wide cell row data format.

[0157] The interface between the streaming data or burst data functions of these two devices has a bit width (N) of a cell row. The streaming data or burst data interface combines clock domain traversal with bit width conversion of the data from the application interface to N bits of a cell row. The cell row payload has been formatted so that the cell footer and header fit into the first and last cell rows.

[0158] According to one aspect of the invention, in addition to the payload data, the cell also provides the possibility of transmitting payload information data, for example, the payload information data is used to generate a frame signal for video or audio in the case of streaming data and to generate a data packet, transaction or burst in the case of burst data.

[0159] Bind frame signals to streaming data

[0160] The basic idea of ​​connecting the frame signal to the data stream is to define an important anchor point (or several anchor points) in the time sequence of the frame signal and use the payload information bits to transmit this anchor point (or these anchor points) so that a clear synchronization of the data stream and the frame signal is possible. Ideally, this is done by placing fixed points of the data stream at fixed points in the marked data cells. To recover the timing of the frame signal, a free-running timing generator is used, which can generate the entire timing independently. Now, the timing is adapted to the data stream by analyzing the payload information bits and adapting the timing to the defined points in the data cells.

[0161] Streaming data (continuous data flow)

[0162] The stream data interface combines the transition from the application clock domain to the cell clock domain with the bit width conversion of the data from the application interface to the N bits of the cell row. The cell row payload is already preformatted so that the cell footer and header fit into the first and last cell rows.

[0163] Streaming data is (usually) source synchronous. Clock domain crossing of the data path from the application clock domain to the cell clock domain is performed here.

[0164] A data buffer is provided in the transmit direction, into which source-synchronized data is written along with the application clock. An input device in the transmit direction retrieves data from the buffer as needed to perform data format conversion into N-bit-wide rows of cells. Frame signals (e.g., Hsync, Vsync, DE) are encoded in the payload information bits so that the frame signals can be reconstructed at the receiver side.

[0165] In the receive direction, the cell data is written to the data buffer by the output device in the receive direction. The frame signal is reconstructed based on the payload information bits. For example, the application clock on the transmit side is regenerated using the buffer fill level and clock synthesis.

[0166] If data encryption (HDCP) is required, the cell data is encrypted or decrypted in this function.

[0167] Due to the different types of stream data, such as encrypted and unencrypted audio and video, this basic function may have different implementation methods (for example: VStream In / Out; AStream In / Out; EncVStream In / Out).

[0168] Burst data (discontinuous data flow)

[0169] The burst data interface combines the overflow from the application clock domain to the cell clock domain with the bit width of the burst data from the application interface into N bits of a cell row. The cell row payload is already preformatted so that the cell footer and header fit into the first and last cell rows.

[0170] The burst data is (usually) synchronized to an external clock and has different identifying signals (address / data / byte enable) for direction and data type.

[0171] This data is usually accompanied by a control line in order to implement a specific protocol.

[0172] In the transmit direction a data buffer is provided into which burst data is written together with an interface clock. An input device in the transmit direction retrieves data from the buffer as required in order to perform data format conversion into N-bit wide row cells.

[0173] In the receive direction, the cell data from the output device is written to the data buffer in the receive direction. The interface control signal is reconstructed based on the payload information bits.

[0174] The payload information bits are used to generate control signals for the dedicated interface or to synchronize a protocol state machine in the dedicated interface.

[0175] Due to the different interfaces that provide burst-like data (SPI, I2C, MII), there may be different implementations of this basic function (for example: SPIBurst, I2CBurst, MIIBurst).

[0176] Therefore, there will also be (slightly) different stream input / output interfaces, although their structure should be the same.

[0177] Cell Format

[0178] According to one aspect of the present invention, a cell includes a header having a fixed bit length, a payload area having 4 selectable bit lengths, and a footer also having a fixed bit length.

[0179] The cell structure is the following bit sequence:

[0180] - A 7-bit Virtual Path Identifier (VP) which indicates the unique address of the virtual path.

[0181] - 3-bit sequence number (SN) which numbers the cells consecutively in order.

[0182] - A 2-bit wide Cell Type (CT) identifier that specifies the length of the user data.

[0183] - 3 bits wide Payload Information (PI) which contains additional information about the payload. This can also be used to synchronize payload data and frame data or control data.

[0184] - A 10-bit wide CRC polynomial (HCRC) used for error protection of header information. This polynomial has a bit sequence of up to 21 bits (P=0x2B9) and a Hamming distance of 5.

[0185] - Length of the payload (PL) field: 187, 411, 635 or 859 bits, depending on the CT value. The shortest payload is chosen so that it is still larger than the largest supported (video) streaming bus width. (Should simplify mapping of streaming data to cell payloads).

[0186] - Finally, a 12-bit wide CRC polynomial (PCRC) is used for error protection of user data. This polynomial has a bit sequence of up to 2035 bits (P=0x8F3) and a Hamming distance of 4.

[0187] Transmission frame format

[0188] According to one aspect of the invention, a transmission frame comprises a sequence of M-bit wide words. The frame starts with an M-bit wide "comma" word from a defined sequence of comma words used for frame alignment. This is followed by K cells. A cell consists of 2, 4, 6 or 8 N-bit wide words that carry headers, payload and footers. These N-bit wide words are encoded into M-bit wide symbols (row encoding).

Claims

1. A transmitting device for efficiently forwarding data in a car, the transmitting device comprising: - an input interface device (10a), the input interface device having a plurality of input interface units, the plurality of input interface units having a first group of input interface units and a second group of input interface units, each of the first group of input interface units being configured in hardware to receive continuous data, and each of the second group of input interface units being configured in hardware to receive discontinuous data; - a packetizing device (20a) arranged to enrich the data with forwarding information and data protection information; as well as - an output device (30a) in the transmission direction, the output device being arranged to provide the data to a physical transmission channel, wherein the input interface device (10a), the packetization device (20a) and the output device (30a) are unidirectionally communicatively coupled.

2. The transmitting device according to claim 1, characterized in that The number of interface units is between 2 and 128 and / or there are up to 128 virtual data paths to the input interface units.

3. The transmitting device according to claim 1 or 2, characterized in that: The input interface device (10a), the packetization device (20a) and the output device (30a) are implemented in hardware.

4. Transmitting device according to one of the preceding claims, characterized in that All units and devices are set up to transfer data in one direction only.

5. Transmitting device according to one of the preceding claims, characterized in that Continuous data exists as stream data and discontinuous data exists as burst data.

6. Transmitting device according to one of the preceding claims, characterized in that Continuous data has frames, and discontinuous data does not have frames.

7. Transmitting device according to one of the preceding claims, characterized in that The interface unit for continuous data has a larger buffer memory than the interface unit for discontinuous data.

8. Transmitting device according to one of the preceding claims, characterized in that The packetizing device (20a) adapts the data in its data format.

9. Transmitting device according to one of the preceding claims, characterized in that The input interface device (10a), the packetization device (20a) and the output device (30a) include volatile memories.

10. Transmitting device according to one of the preceding claims, characterized in that The number of interface units of the first group and the second group are the same.

11. A receiving device for efficiently forwarding data in a car, the receiving device comprising: - an output interface device (10b), the output interface device having a plurality of output interface units, the output interface units having a first group of output interface units and a second group of output interface units, each of the first group of output interface units being configured in hardware to transmit continuous data, and each of the second group of output interface units being configured in hardware to transmit discontinuous data; - an unpacking device (20b) arranged to separate the data from the forwarding information and the data protection information; as well as - an input device (30b) in a receiving direction, the input device being arranged to receive the data on a physical transmission channel, wherein the output interface device (10b), the unpacking device (20b) and the input device (30b) are unidirectionally communicatively coupled.

12. A system arrangement comprising a transmitting device according to one of claims 1 to 10 and a receiving device according to claim 11, the transmitting device and the receiving device being communicatively coupled by means of a serial data link.

13. The system arrangement according to claim 12, characterized in that Provide static routing and / or hard wiring between all devices, equipment and units.

14. System arrangement according to claim 12 or 13, characterized in that The system arrangement is integrally formed.

15. System arrangement according to any one of claims 12 to 14, characterized in that The input interface device (10a) and the input interface device (10b) have a hardwired communicative coupling with each other.

16. The system arrangement according to claim 15, characterized in that The system arrangement is configured to be capable of performing a functional test, namely inputting and outputting the same data through direct data communication between the input interface device (10a) and the input interface device (10b).

17. A method of providing an input device for efficiently routing data on a virtual data path, the method comprising: - providing (100) an input interface device, the input interface device having a plurality of input interface units, the plurality of input interface units having a first group of input interface units and a second group of input interface units, the first group of input interface units each being configured in hardware to receive continuous data, the second group of input interface units each being configured in hardware to receive discontinuous data; - providing (101) a packetizing device, said packetizing device being arranged to enrich said data with forwarding information and data protection information; as well as - providing (102) an output device arranged to provide said data to a physical transmission channel, wherein said input interface device, said packetizing device and said output device are unidirectionally communicatively coupled.

18. A method for providing a system arrangement according to any one of claims 12 to 16, the system arrangement comprising providing a transmitting device according to any one of claims 1 to 10 and a receiving device according to claim 11, the transmitting device and the receiving device being communicatively coupled.

19. A computer program product comprising instructions which, when executed by at least one computer, cause the computer to perform the steps of the method according to claim 17 or 18.

20. A computer-readable storage medium comprising instructions which, when executed by at least one computer, cause the computer to perform the steps of the method according to claim 17 or 18.

Images