OAM module installation state detection system

Abstract

The utility model relates to the technical field of servers, and provides an OAM module installation state detection system, which comprises a processor, a universal bottom plate, an OAM module, a pressure sensing module and a pressure sensitive material, the pressure sensitive material is fixed between the bottom of the OAM module and the universal bottom plate, the pressure sensitive material is connected with the pressure sensing module, the pressure sensing module is connected with the processor, and the OAM module is installed on the universal bottom plate. The OAM pressure value of the OAM module is sensed through the pressure sensitive material, the OAM pressure value is read through the pressure sensing module, real-time automatic monitoring of the OAM pressure value is achieved, and the accuracy of obtaining the OAM pressure value is also improved. According to the invention, the pressure sensitive material is installed between the bottom of the OAM module and the universal bottom plate, and the real-time monitoring of the OAM pressure value is realized through the pressure sensor, thereby facilitating the improvement of the standardization of the installation and monitoring of the OAM module, and also improving the efficiency of the firmness monitoring of the installed OAM module.

Description

Technical Field

[0001] The present application relates to the technical field of servers, and in particular to an OAM module installation status detection system. Background Art

[0002] With the rapid development of application fields such as AI, High Performance Computing (HPC), and big data, the requirements for computing performance are getting higher and higher. Traditional CPU servers are difficult to meet the performance requirements of new businesses. The heterogeneous computing mode composed of CPU, GPU, FPGA, ASIC and other processors for data training or reasoning has gradually become the mainstream. The OCP community has established the Open Accelerator Module (OAM) specification under the server project to standardize the acceleration module, simplify the design of the AI ​​infrastructure, and shorten the hardware design cycle. After the OAM module is produced, it needs to be installed on the Universal Baseboard (UBB) to provide the hardware computing power foundation for AI computing.

[0003] The existing OAM modules are installed manually during production. Manual installation of OAM modules will bring uncertainty to manual operation, resulting in improper installation of the modules; installing OAM modules with a robot arm places high demands on production line costs. After the OAM modules are produced, they must be transported over long distances and then put on the shelves for use in the customer's room. The vibrations during transportation and shelving will also affect the firmness of the OAM modules. Slightly improper installation may not be found in the early stage, but with the vibration caused by the long-term high-speed operation of the fan, the OAM module will become looser and looser during use, which will cause various problems in use; and these problems cannot be effectively avoided in a timely manner.

[0004] In summary, the installation and monitoring of existing OAM modules are not standardized. Utility Model Content

[0005] The embodiment of the present application provides an OAM module installation status detection system to solve the technical problem of non-standard installation monitoring of existing OAM modules.

[0006] In a first aspect, an embodiment of the present application provides an OAM module installation status detection system, comprising: a processor, a universal base plate, an OAM module, a pressure sensing module and a plurality of pressure sensitive materials; the pressure sensitive material is fixed between the bottom of the OAM module and the universal base plate, the pressure sensitive material is connected to the pressure sensing module, the pressure sensing module is connected to the processor, the OAM module is mounted on the universal base plate, and each of the pressure sensitive materials is fixed at a different position on the bottom of the OAM module.

[0007] In one embodiment, the pressure sensing module further includes a pressure determiner, and the pressure determiner is connected to the processor.

[0008] In one embodiment, there are multiple OAM modules, multiple pressure sensing modules, and multiple pressure sensitive materials, and the pressure sensitive material 200 installed at the bottom of the same OAM module is connected to the same pressure sensing module.

[0009] In one embodiment, four pressure sensitive materials are installed at the bottom of each OAM module, and each pressure sensitive material is installed at a corner of the bottom plane of the OAM module.

[0010] In one embodiment, the OAM module further includes an identification pin, and the processor is connected to the identification pin.

[0011] In one embodiment, there are multiple identification pins.

[0012] In one embodiment, a mainboard management controller BMC is also included, and the mainboard management controller BMC is connected to the processor.

[0013] In one embodiment, the pressure sensitive material is a foil strain gauge.

[0014] In one embodiment, the processor pre-stores multiple models of the OAM module and a standard pressure value of each model.

[0015] In one embodiment, the pressure sensitive material is adhered to the bottom of the OAM module.

[0016] The OAM module installation status detection system provided in the present application includes: a processor, a universal base plate, an OAM module, a pressure sensing module and a plurality of pressure sensitive materials; the pressure sensitive material is fixed between the bottom of the OAM module and the universal base plate, the pressure sensitive material is connected to the pressure sensing module, the pressure sensing module is connected to the processor, the OAM module is installed on the universal base plate, and each pressure sensitive material is fixed at a different position at the bottom of the OAM module. The present application senses the OAM pressure value of the OAM module through the pressure sensitive material, interprets the OAM pressure value through the pressure sensing module, realizes real-time automatic monitoring of the OAM pressure value, and also improves the accuracy of obtaining the OAM pressure value. The present application installs the pressure sensitive material between the bottom of the OAM module and the universal base plate, and realizes real-time monitoring of the OAM pressure value through the pressure sensor, which is conducive to improving the standardization of the installation monitoring of the OAM module, and also improves the efficiency of monitoring the firmness of the installed OAM module. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a structural diagram of the OAM module installation status detection system provided in an embodiment of the present application.

[0019] Figure 2 It is a flowchart of the OAM module installation provided in the embodiment of the present application.

[0020] Figure 3 It is a structural diagram of the identification pin provided in an embodiment of the present application.

[0021] Reference numerals:

[0022] 100: OAM module; 200: pressure sensitive material; 300: universal baseboard; 400: CPU mainboard. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] It should be noted that in the description of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be a connection between two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] The installation of OAM modules belongs to the server production process. Currently, the installation methods of OAM modules are divided into manual and robotic arm installation. After production, they will be transported over long distances and put on shelves to the customer's room for use, which also poses a great challenge to packaging and transportation.

[0026] Figure 1 Schematic diagram of the structure of the OAM module installation status detection system provided in the embodiment of the present application. Figure 1 An embodiment of the present application provides an OAM module installation status detection system, including: a processor, a universal base plate 300, an OAM module 100, a pressure sensing module and a plurality of pressure sensitive materials 200; the pressure sensitive material 200 is fixed between the bottom of the OAM module and the universal base plate 300, the pressure sensitive material 200 is connected to the pressure sensing module, the pressure sensing module is connected to the processor, the OAM module 100 is installed on the universal base plate 300, and each pressure sensitive material is fixed at a different position on the bottom of the OAM module.

[0027] It can be understood that the pressure sensing module also includes a pressure determiner, and the pressure determiner is connected to the processor.

[0028] It is understandable that there are multiple OAM modules 100, multiple pressure sensing modules, and multiple pressure sensitive materials 200, and the pressure sensitive materials 200 installed at the bottom of the same OAM module 100 are connected to the same pressure sensing module.

[0029] It can be understood that four pressure-sensitive materials 200 are fixed at the bottom of each OAM module 100 , and each pressure-sensitive material 200 is fixed at a corner of the bottom plane of the OAM module 100 .

[0030] Generally, the size of a standard OAM module is 102mm×165mm. The front of the OAM module is composed of acceleration chips such as GPU and FPGA and peripheral circuits. The back of the OAM module is composed of two sets of high-density connectors.

[0031] The universal base plate is used to fix the OAM module. For example, 8 OAM modules are fixed on the universal base plate. The universal base plate with the OAM module installed is connected to the CPU motherboard to form the OAM system, which provides the hardware computing power foundation for AI computing. The OAM module is usually installed on the universal base plate with 4 hand screws. Due to the high power consumption of the OAM module, the OAM module usually also includes a heat sink. Because the OAM module with the heat sink is heavier, and the high-density connector at the bottom of the OAM module has more pins, it is very sensitive to installation accuracy. Once the 4 fixing screws are not installed in place, for example, there is inconsistent screw torque, human error, etc., it is easy to cause crooked pins, pins not fully contacted, etc. At this time, there will be problems such as OAM cannot be recognized, high-speed link quality is poor, and the flow capacity does not meet the requirements.

[0032] like Figure 2 As shown, the OAM module 100 is fixed to the universal base plate 300 by screws. For example, the bottom of the OAM module 100 is rectangular, and on the plane at the bottom of the OAM module 100, the OAM is fixed at each corner by 4 screws. When installed in place according to the required torque, the stroke of the four screws screwed into the screw holes on the universal base plate 300 should be consistent. At this time, the OAM pressure values ​​of the four corners of the OAM module 100 to the universal base plate 300 should also be the same. Assuming that the OAM module 100 weighs 4kg, after tightening the four screws of the OAM module 100 according to the required torque, the OAM pressure values ​​of the four corners of the bottom of the OAM module 100 to the universal base plate 300 should all be equal to the standard pressure value. If the OAM pressure value at a corner is greater than the standard pressure value, it means that the screws of the OAM module 100 at the corner are tightened too tight. If the OAM pressure value at a corner is less than the standard pressure value, it means that the screws of the OAM module 100 at the corner are tightened too loose.

[0033] A plurality of pressure sensitive materials 200 are installed on the bottom of the same OAM module 100, and are used to obtain OAM pressure values ​​at different positions of the bottom. For example, the bottom of the OAM module 100 is rectangular, and a pressure sensitive material 200 is installed at each corner of the rectangle. The pressure sensitive material 200 is located between each plane corner of the OAM bottom and the universal base plate 300, and is used to sense the pressure of the bottom of the OAM module 100 on the universal base plate 300 at each corner in real time. By obtaining the OAM pressure value of each OAM module at different positions, it is helpful to more accurately judge the installation status of the OAM module.

[0034] The pressure sensitive material 200 installed on the same OAM module 100 is connected to the same pressure sensing module for real-time monitoring of the installation status of the OAM module 100. For example, four pressure sensitive materials 200 are installed at the bottom of each OAM module 100. The same pressure sensing module is connected to the four pressure sensitive materials 200 of the same OAM module 100. When the OAM module 100 is installed on the universal base plate 300, the pressure sensitive material 200 installed at the bottom of the OAM module 100 is deformed due to the pressure and produces a change in resistance. The pressure sensing module reads the resistance value of the pressure sensitive material 200 in real time and converts the resistance value into the OAM pressure value of the OAM module 100. For example, when the OAM module 100 has been installed on the universal base plate 300, the OAM pressure value of the OAM module 100 to the universal base plate 300 is monitored in real time by the pressure sensitive material 200 and the pressure sensing module installed at the bottom of the OAM module 100, thereby detecting the tightness of the OAM module 100. When the monitored OAM pressure value is less than the standard pressure value, it is determined that the OAM module 100 is loose. The standard pressure value is the pressure exerted by the OAM module 100 on the universal baseboard 300 when the OAM module 100 is installed on the universal baseboard 300 in a standard manner.

[0035] The pressure judger judges whether the OAM pressure value is a standard pressure value and obtains a judgment result of the OAM pressure value. For example, if the OAM pressure value is a standard pressure value, the judgment result is 1, and if the OAM pressure value is not a standard pressure value, the judgment result is 0. The processor obtains all the pressure value judgment results of the same OAM module 100 through the pressure judger to determine whether the OAM module 100 is installed in a standard manner. For example, the processor obtains the judgment results of 4 pressure values ​​of the same OAM module 100. If the judgment results of the 4 pressure values ​​are all 1, it is determined that the OAM module 100 is installed in a standard manner. If one of the judgment results of the 4 pressure values ​​is not 1, it is determined that the OAM module 100 is not installed in a standard manner.

[0036] By comparing the size of each OAM pressure value of the OAM module with the standard pressure value, the installation status of the OAM module at multiple installation positions is obtained, which is conducive to improving the accuracy of identifying the installation of the OAM module.

[0037] It can be understood that the OAM module 100 further includes an identification pin, and the processor is connected to the identification pin.

[0038] It can be understood that the processor stores multiple models of the OAM module 100 and a standard pressure value for each model.

[0039] It is understandable that there are multiple identification pins.

[0040] Since the weight and structure of different types of OAM modules 100 are different, the standards (standard pressure values) for judging the installation conditions of different types of OAM modules 100 are also different. The identification pin (ID pin) is used to identify the type of the OAM module 100. Connect the identification pin of the OAM module 100 to the processor. The processor can obtain the ID level through the identification pin. The model of the OAM module 100 can be determined by the level of the ID level. The processor pre-stores the ID level and standard pressure values ​​corresponding to various types of OAM modules 100. The processor matches the model of the OAM module 100 through the ID level, and matches the standard pressure value of the OAM module 100 through the model.

[0041] The identification pin (ID pin) is a pin used to identify the type of the OAM module 100. The ID level of the identification pin (ID pin) refers to the level state of the identification pin (ID pin), which is usually used to indicate the identity information or working mode of the device. The ID level of this application includes a high level and a low level, where the high level is marked as 1 and the low level is marked as 0.

[0042] like Figure 3As shown, there may be multiple identification pins (for example, a first identification pin 510, a second identification pin 520, and a third identification pin 530), each identification pin corresponds to an ID level, and multiple ID levels corresponding to an OAM module 100 are obtained through multiple identification pins of an OAM module 100. The model of the OAM module 100 is matched through the multiple ID levels. The matching relationship between the ID level and the number of the OAM module 100 is shown in Table 1. Different OAM module 100 numbers correspond to different OAM module models. For example, the OAM module numbered 1 corresponds to the OAM module model NSP. The processor obtains the ID level of each identification pin, for example, the high level is identified as 1 and the low level is identified as 0. According to the identification of the three ID levels (including ID0, ID1, and ID2) of an OAM module 100, the model of the OAM module 100 is matched. For example, the processor obtains three pin identifiers of an OAM module 100 as 000, then the number of the OAM module 100 corresponding to the three pin identifiers is 1, and the corresponding model of the OAM module is NSP.

[0043] Table 1 Matching relationship between ID level and number of OAM module 100

[0044]

[0045] The model of the OAM module is obtained through the ID levels of multiple identification pins, which expands the number of OAM model models and is conducive to monitoring a large number of OAM model types.

[0046] It is understandable that the OAM module installation status detection system further includes a mainboard management controller BMC, and the mainboard management controller BMC is connected to the processor.

[0047] The Baseboard Management Controller (BMC) is usually embedded in the CPU motherboard 400 and is used to manage and monitor various functions and components of the motherboard, such as power management, temperature monitoring, fan control, etc. It can ensure that the motherboard runs in a safe and stable state and provide diagnostic and management functions to ensure the normal operation of the system.

[0048] The motherboard management controller (BMC) is connected to the processor via a serial two-wire interface I2C. For example, the BMC is connected to the connector via I2C, and the connector is connected to the motherboard management controller (BMC). The motherboard management controller is connected to the processor to obtain the installation status of each OAM module 100. For example, if the installation status is that the OAM module 100 is installed in a standard manner, the processor is marked as 1 and sends 1 to the BMC. If the installation status is that the OAM module 100 is not installed in a standard manner, the processor is marked as 0 and sends 0 to the OAM module. The serial two-wire interface (Inter-Integrated Circuit, I2C) is conducive to improving the communication efficiency between the BMC and the processor. For example, when it is necessary to obtain the installation status of multiple OAM modules 100, the installation status of each OAM module 100 can be efficiently obtained through I2C. When the BMC recognizes that the OAM module is not installed in a standard manner or the installed OAM module is loose, an alarm can be issued to prompt the management personnel.

[0049] It can be understood that the pressure sensitive material 200 is a foil strain gauge.

[0050] It can be understood that the pressure sensitive material 200 is pasted on the bottom of the OAM module 100 .

[0051] The foil strain gauge is made of very thin metal foil, usually steel or copper. For example, the thickness of the foil strain gauge is 0.002-0.008mm metal foil. Since the foil strain gauge is very thin, it will not affect the installation of the OAM module 100. The foil strain gauge can accurately measure the deformation of the OAM module 100 when it is subjected to force. The foil strain gauge is pasted or fixed to the bottom of the OAM module 100 to monitor the pressure of the OAM module 100 on the universal base plate 300 in real time. When the OAM module 100 exerts pressure on the universal base plate 300, the foil strain gauge will deform and produce a resistance change. This resistance change can be read and analyzed by the connected pressure sensing module to obtain the pressure value of the OAM module 100 on the universal base plate 300.

[0052] The OAM module installation status detection system provided in the embodiment of the present application includes: a processor, a universal base plate 300, an OAM module 100, a pressure sensing module and a plurality of pressure sensitive materials 200; the pressure sensitive material 200 is fixed at the bottom of the OAM module, the pressure sensitive material 200 is connected to the pressure sensing module, the pressure sensing module is connected to the processor, the OAM module 100 is installed on the universal base plate 300, and each pressure sensitive material is fixed at a different position at the bottom of the OAM module. The embodiment of the present application senses the OAM pressure value of the OAM module through the pressure sensitive material, interprets the OAM pressure value through the pressure sensing module, realizes real-time automatic monitoring of the OAM pressure value, and also improves the accuracy of obtaining the OAM pressure value. The embodiment of the present application installs the pressure sensitive material between the bottom of the OAM module and the universal base plate, and realizes real-time monitoring of the OAM pressure value through the pressure sensor, which is conducive to improving the standardization of the installation monitoring of the OAM module, and also improves the efficiency of the monitoring of the firmness of the installed OAM module.

[0053] The OAM module installation status detection system provided in the embodiment of the present application introduces a pressure sensing module and pressure sensitive materials, and has the following advantages: timely warning for the current AI server OAM module that is not installed properly, ensuring that the installation of the OAM module meets the requirements after it is put on the shelf in the customer's room, and in the subsequent use process, timely monitoring whether the OAM module is loose due to vibration, thereby avoiding various hidden dangers in the later use process caused by OAM module installation problems. The present application eliminates the risks caused by improper installation of the OAM module during subsequent use by timely warning of the hidden dangers of improper installation of the OAM module caused by the production, transportation and deployment links. The present application monitors the looseness of the OAM module caused by mechanical vibration in real time during use and handles the hidden dangers in a timely manner.

[0054] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0055] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An OAM module installation status detection system, characterized in that: include: Processor, universal baseboard, OAM module, pressure sensing module and multiple pressure sensitive materials; The pressure sensitive material is fixed between the bottom of the OAM module and the universal base plate, the pressure sensitive material is connected to the pressure sensing module, the pressure sensing module is connected to the processor, the OAM module is mounted on the universal base plate, and each of the pressure sensitive materials is fixed at a different position on the bottom of the OAM module.

2. The OAM module installation status detection system according to claim 1, characterized in that: The pressure sensing module further includes a pressure determiner, and the pressure determiner is connected to the processor.

3. The OAM module installation status detection system according to claim 2, characterized in that: There are multiple OAM modules, multiple pressure sensing modules, and multiple pressure sensitive materials. The pressure sensitive materials installed at the bottom of the same OAM module are connected to the same pressure sensing module.

4. The OAM module installation status detection system according to claim 3, characterized in that: Four pressure-sensitive materials are installed at the bottom of each OAM module, and each pressure-sensitive material is installed at a corner of the bottom plane of the OAM module.

5. The OAM module installation status detection system according to claim 1, characterized in that: The OAM module further includes an identification pin, and the processor is connected to the identification pin.

6. The OAM module installation status detection system according to claim 5, characterized in that: There are multiple identification pins.

7. The OAM module installation status detection system according to claim 1, characterized in that: It also includes a mainboard management controller BMC, which is connected to the processor.

8. The OAM module installation status detection system according to claim 1, characterized in that: The pressure sensitive material is a foil strain gauge.

9. The OAM module installation status detection system according to claim 1, characterized in that: The pressure sensitive material is pasted on the bottom of the OAM module.

Images