Test system
By adopting multiple distributed memory units cascaded and reflected memory technology in the HIL test system, the problem of high data transmission delay caused by Ethernet dependence in the existing technology is solved, and low-latency and efficient data sharing between industrial control machines is realized. Synchronization.
Patent Information
- Application Number
- CN202420436197.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Priority Date
- 2023-03-17
- Filing Date
- 2024-03-06
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2034-03-06
AI Technical Summary
In the existing HIL test system, communication means rely too much on Ethernet, resulting in high data transmission delays and cannot meet the data sharing needs of complex vehicle electronic and electrical architectures.
Multiple distributed memory units are cascaded to provide another path for data sharing, and each device is connected through the PCIe bus, and data synchronization is maintained using reflected memory technology to reduce latency and improve efficiency.
It realizes low-latency and efficient data sharing between multiple industrial control machines, ensures data synchronization during HIL testing, and solves the inefficiency and delay problems under Ethernet mode.
Smart Images

Figure CN222071090U_ABST
Abstract
Description
Technical Field
[0001] The utility model relates to the technical field of testing, in particular to a testing system. Background Art
[0002] In cars, new energy vehicles and other vehicles, the electronic and electrical architecture of the entire vehicle is becoming more and more complex. The number of electronic control units (ECUs), data bandwidth, and the processing power of CPUs and GPUs have all changed by an order of magnitude compared to before.
[0003] Hardware-in-the-Loop (HIL) testing can verify the functions of various domain controllers, ECUs, CPUs and other controllers in the vehicle in advance to shorten the controller development cycle.
[0004] In the existing HIL test system, the equipment with data storage and processing capabilities (such as real-time machines, or industrial computers, Real-time Parameter Controls, RTPC, or other devices) and I / O cards in the HIL test system are used to perform test tasks to complete the test of the device under test. Generally speaking, a single industrial computer is used for testing in the HIL system, and data is usually shared between the industrial computer and the I / O card through Ethernet. It can be seen that the communication means of the internal devices of the HIL system (such as the industrial computer) are too dependent on Ethernet, which will cause problems such as high data transmission delay. Utility Model Content
[0005] The utility model aims to provide a test system, in which a plurality of devices are cascaded through a plurality of distributed memory units in the HIL test system, and further, the cascaded distributed memory units can provide another path for data sharing between devices, thereby solving the problem that the communication means are too dependent on Ethernet.
[0006] To achieve the above-mentioned purpose, the utility model provides a test system, which is a HIL system, comprising: multiple devices and multiple distributed memory units; the multiple distributed memory units are cascaded in sequence; the multiple devices correspond to the multiple distributed memory units one by one, each of the devices is connected to the corresponding distributed memory unit, and at least one of the multiple devices is an industrial computer.
[0007] In one embodiment, the test system further includes: at least one I / O unit, at least one of the multiple devices is a control module, the control module is communicatively connected to the I / O unit, and the I / O unit is used to directly or indirectly connect to the device under test.
[0008] In one embodiment, each of the distributed memory units includes a target memory and a memory read-write unit for reading and writing the target memory; each of the devices is connected to the memory read-write unit in the corresponding distributed memory unit, and the target memory in each of the distributed memory units is connected to the memory read-write unit.
[0009] In one embodiment, the plurality of distributed memory units are capable of maintaining data synchronization.
[0010] In one embodiment, in each of the distributed memory units, the memory read / write unit includes: three signal transceivers, an interface controller, a data transfer module, an access arbitration module, and a storage controller, and the three signal transceivers include: an interface signal transceiver, an upper signal transceiver, and a lower signal transceiver;
[0011] The interface controller is connected to the corresponding device via an interface signal transceiver in the same distributed memory unit;
[0012] The interface controller is connected to a data transfer module in the same distributed memory unit;
[0013] The data transmission module is connected to the subordinate signal transceiver in the distributed memory unit of the upper level through the superior signal transceiver in the same distributed memory unit;
[0014] The data transfer module is connected to the upper signal transceiver in the distributed memory unit of the next level through the lower signal transceiver in the same distributed memory unit;
[0015] The data transfer module is connected to the access arbitration module in the same distributed memory unit;
[0016] The access arbitration module is connected to a storage controller in the same distributed memory unit;
[0017] The storage controller is connected to a corresponding target storage.
[0018] In one embodiment, the interface controller is also connected to an access arbitration module or a storage controller in the same distributed memory unit.
[0019] In one embodiment, the plurality of distributed memory units cascaded in sequence are connected in an open loop.
[0020] In one embodiment, the control module and the industrial computer are also connected via Ethernet communication.
[0021] In one embodiment, there are multiple control modules, and different control modules are communicatively connected to different I / O units respectively.
[0022] In one embodiment, the distributed memory unit is connected to the corresponding device via a PCIe bus. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 is a schematic diagram of a test system according to a first embodiment of the present utility model;
[0024] Figure 2 is a schematic diagram of a test system according to a first embodiment of the utility model, wherein the distributed memory unit includes a memory read-write unit and a target memory;
[0025] Figure 3 is a schematic diagram of a test system according to a first embodiment of the present utility model being a HIL system;
[0026] Figure 4 It is a schematic diagram of a test system according to the first embodiment of the utility model as a HIL system, the number of control modules is multiple, and each control module is connected to a corresponding I / O unit in a cascade manner;
[0027] Figure 5 It is a schematic diagram of a test system according to the first embodiment of the utility model as a HIL system, the number of control modules is multiple, and each control module is directly connected to the corresponding I / O unit;
[0028] Figure 6 Schematic diagram of a memory read-write unit of a test system according to a second embodiment of the present invention. DETAILED DESCRIPTION
[0029] The following will be combined with the accompanying drawings to describe the various embodiments of the present invention in detail, so as to more clearly understand the purpose, characteristics and advantages of the present invention. It should be understood that the embodiments shown in the accompanying drawings are not intended to limit the scope of the present invention, but are only intended to illustrate the essential spirit of the technical solution of the present invention.
[0030] In the following description, certain specific details are set forth for the purpose of illustrating various disclosed embodiments to provide a thorough understanding of the various disclosed embodiments. However, those skilled in the relevant art will recognize that the embodiments may be practiced without one or more of these specific details. In other cases, well-known devices, structures, and techniques associated with the present application may not be shown or described in detail to avoid unnecessarily obscuring the description of the embodiments.
[0031] Unless the context requires otherwise, throughout the specification and claims, the word "comprise" and variations such as "include" and "have" should be construed in an open, inclusive sense, ie, should be interpreted as "including, but not limited to."
[0032] References throughout the specification to "one embodiment" or "an embodiment" indicate that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any manner in one or more embodiments.
[0033] As used in this specification and the appended claims, the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It should be noted that the term "or" is generally employed in its sense including "or / and" unless the context clearly dictates otherwise.
[0034] In the following description, in order to clearly demonstrate the structure and working mode of the utility model, many directional words will be used for description, but the words "front", "back", "left", "right", "outside", "inside", "outward", "inward", "up", "down", etc. should be understood as convenient terms and should not be understood as restrictive terms.
[0035] The first embodiment of the utility model relates to a test system, please refer to Figure 1 The test system includes: multiple devices 1 and multiple distributed memory units 2, the multiple devices 1 correspond one to one with the multiple distributed memory units 2 for caching target data of the test, each device 1 is connected to the corresponding distributed memory unit 2, the distributed memory unit 2 can be connected to the corresponding device 1 through a PCIe bus, and at least one of the multiple devices 1 is an industrial computer.
[0036] Multiple distributed memory units 2 are cascaded in sequence, and the multiple distributed memory units 2 cascaded in sequence can be connected in an open loop ( Figure 1 In the example, multiple distributed memory units 2 are connected in an open loop, but they can also be connected in a closed loop.
[0037] The device 1 referred to in this specification may refer to a circuit, a circuit board, a combination of circuit boards, or an overall structure including a circuit board and other structures (such as an assembly and / or a housing, etc.).
[0038] In one example, the test system further includes: a cluster control module, the cluster controller is used to manage each industrial computer. The cluster control module can be any industrial computer, or another device that is in communication with each industrial computer.
[0039] Compared with the prior art of performing HIL testing through a single industrial computer, the test system of the specific example of the present application can be configured with multiple industrial computers, and the multiple industrial computers are cascaded through multiple distributed memory units, and the cascaded multiple distributed memory units are used to cache and share the target data of the test.
[0040] Furthermore, multiple distributed memory units can keep data synchronized.
[0041] In a specific example, the use of distributed memory units can realize data sharing between multiple industrial computers, that is, multiple distributed memory units are used to cache the target data generated in the HIL test, so as to facilitate data sharing between multiple industrial computers. Compared with the inefficient and high-latency data sharing method between devices under the Ethernet mode, the method of reading and writing memory in the utility model is relatively efficient, which can ensure low latency and high efficiency of data sharing between devices during the HIL test. When there are multiple industrial computers, since data sharing is realized between devices with low latency and high efficiency, it can help to ensure the synchronization of shared data of each industrial computer relative to the control module.
[0042] In one example, multiple distributed memory units keep data synchronized by means of reflective memory, as follows:
[0043] Reflective memory is an existing shared memory system that enables multiple independent devices to share data. In this embodiment, multiple distributed memory units can use multiple reflective memory nodes. For each distributed memory unit, when it needs to cache new data, it will send the new data to the next distributed memory unit after caching the new data. Each subsequent distributed memory unit will also cache the new data and send it to the next distributed memory unit until all distributed memory units have cached the new data, thereby maintaining data synchronization of multiple distributed memory units; for multiple distributed memory units connected in a ring, the data that needs to be cached can be transmitted from the current distributed memory unit along the ring network once and then stopped, so that all distributed memory units complete data caching; for multiple distributed memory units connected in an open loop, the current distributed memory unit of the data that needs to be cached will transmit the data simultaneously along the cascade forward and reverse directions, and the data will stop transmitting after being transmitted to the first and last two distributed memory units, so that all distributed memory units complete data caching.
[0044] For example, the multiple distributed memory units in this embodiment are similar to the reflective memory module in the patent application with application number CN201820735369.0 and the reflective memory card in the patent application with application number CN201410679949.9. Taking the patent application CN201410679949.9 as an example, multiple computers are connected through reflective memory cards, and the topological connection of multiple reflective memory cards is used to realize real-time sharing and transmission of data between multiple computers. The multiple devices 1 in this embodiment can also realize similar real-time sharing and transmission of data through multiple distributed memory units.
[0045] In one embodiment, each distributed memory unit 2 includes a target memory 21 for caching target data of the test, and a memory read / write unit 22 for reading and writing the target memory. Each device 1 is connected to the memory read / write unit 22 in the corresponding distributed memory unit 2; multiple memory read / write units 22 in multiple distributed memory units 2 are sequentially cascaded to sequentially cascade multiple distributed memory units 2 to transmit data and / or operation instructions (such as write operation instructions) between multiple distributed memory units 2; multiple distributed memory units 2 cascaded in sequence can be connected in an open loop ( Figure 1 In the example, multiple distributed memory units 2 are connected in an open loop, but they can also be connected in a closed loop. The memory read / write unit 22 is connected to the target memory 21 for reading and writing the target memory 21.
[0046] Among them, the memory read-write unit 22 can write the received target data into the target memory 21 and send the target data to the memory read-write unit 22 of the cascaded distributed memory unit 2; the memory read-write unit 22 is also used to read the target data from the target memory 21.
[0047] That is to say, the memory read-write unit 22 performs data read and write operations on the connected target memory 21. For example, each device 1 sends a data read or write operation instruction to the memory read-write unit 22, and the memory read-write unit 22 executes the operation instruction to perform data read and write operations on the target memory 21.
[0048] Among them, for the target memory, the reading and writing of data must be completed through corresponding operation instructions. Therefore, in the prior art, there are several solutions for the relationship and conversion algorithm between the data (such as target data) and the operation instructions for reading and writing the data (such as target data).
[0049] Figure 2The test system can be a HIL system, in which case the test system also includes: an I / O unit, at least one of the multiple devices being a control module, the control module can be a circuit, or can refer to a circuit board, a combination of circuit boards, or an overall structure including a circuit board and other structures (such as assemblies and / or housings, etc.), the control module is communicatively connected to the I / O unit, and the I / O unit is used to directly or indirectly connect to the device under test.
[0050] This embodiment utilizes multiple cascaded distributed memory units 2 to cascade multiple devices 1, and the cascaded multiple distributed memory units 2 maintain data synchronization, thereby being able to synchronize all devices 1 between multiple distributed memory units 2. This embodiment provides a reliable hardware foundation for the implementation of such data synchronization. When the hardware architecture in this embodiment is adopted, when data synchronization is implemented using the existing reflective memory method, each time a write operation instruction is generated, the operation request containing the operation instruction is passed around the cascaded devices, and then the memory read-write unit 22 that obtains the operation request can execute the corresponding operation instruction to implement the writing of the target memory 21 in the same distributed memory unit 2.
[0051] Based on the hardware architecture of the present invention, a reliable way different from Ethernet can be provided for data sharing between devices (for example, between industrial computers and control modules, between industrial computers, and even between other devices and industrial computers and control modules), and the process eliminates various defects under the Ethernet mode. Compared with the inefficient and high-latency data sharing method between devices under the Ethernet mode, the method of reading and writing memory in the present invention is relatively efficient, which can ensure low latency and high efficiency of data sharing between devices during HIL testing.
[0052] Furthermore, when there are multiple industrial computers, low-latency and efficient data sharing between devices can help ensure the synchronization of shared data of each industrial computer relative to the control module.
[0053] The target data refers to any data that the industrial computer inside the HIL system needs to interact with during the HIL test process, such as at least one of the following: target data transmitted between the industrial computer and the I / O unit, and target data transmitted between industrial computers; and the data content that needs to be shared between devices is not an improvement of the present application.
[0054] In a specific example, corresponding to the above I / O board, the target data may include at least one of the following: the downlink information generated by the industrial computer to be sent to the device under test; the uplink information from the device under test to be sent to the industrial computer.
[0055] Furthermore, if the functions of the I / O board are relatively diverse, the target data may also include at least one of the following: the downlink information generated by the industrial computer that needs to be sent to the I / O unit for processing; the uplink information generated by the I / O unit that needs to be sent to the industrial computer.
[0056] In this embodiment, multiple devices are integrated in the HIL system, including an industrial computer and a control module, which can help meet more diverse and complex testing requirements. On this basis, the utility model utilizes cascaded multiple distributed memory units to cascade multiple devices, and realizes data synchronization of target data in the target memory of all devices in a cascaded manner.
[0057] For an example, see Figure 3 The HIL system includes: the above-mentioned distributed memory unit 2, industrial computer pool 3, control module 4 and I / O pool 5. Among them, the industrial computer pool 3 may include at least one industrial computer 31, and the I / O pool 5 may include multiple I / O units 51. The industrial computer 31 and the I / O units 51 may be arranged in different cabinets or in the same cabinet. Specifically, the number of industrial computers 31 in the industrial computer pool 3 may be fixed or expandable, and the industrial computers 31 in the industrial computer pool 3 may be arranged in the same cabinet or in different cabinets. The number of I / O units 51 in the I / O pool 5 may be fixed or expandable, and the I / O units 51 in the I / O pool 5 may be arranged in the same cabinet or in different cabinets.
[0058] In one example, the industrial computer pool 3 includes at least one configurable number of industrial computers 31 (the figure takes three industrial computers 31 in the industrial computer pool 3 as an example), that is, the number of industrial computers 31 in the industrial computer pool 3 is scalable, and the number can be configured according to demand, site, cost, etc. Among them, the industrial computers 31 in the industrial computer pool 3 are connected to each other in communication.
[0059] In one example, the I / O pool 5 includes at least one configurable number of I / O units 51 (the figure takes three I / O units 51 in the I / O pool 5 as an example), that is, the number of I / O units 51 in the I / O pool 5 is expandable, and the number can be configured according to demand, site, cost, etc. Among them, the I / O units 51 in the I / O pool 5 are connected to each other in communication.
[0060] The control module 4 is communicatively connected with the industrial computer 31 in the industrial computer pool 3, and the control module 4 is also communicatively connected with each I / O unit 51 in the I / O pool 5. Among them, the control module 4 can be a computer including an I / O controller. The control module 4 and each I / O unit 51 are connected to the same EtherCAT network, wherein the I / O unit 51 is connected to the control module 4 in a cascade manner and communicates based on EtherCAT, and the use of EtherCAT can basically meet the demand for low latency. In addition, the I / O unit 51 can also be plugged into the control module 4, for example, the I / O unit 51 is connected to the control module 4 via a data bus (such as a PCIe bus) of the control module 4.
[0061] The industrial computer 31 can be understood as part or all of the real-time simulator RTPC in the HIL system.
[0062] The I / O unit 51 can be understood as an input / output unit.
[0063] Specifically, it can be understood that the I / O unit 51 satisfies at least one of the following:
[0064] Able to input data relative to the device under test 6;
[0065] Capable of outputting data relative to the device under test 6;
[0066] Able to input data relative to industrial computers;
[0067] Able to output data relative to industrial computers;
[0068] The data A input and / or output of the I / O unit 51 to the device under test 6 and the data B input and / or output of the I / O unit 51 to the industrial computer 31 may be related or unrelated.
[0069] Specifically, data A and data B may be different data with the same content, for example, a digital signal with a certain content is received from the industrial computer 31, and an analog signal with the same content is sent to the device under test 6, or vice versa, for example, a signal before the fault is injected is received from the industrial computer, and a signal after the fault is injected by the I / O unit 51 is sent to the device under test 6;
[0070] Data A and data B may also be data with the same content and the same format;
[0071] Data A and data B may also be data of different contents. For example, data A and data B are respectively a trigger signal for triggering the I / O unit 51 to generate a certain Sign1 signal and the Sign1 signal. For another example, the I / O unit 51 needs to obtain a certain conditional signal from the industrial computer 31 to simulate the Sign2 signal to be sent to the device under test. In this case, the conditional signal and the Sign2 signal are respectively data A and data B.
[0072] The I / O unit 51 may refer to a circuit, a circuit board, or a device including a circuit board and other assemblies.
[0073] In one example, the I / O unit 51 can interact with the industrial computer 31 via the control module 4, and can also interact with the device under test 6 (such as a vehicle controller) directly or via a switching matrix.
[0074] The I / O unit 51 can only realize the input and output functions. In some examples, the transmitted signals can also be processed during the input and output process, such as signal conversion, fault simulation, information simulation, signal generation, on-off control, etc. It can be seen that as long as the signal interaction between the industrial computer 31 and the device under test 6 can be realized, whether or not other functions are integrated, it can be used as an implementation method of the I / O unit 51.
[0075] The I / O unit 51 may be an I / O board, for example, a board supporting at least one of the following functions: digital signal input, analog signal input, digital signal output, analog signal output, PWM signal input, PWM signal output, high-side power output, and low-side power output. The acquisition and output of high-speed signals can be further realized. In addition, the flexible configuration of board resources can be realized according to the requirements. The board accuracy and sampling frequency indicators brought by this technology have reached the industry-leading level.
[0076] The I / O boards include at least one of the following: AD PWM-IN board, DAC board, FIU board, PWM-OUT board, RELAY-IO board, RC board, PSI5&DSI3&SENT board, multi-bus board (Flexray / CANFD / LIN), Eth (vehicle-mounted Ethernet) board, etc.
[0077] The I / O board may also be, for example, at least one of the following special boards: a current output board, a thermocouple board, a battery simulator, a temperature simulator, a motor board, and an IO_HUB board.
[0078] It should be noted that Figure 3The number of control modules 4 is taken as an example, but it is not limited thereto. The number of control modules 4 can also be multiple, each control module 4 corresponds to one or more I / O units 51, each I / O unit 51 corresponds to only one control module 4, and each control module 4 is connected to the corresponding I / O unit 51. Each control module 4 and the corresponding I / O unit 51 can be connected in a cascade manner, such as Figure 4 As shown, it is taken as an example that the number of control modules 4 is 2 and each control module 4 corresponds to 3 I / O units 51; or each control module 4 is directly connected to the corresponding I / O units 51, such as Figure 5 As shown, it is taken as an example that the number of control modules 4 is 2 and each control module 4 corresponds to a plurality of I / O units 51 .
[0079] In this embodiment, each I / O unit 51 is directly or indirectly connected to the device under test 6, and the number of the device under test 6 can be one or more. Figures 3 to 5 In the example, the direct connection between the I / O unit 51 and the device under test 6 is taken as an example, that is, the device under test 6 is directly connected to the port of each I / O unit 51 through a connector to realize signal transmission; different I / O units 51 can be connected to different pins of the device under test 6 to transmit different information. In another example, a switching matrix can also be set in the HIL system, and the switching matrix is connected between the I / O unit 51 and the device under test 6, that is, each I / O unit 51 is indirectly connected to the corresponding device under test 6 through the switching matrix. The switching matrix can be configured as needed, that is, when the switching matrix is set, the device under test can be connected to the switching matrix more freely, and then the communication connection between the I / O unit 51 and the corresponding device under test 6 can be achieved by simply configuring the switching matrix.
[0080] As automotive functions become increasingly complex and data bandwidth increases (cameras, lidar), CPU processing power has exceeded 50,000 DMIPS, and AI computing power has even reached 1,000 TOPS. Traditional isolated single industrial computers can no longer meet this test requirement. Only by clustering and pooling more computing resources, CPU resources, and bus bandwidth together can the simulation resource bottleneck be solved. The above solution includes the use of industrial computer pools, which can effectively solve the problem of resource bottlenecks. In addition, the solution in this manual can be applied to solve the resource bottleneck while ensuring efficient and effective test operation.
[0081] Multiple devices 1 include: an industrial computer 31 and a control module 4 in the HIL system, that is, the industrial computer 31 corresponds to the distributed memory unit 2 one by one, the industrial computer 31 is connected to the memory read-write unit 22 of the corresponding distributed memory unit 2, the control module 4 and a distributed memory unit 2, the control module 4 is connected to the memory read-write unit 22 of the corresponding distributed memory unit 2, and the memory read-write units 22 of multiple distributed memory units 2 are cascaded in sequence; thereby, the cascade connection between the industrial computer 31 and the control module 4 is realized through the cascaded multiple distributed memory units 2.
[0082] In the vehicle hardware-in-the-loop test, multiple DUTs 6 (such as ECUs) need to be tested simultaneously, requiring the HIL system to simulate multiple physical systems simultaneously. The single-cabinet industrial computer 31 cannot meet such applications. Different physical systems need to be jointly simulated in different HILs, such as realizing joint simulation between different industrial computers 31. For this purpose, the solution involved in this specification needs to be adopted to ensure the data synchronization performance of cluster work.
[0083] The second embodiment of the utility model relates to a test system. The main difference between this embodiment and the first embodiment is that this embodiment provides a specific structure of a memory read-write unit in a distributed memory unit.
[0084] Please refer to Figure 6 In each distributed memory unit 2, the memory read / write unit 22 includes: three signal transceivers, and an interface controller 221, a data transfer module 222, an access arbitration module 223 and a storage controller 224 that are sequentially connected in communication, and the three signal transceivers include: an interface signal transceiver 2201, an upper signal transceiver 2202 and a lower signal transceiver 2203. Among them, the three signal transceivers, the interface controller 221, the data transfer module 222, the access arbitration module 223 and the storage controller 224 can be implemented based on FPGA.
[0085] It should be noted that, in this embodiment, the access arbitration module 223 is connected between the data transmission module 222 and the storage controller 224 as an example, but it is not limited thereto. The access arbitration module 223 may also be connected between the interface controller 221 and the data transmission module 222 .
[0086] In addition, the interface controller 221 (eg, a PCIE controller) and the target memory 21 (eg, a DDR) may also be directly connected, and data reading or even writing may also be achieved based on this connection mode.
[0087] In the memory read-write unit 22 of each distributed memory unit 2, the interface signal transceiver 2201 is connected to the device corresponding to the distributed memory unit, the upper-level signal transceiver 2202 is connected to the lower-level signal transceiver 2203 of the upper-level distributed memory unit 2, and the lower-level signal transceiver 2203 is connected to the upper-level signal transceiver 2202 of the lower-level distributed memory unit.
[0088] In the memory read / write unit 22 of each distributed memory unit 2:
[0089] The interface signal transceiver 2201 is used to receive operation instructions sent by the connected device, and the operation instructions include write operation instructions and / or read operation instructions.
[0090] The interface signal transceiver 2201 sends the operation instruction to the interface controller 221 , and the interface controller 221 sends the write operation instruction to the data transfer module 222 .
[0091] The upper level signal transceiver 2202 receives the write operation instruction sent by the upper level distributed memory unit 2, and the data transmission module 222 is connected to the upper level signal transceiver 2202, and can receive the write operation instruction;
[0092] The data transmission module 222 is connected to the lower-level signal transceiver 2203 , and can send the write operation instruction to the distributed memory unit of the next level via the lower-level signal transceiver 2203 .
[0093] The data transmission module 222 sends all received operation instructions to the access arbitration module.
[0094] The access arbitration module 223 is used to send the received operation instruction to the storage controller 224 .
[0095] The storage controller 224 is used to execute all received operation instructions and perform read and write operations on the target memory 21 .
[0096] In one example, the interface controller 221 is also connected to the access arbitration module 223 or the storage controller 224 in the same distributed memory unit 2 to directly or indirectly feed back the read operation instruction to the storage controller 224. For example, the read operation instruction can be sent from the interface controller 221 to the access arbitration module 223, and then sent to the storage controller 224 via the access arbitration module 223; for another example, the read operation instruction can be sent directly from the interface controller 221 to the storage controller 224.
[0097] In another example, the read operation instruction may also be transmitted to the access arbitration module 223 via the data transmission module 222 , and then finally given to the storage controller 224 .
[0098] In other examples, the operation instruction may not be forwarded through the access arbitration module, and thus the access arbitration module may not be used, that is, the data transmission module is directly connected to the controller.
[0099] In addition, when the storage controller 224 is also connected to the interface controller 221 in the same distributed memory unit 2, the target data read from the target memory by the storage controller 224 can be sent to the corresponding device 1 through the interface controller 221. In other examples, the target data read from the target memory by the storage controller 224 can also be fed back from the storage controller 224 to the interface controller 221 through the access arbitration module 223 and / or the data transfer module 222, and then the target data is sent to the corresponding device 1 by the interface controller 221.
[0100] The target memory 21 in this specification can be a built-in or external device, chip, circuit, device containing a device, chip, circuit, etc., which can be used as an example of the target memory 21. In addition, the device 1 can only be externally or internally connected to one memory, namely the target memory 21. A variety of memories can be set in the industrial computer 31, and the target memory 21 can be one of them. At the same time, the target memory 21 can also be understood as a memory used to share data between devices (especially between the industrial computer 31 and the control module 4). The interaction speed between the target memory 21 and the CPU (for example, the speed of writing and reading data) is higher than that of traditional communication networks such as Ethernet, for example, it can be realized by at least one of the methods such as high-speed serial bus and optical fiber. Furthermore, different from traditional communication networks such as Ethernet, it provides a concept of high-speed data sharing.
[0101] The CPU can directly access the target memory 21 just like accessing the local memory, which effectively improves the synchronization efficiency. According to detection, in a specific embodiment, the data synchronization bandwidth can reach 10 Gbps.
[0102] The target memory 21 may be a single memory (eg, DDR) or a cluster of multiple memories.
[0103] Preferred embodiments of the present invention have been described in detail above, but it should be understood that aspects of the embodiments can be modified, if necessary, to employ aspects, features and concepts of various patents, applications and publications to provide further embodiments.
[0104] These and other changes can be made to the embodiments in light of the above detailed description.In general, in the claims, the terms used should not be considered limited to the specific embodiments disclosed in the specification and the claims, but should be construed to include all possible embodiments along with the full scope of equivalents to which these claims are entitled.
Claims
1. A test system, It is characterized in that The test system is a HIL system, comprising: a plurality of devices and a plurality of distributed memory units; the plurality of distributed memory units are cascaded in sequence; The multiple devices correspond to the multiple distributed memory units one by one, each of the devices is connected to the corresponding distributed memory unit, and at least one of the multiple devices is an industrial computer.
2. The test system according to claim 1, It is characterized in that The test system further includes: at least one I / O unit, at least one of the multiple devices is a control module, the control module is communicatively connected to the I / O unit, and the I / O unit is used to be directly or indirectly connected to the device under test.
3. The test system according to claim 1, It is characterized in that Each of the distributed memory units includes a target memory and a memory read-write unit for reading and writing the target memory; each of the devices is connected to the memory read-write unit in the corresponding distributed memory unit, and the target memory in each of the distributed memory units is connected to the memory read-write unit.
4. The test system according to claim 1, It is characterized in that The multiple distributed memory units are capable of maintaining data synchronization.
5. The test system according to claim 3, It is characterized in that In each of the distributed memory units, the memory read / write unit includes: three signal transceivers, an interface controller, a data transfer module, an access arbitration module and a storage controller, and the three signal transceivers include: an interface signal transceiver, an upper signal transceiver and a lower signal transceiver; The interface controller is connected to the corresponding device via an interface signal transceiver in the same distributed memory unit; The interface controller is connected to a data transfer module in the same distributed memory unit; The data transmission module is connected to the subordinate signal transceiver in the distributed memory unit of the upper level through the superior signal transceiver in the same distributed memory unit; The data transfer module is connected to the upper signal transceiver in the distributed memory unit of the next level through the lower signal transceiver in the same distributed memory unit; The data transfer module is connected to the access arbitration module in the same distributed memory unit; The access arbitration module is connected to a storage controller in the same distributed memory unit; The storage controller is connected to a corresponding target storage.
6. The test system according to claim 5, It is characterized in that The interface controller is also connected to an access arbitration module or a storage controller in the same distributed memory unit.
7. The test system according to claim 1, It is characterized in that The multiple distributed memory units that are cascaded in sequence are connected in an open loop.
8. The test system according to claim 2, It is characterized in that The control module and the industrial computer are also connected via Ethernet communication.
9. The test system according to claim 2, It is characterized in that There are multiple control modules, and different control modules are respectively communicatively connected to different I / O units.
10. The test system according to claim 1, It is characterized in that The distributed memory unit is connected to the corresponding device via a PCIe bus.
