Disclosed are a method and apparatus for optimizing server system interrupts, a device and a medium, which relate to the field of servers. The method is applied to a server system, and comprises: when a peripheral driver of a kernel space monitors an interrupt request signal sent by a hardware peripheral, reading a hardware event queue in the hardware peripheral, so as to acquire a target hardware event in the hardware event queue; then, converting the target hardware event into a target software event by using the peripheral driver, and writing the target software event into a preset global event queue; reading the target software event in the global event queue by means of a user space, and forwarding the target software event to a corresponding target service process by means of the user space, such that the target service process processes the target. In this way, by using hardware interrupt coalescing and software event coalescing techniques, this solution may not only reduce the interrupt processing overhead, but also reduce the processor utilization.
The person intention reasoning method includes: performing object detection on a to-be-reasoned image to obtain an object detection result; determining that an image portion corresponding to a detection bounding box of each person in the to-be-reasoned image is a to-be-reasoned sub-image of the corresponding person respectively, and acquiring a joint feature and an occlusion probability of a joint of the corresponding person; performing prediction and analysis on the joint feature of corresponding joint based on the occlusion probability to obtain a corresponding prediction feature, and performing correction based on the joint feature and the prediction feature of the joint of the corresponding person to obtain a corresponding correction feature; and performing person intention reasoning by using the object detection result and the correction feature of the joint of the corresponding person to obtain a corresponding person intention reasoning result.
G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
G06T 3/4046 - Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
3.
SYSTEM RUNNING METHOD OF BASEBOARD MANAGEMENT CONTROLLER AND BASEBOARD MANAGEMENT CONTROLLER
Embodiments of the present application relate to the technical field of electronic information and provide a system running method of a baseboard management controller and a baseboard management controller. The method comprises: starting a target operating system on a baseboard management controller, wherein the target operating system is used for managing a target hardware partition among a plurality of hardware partitions obtained by dividing on a server host system; loading a target hardware interface for the target operating system, wherein the target hardware interface is configured to establish a connection between the target operating system and the target hardware partition; and running the target operating system on the baseboard management controller, wherein the target operating system is used for managing the target hardware partition by means of the target hardware interface. The present application solves the problem that the applicability of hardware partitions of a server host system is relatively low, thereby achieving the effect of improving the applicability of the hardware partitions of the server host system.
A fan control system, a server system, and a fan control method and apparatus. The fan control system comprises a measurement circuit and a delay circuit, the measurement circuit acquiring a first voltage of an alternating current power supply and/or a second voltage output by a power supply unit during rotating of a fan; when the first voltage and/or the second voltage drops, a mainboard stops outputting a closing signal to the delay circuit, such that an energy storage unit discharges within a preset time, the delay circuit being provided between an output end of the mainboard and an enabling end of an overcurrent protection switch, and the delay time of the delay circuit being the preset time. The mainboard is used for outputting, when the server system satisfies a preset cooling condition, the closing signal to the overcurrent protection switch by means of the delay circuit. By means of the delay circuit, the fan control system can prevent a fan controller from performing closed-loop control on the rotating speed of the fan, thereby avoiding fan stopping caused by disconnection of the overcurrent protection switch.
Disclosed in the present application are a baseboard management controller, and a basic input/output system debugging method and apparatus, which are applied to the technical field of basic input/output system debugging. The baseboard management controller comprises: a target bus connected to a central processing unit and used for acquiring an access request sent by the central processing unit; a system bus, and a dynamic random access memory mounted on the system bus and used for storing a first basic input/output system image; a bus agent mounted on the system bus and used for configuring a first address range for a preset register and, on the basis of the first address range, forwarding the access request to a memory controller mounted on the system bus, the first address range being an address range in a bus address space of the system bus; and a memory controller, used for accessing the first basic input/output system image in the dynamic random access memory. The present application avoids the problem of lengthy time consumption of basic input/output system refreshing, thereby improving the efficiency of basic input/output system debugging.
The present application relates to the technical field of communications, and in particular relates to a data interaction system and method, a large-scale operation processing method, a device and a medium. The system comprises: a first processor and a second processor, configured to respectively execute different data operations so as to generate operation results and operation completion indications; a first memory, configured to store the operation results; and a read/write controller, connected to the first processor, the second processor and the first memory, the read/write controller being internally provided with a second memory configured to store the operation completion indications and storage information of the operation results in the first memory. The read/write controller is configured to gate the first memory to communicate with a processor generating an operation result, such that the processor writes the operation result into the first memory, and when the read/write controller detects that an operation completion indication and storage information are written into the second memory, to gate the first memory to communicate with the other processor so as to read the operation result from the first memory. The solution of the present application significantly improves data interaction efficiency.
The present application relates to the technical field of servers, and in particular relates to a PCIE device management architecture, method and system, and a device and a medium. The method comprises: acquiring a driver program of a PCIE first switch chip, installing the driver program of the PCIE first switch chip to a baseboard management controller, and establishing a PCIE specification and protocol of a baseboard management controller chip and the PCIE first switch chip; configuring a PCIE first controller in the baseboard management controller to be in an RC mode, and configuring a PCIE second controller of a central processing unit to be in an EP mode; and managing a PCIE device by means of the baseboard management controller, which is configured to be in the RC mode, so as to improve the efficiency of the baseboard management controller managing the PCIE device.
A system starting method includes: reading secure startup data; judging whether a private key number in the secure startup data is the same as a public key number recorded in a one time programmable memory, where the one time programmable memory records a currently effective public key number; when the private key number is the same as the public key number, performing a system startup procedure; and when the private key number is different from the public key number, sending a startup ending instruction.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
H04L 9/30 - Public key, i.e. encryption algorithm being computationally infeasible to invert and users' encryption keys not requiring secrecy
9.
METHOD FOR MANUFACTURING STUB-FREE VIA HOLE, PCB, ELECTRONIC DEVICE, AND STORAGE MEDIUM
Embodiments of the present disclosure relate to the technical field of PCBs, and in particular, relate to a method for manufacturing a stub-free via hole, a PCB, an electronic device, and a non-transitory readable storage medium. The method for manufacturing a stub-free via hole comprises: acquiring a target copper plating length of a to-be-opened via hole; forming a through-hole at a position of the to-be-opened via hole along a thickness direction of a PCB; blocking the through-hole to form a blind hole, so that a distance from a bottom of the blind hole to a surface of the PCB is equal to the target copper plating length; and performing copper plating on an inner wall of the blind hole to form a via hole. In solutions of embodiments of the present disclosure, before copper plating is performed on the through-hole, the through-hole is blocked according to an expected copper plating length of the via hole so as to form a blind hole; as a part where a stub may be formed is shielded, copper will not be attached at this position during subsequent copper plating, so that a via hole stub is completely removed, thereby solving the effect of the via hole stub on the signal integrity of a high-speed line signal link. Compared with a conventional back drilling process, a stub may not be left, thereby achieving the effect of completely removing the via hole stub.
The present application relates to the technical field of computers. Disclosed are a program update method and apparatus, and an electronic device and a non-volatile readable storage medium. The method comprises: moving a new interrupt handler to a physical memory; acquiring upgrade parameters, and on the basis of the upgrade parameters, determining a first location of the new interrupt handler in the physical memory and a second location of an interrupt handler to be upgraded that is in the physical memory; and moving the new interrupt handler in the first location to the second location to replace the interrupt handler to be upgraded. In the program update method provided in the present application, the new interrupt handler is moved to the location of the interrupt handler to be upgraded that is in the physical memory; and since the new interrupt handler is in the physical memory and takes effect immediately after exiting an upgrade program, the interrupt handler is updated without the need to reboot a system.
The present application relates to the technical field of servers. Disclosed are a data access method, system and apparatus, an electronic device and a nonvolatile readable storage medium, which aim to solve the problem in traditional data access technology of insecure data access caused by using a non-secure protocol for data interaction. The data access method applied to a server comprises: when an access request sent by a client is received, determining a protocol conversion flag of the access request; according to the protocol conversion flag, determining a request type of the access request, request types comprising a protocol conversion request and a protocol non-conversion request, and the protocol conversion request being obtained by the client packaging, according to a preset security protocol, a protocol type and protocol data of a non-secure protocol; when the request type is a protocol conversion request, analyzing the protocol conversion request, so as to obtain the protocol type and the protocol data of the non-secure protocol; and, by using a non-secure protocol service process corresponding to the protocol type, processing the protocol data, so as to obtain an access result.
Provided are an IO processing method and system for a multi-control storage system. The IO processing method includes: determining a correspondence between a plurality of strips and a plurality of controllers, so that write processing tasks of all the strips are respectively in the charge of the plurality of controllers, and two strips in the charge of any two controllers do not overlap; receiving an IO task, and determining, from among all the strips, a target strip corresponding to the IO task; determining whether the IO task is a write processing task; if the IO task is a write processing task, determining that a target controller is a controller corresponding to the target strip; if the IO task is not a write processing task, determining that the target controller is any controller; and controlling the target controller to execute the IO task.
An access request capturing method comprises: upon receiving an initial access request from a current user, returning session response information, wherein the session response information comprises a session control identifier and auxiliary authentication data that are stored at different locations; receiving a current non-initial access request from the current user; and when the current non-initial access request carries the session control identifier and does not carry the auxiliary authentication data, capturing the current non-initial access request.
An air guide and noise reduction device and a server. The air guide and noise reduction device comprises: an air guide channel (100), having an air inlet (101) and an air outlet (102), wherein the area of the air inlet (101) is less than the area of the air outlet (102); and a resonant cavity (200), being in communication with the air guide channel (100) by means of a plurality of first openings (300), so that the resonant cavity (200) absorbs, by means of the first openings (300), noise propagating along the air flow of the air guide channel (100), and resonates with the noise. The device can filter and eliminate sound waves propagating from a fan to the surface of a hard disk, can reduce the impact of the sound waves on the performance of the hard disk, so as to improve the performance of the hard disk and reduce the hard disk damage rate, and can provide an efficient and stable noise reduction solution for the server.
Embodiments of the present application provide an attribute value determination method and apparatus, a non-volatile readable storage medium, and an electronic device. The method comprises: when sensors of the same sensor type exist in N devices of the same device type, setting a target attribute corresponding to the sensor type; when an attribute value of the target attribute needs to be read, sequentially reading an attribute value of each sub-attribute among N sub-attributes until an attribute value of one sub-attribute among the N sub-attributes is read or traversal of the N sub-attributes is complete; and when the attribute value of one sub-attribute among the N sub-attributes is read, determining the read attribute value of the one sub-attribute as the attribute value of the target attribute. By means of the present application, the problem in the related art of incompatible monitoring of devices of the same type produced by different manufacturers is solved, thereby achieving the effect of compatible monitoring of devices of the same type produced by different manufacturers.
Disclosed are a person Re-identification (Re-ID) method, apparatus, and device and a storage medium, and the method includes: acquiring a data set, where pieces of data in the data set are unlabeled person images; performing block processing on each piece of data in the data set, performing random ordering on each piece of blocked data to obtain out-of-order data corresponding to each piece of data, and generating negative sample data corresponding to each piece of data based on each piece of data and the corresponding out-of-order data; and performing unsupervised learning based on each piece of data in the data set, the out-of-order data of each piece of data, and the negative sample data of each piece of data to obtain a corresponding ID network, and performing person Re-ID based on the ID network.
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
17.
FAULT PREDICTION METHOD AND APPARATUS, DEVICE, AND READABLE STORAGE MEDIUM
The present application relates to the technical field of computers, and discloses a fault prediction method and apparatus, a device, and a non-volatile readable storage medium. According to the present application, a graph structure related to alert information is constructed on the basis of a data set collected by each sensor of a server at an alert moment, fault prediction data can be calculated on the basis of attribute information of each edge node in the graph structure, and then fault prediction is performed on a target component on the basis of the fault prediction data. The attribute information of each edge node comprises a data change trend, a difference between data and a preset threshold, and the degree of association between the data and the alert information, so that changes in various sensor data collected at an alert moment can be comprehensively considered, ensuring the prediction accuracy, and achieving accurate fault prediction of server components in the future.
The present application relates to a computing system, a model training method and apparatus, and a product. The computing system relates to a computing unit, and the computing unit comprises: a main board, which is configured with a central processing unit (CPU); and a base board, which is connected to the main board by means of a first communication link, wherein the base board is configured with a plurality of accelerator cards, and the plurality of accelerator cards are connected to each other by means of a second communication link. The main board is used for splitting a training task of a target model into a plurality of concurrent model training tasks and releasing same to the plurality of accelerator cards, and processing training results of the plurality of accelerator cards, so as to obtain a trained target model. The plurality of accelerator cards are used for concurrently executing the respective model training tasks thereof, so as to obtain the training results. The computing system forms an elastically scalable computing system architecture by means of modular base-board design and interconnection, such that the computing power and bandwidth of the computing system can match model training tasks at different parameter scales.
The present application relates to a processing method and apparatus for a runtime file of a PCIE device, and a device. The main technical solution comprises: in response to a base input/output system loading a memory drive file of a PCIE device, acquiring identification number information of the PCIE device; on the basis of the identification number information and prestored identification number information, determining whether the base input/output system has processed a historical PCIE device having the same model as the PCIE device, and obtaining a determination result; on the basis of the determination result, processing a runtime file in the memory drive file of the PCIE device.
The embodiments of the present application relate to the field of computers. Provided are a switch device, and a serial communication interface switching method and apparatus. The switch device comprises a baseboard, a serial communication interface unit, and, provided on the baseboard, a processor, a resistor unit and a gating unit, wherein the serial communication interface unit comprises a plurality of serial communication interfaces, each serial communication interface comprises a signal input end and a signal output end, and the gating unit is separately and electrically connected to the processor and the resistor unit and is configured to, when a control signal is received, control one serial communication interface to be connected to the processor. The present application solves the problem in related art of relatively high costs of production and management of switch devices, thus achieving the effect of greatly reducing the costs of production and management of switch devices.
The present application relates to the technical field of servers. Disclosed are a server system and a communication method therefor. The server system comprises: at least one first processor board and a host server, wherein the at least one first processor board is in communication connection with the host server by means of a switching network; the first processor board comprises a first field programmable gate array chip and a first processor chip; the first field programmable gate array chip and the first processor chip are packaged and interconnected; the host server is configured to transmit host data to the first field programmable gate array chip by means of the switching network; and the first field programmable gate array chip is configured to process the host data, receive request data which is sent by means of the first processor chip, generate a communication protocol message on the basis of the processed host data and the request data, and transmit the communication protocol message to a destination processor board by means of the switching network. By means of the present application, pooling acceleration of a server system is realized, thereby realizing efficient layout of computing power resources.
A compute express link (CXL) data transmission board and a data transmission control method. The CXL data transmission board comprises: a control chip, wherein the control chip is a chip supporting a CXL protocol, and uplink ports and downlink ports are deployed on the control chip; the uplink ports connected to hosts, wherein the hosts are devices supporting a peripheral component interconnect express (PCIe) protocol or devices supporting a CXL protocol; and the downlink ports connected to processors and/or memory modules, wherein the downlink ports are correspondingly connected to the uplink ports, and the hosts are configured to transmit data to the corresponding downlink ports by means of the uplink ports, so as to transmit the data to the processors and/or the memory modules by means of the downlink ports. By means of the present application, the problem in the related art that resources cannot be re-allocated on the basis of different workloads is solved, achieving the effect of flexibly allocating resources.
The present application relates to the technical field of signal transmission. Disclosed are a method and apparatus for establishing a peripheral component interconnect express (PCIe) optical interconnection link, and a device, a non-volatile readable storage medium and a system. The method comprises: acquiring an upstream data signal which is transmitted by means of an electrical path, and detecting whether there is an electrical idle ordered set in the upstream data signal (S11); if there is an electrical idle ordered set, recording the current link rate, and by means of counting the electrical idle ordered set, determining whether the current sending of the electrical idle ordered set has been completed (S12); and when the current sending of the electrical idle ordered set has been completed, generating a target signal sequence of a corresponding rate according to the link rate, and sending the target signal sequence to an opposite end by means of a PCIe optical interconnection link, such that the opposite end maintains stable operation on the basis of the target signal sequence (S13). A PCIe optical interconnection link can be established, and the success rate of establishing the PCIe optical interconnection link can be increased, thereby avoiding the problem of a link establishment failure caused by an electrical idle state during link establishment.
Provided in the embodiments of the present application are an asset information reporting method and apparatus, and a non-volatile readable storage medium and an electronic device. The asset information reporting method comprises: when a target device supports memory expansion, by means of a basic input output system and from a configuration space register of a memory expander controller of the target device, reading serial presence detect (SPD) information of a designated memory bank mounted to the target device, wherein the target device is a device that supports a CXL protocol, which is an open interconnection standard; and when target SPD information has been read, by means of the basic input output system, reporting the target SPD information to a central processing unit of the target device as system asset information.
The present disclosure provides a method and apparatus for traffic management and control method, device and readable storage medium. The method includes: acquiring a data frame sent from a heterogeneous accelerator; selecting a target traffic management and control mode corresponding to data in the data frame from a plurality of preset traffic management and control modes; and managing and controlling the data in the data frame according to the target traffic management and control mode, so as to allocate the data to a QDMA queue, and send the data by the QDMA queue, and process the data by a corresponding CPU core.
Embodiments of the present application provide a single-phase cold plate liquid cooling system and a control method therefor, and an electronic device. The single-phase cold plate liquid cooling system comprises a cooling pipeline, a measurement assembly, and an auxiliary pipeline. The cooling pipeline comprises a heat exchanger and at least one single-phase cold plate, the heat exchanger is communicated with the single-phase cold plate, and the cooling pipeline has a forward circulation mode and a reverse circulation mode. The measurement assembly is arranged at the quick connector of the single-phase cold plate and/or the cooling pipeline so as to measure an operating parameter of the cooling pipeline. The auxiliary pipeline is communicated with the single-phase cold plate in an openable and closable fashion, and the auxiliary pipeline is provided with a vacuum generator. When the measurement assembly detects that the operating parameter exceeds a preset value, the circulation mode of the cooling pipeline changes, and the auxiliary pipeline is communicated with the single-phase cold plate. The present application solves the problem that electrochemical corrosion and blockage easily occur at a single-phase cold plate and a quick connector, thereby achieving the effect of improving the stability and the maintenance convenience of the liquid cooling system.
Embodiments of the present application relate to the technical field of computers, and provide a faulty memory module processing method and apparatus, an electronic device, and a nonvolatile readable storage medium. The faulty memory module processing method comprises: acquiring a first power-off command, wherein the first power-off command is used for instructing a baseboard management controller of a memory resource pool to perform power-off processing on a faulty memory module in the memory resource pool; and in response to the first power-off command, when a first memory module in the memory resource pool is in a faulty state and the first memory module is allowed to be powered off, sending a second power-off command to a target memory expander controller to which the first memory module belongs, wherein the second power-off command is used for instructing the target memory expander controller to perform power-off processing on the first memory module in a plurality of memory modules belonging to the target memory expander controller. The present application solves the problem in the related art of resource waste caused by power-off of the whole memory resource pool in faulty memory module processing methods.
Provided in the embodiments of the present application are a method and apparatus for migrating memory data, and a non-volatile readable storage medium and an electronic apparatus. The method comprises: detecting a memory usage parameter of a target memory space, wherein the target memory space is a memory space that is allocated to a target application of memory data to be migrated, the target memory space comprises a first memory space of a first type and a second memory space of a second type, the memory usage parameter is used for indicating a frequency distribution of the target memory space being used, and the operation efficiency of the target application for the first memory space is higher than the operation efficiency of the target application for the second memory space; selecting a third memory space from the second memory space according to the memory usage parameter and a target migration parameter; and migrating, to the first memory space, first memory data which is stored in the third memory space. By means of the present application, the problem of the usage efficiency of a memory being relatively low is solved, thereby achieving the effect of improving the usage efficiency of the memory.
The present application provides a sequential read prefetching method and apparatus based on an Inspur Cluster File System (ICFS) distributed block storage system, a device, and a non-volatile readable storage medium. The method includes: in response to an OSD receiving a read request issued by a client, determining whether the read request is a sequential read request; in response to the read request being the sequential read request, creating a prefetching sliding window according to a data object to be read in the read request; in response to completion of the creation of the prefetching sliding window, calculating, according to the data object to be read in the read request, anew volume object needing to be prefetched; and adding the calculated new volume object needing to be prefetched into a queue of objects to be prefetched of the prefetching sliding window and executing prefetching.
The present application relates to the technical field of artificial intelligence, and discloses a visual positioning method and apparatus, a device, and a medium. The method includes: performing feature splicing on an image encoding feature and a text encoding feature; performing feature fusion on spliced encoding features to obtain a first fused encoding feature; performing noise correction on the first fused encoding feature and the text encoding feature on the basis of a preset cross-attention mechanism to obtain a corrected fused feature and a corrected text encoding feature, and performing feature fusion on the spliced encoding feature and the corrected text encoding feature to obtain a second fused encoding feature; and correcting a preset frame feature using a target encoding feature on the basis of the corrected fused feature and the second fused encoding feature to predict a regional position coordinate of a target visual object.
G06V 10/72 - Data preparation, e.g. statistical preprocessing of image or video features
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
31.
CLOCK CONTROL METHOD, SYSTEM AND DEVICE FOR SWITCH CHIP, AND SWITCH BOARD
Provided in the embodiments of the present application are a clock control method, system and device for a switch chip, and a switch board. The method is applied to a clock control device, and comprises: receiving clock signals, which are transmitted by clock generators of a plurality of clock types, wherein a clock control device is connected to a switch chip, the switch chip uses clock signals of different clock types when controlling target devices of different device types, and a plurality of clock types correspond to a plurality of device types; identifying a target device type of a target device among the plurality of device types; and transmitting, to the switch chip and the target device, a target clock signal which is transmitted by a target clock generator among the clock generators of the plurality of clock types, wherein the target clock generator is a clock generator of a target clock type corresponding to the target device type. By means of the present application, the problem of the clock adaptation efficiency of a switch chip being relatively low is solved, thereby achieving the effect of improving the clock adaptation efficiency of the switch chip.
The present application relates to a memory failure processing method and apparatus, and a computer device and a storage medium. The method comprises: acquiring correctable error information of a memory; performing an out-of-band memory failure prediction operation according to the correctable error information; according to a prediction result, determining whether to trigger a system control interrupt; in response to the system control interrupt, calling a PRM processing module to acquire memory failure address information corresponding to the triggering of the system control interrupt; and performing an address isolation operation according to the memory failure address information.
Embodiments of the present application relate to the technical field of computers, and disclose a distributed training task scheduling method and apparatus, a device, and a non-volatile readable storage medium. The method comprises: acquiring the scheduling state of each training task, wherein the scheduling state comprises a successful scheduling state and an unsuccessful scheduling state; for unsuccessfully scheduled first training tasks, acquiring the quantity of idle resources of a target cluster resource and the minimum quantity of resources required by the first training tasks; if the quantity of idle resources is less than the minimum quantity of required resources, screening from among successfully scheduled second training tasks a training task from which a resource is allocatable, so as to acquire the allocatable resource; and performing task scheduling on the first training tasks on the basis of the allocatable resource and the quantity of idle resources. The embodiments of the present application can greatly improve the resource utilization rate and the fault-tolerant capability, and shorten the model training cycle.
Embodiments of the present application provide a data access method and apparatus, a non-volatile readable storage medium, and an electronic device. The method comprises: obtaining a first start physical address to be accessed by a processor in a first device and the length of a physical address to be accessed; on the basis of a predetermined first mapping relationship and the first start physical address, determining a second start virtual address corresponding to a target memory space; and sending a data access request to a second device. According to the embodiments of the present application, the problem that the first device cannot access the memory space in the memory of the second device that is allowed to be accessed by the first device is solved, thereby achieving the effect that the first device can access the memory space in the memory of the second device that is allowed to be accessed by the first device.
Embodiments of the present application provide a memory module, and a memory expansion board for a server. The memory module comprises a control chip, a first memory channel and a second memory channel; the control chip is separately connected to the first memory channel and the second memory channel, and a computing quick connection protocol interface adapted to be connected to a device conforming to a quick connection protocol is deployed on the control chip; the first memory channel is deployed on the top surface of a memory board, and the second memory channel is deployed on the bottom surface of the memory board; the first memory channel comprises a plurality of first memory cells, the second memory channel comprises a plurality of second memory cells, and the plurality of first memory cells and the plurality of second memory cells are in one-to-one correspondence and are arranged in mirror symmetry relative to the memory board. The present application solves the problem of low memory capacity and memory expansion capability, thereby achieving the effect of improving the memory capacity and the memory expansion capability.
Embodiments of the present application provide a data backup method, apparatus and system, and a nonvolatile readable storage medium. The method comprises: acquiring metadata information in a container cloud platform and service system data information generated by a service system running on the container cloud platform, wherein the metadata information is used for representing attribute information of the container cloud platform; and backing up the metadata information and the service system data information on the basis of an association relationship between the service system data information and the metadata information. The present application solves the problem in the related art that backup data information cannot be identified by an original container cloud platform due to the fact that the backup of the container cloud platform is only to repeatedly duplicate a file directory, thereby achieving the effect of improving the disaster recovery backup capability of the container cloud platform.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
37.
CONTROL CIRCUIT, METHOD, AND APPARATUS FOR BACKUP BATTERY UNIT, AND STORAGE SYSTEM
Disclosed are a control circuit, method, and apparatus for a backup battery unit (BBU), and a storage system, being applied to the technical field of storage. The control circuit includes a BBU charge circuit; the BBU charge circuit includes an improved H-bridge charge unit; and the improved H-bridge charge unit includes a first switch transistor, a second switch transistor, a third switch transistor, a diode, and an inductor.
H02J 9/06 - Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source with automatic change-over
H02J 7/00 - Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
Disclosed in the present disclosure are a video compression system and a server. The video compression system includes a Central Processing Unit (CPU), a hardware detection module, a write control module, a read control module, and an First In First Out (FIFO) array module; the CPU is configured to send a first enable signal to the hardware detection module, the read control module, and the selection switch; the selection switch is configured to select to write test data into the FIFO array module through the hardware detection module based on the first enable signal; the hardware detection module is configured to write test data into the FIFO array module based on the first enable signal; and the read control module is configured to read the test data from the FIFO array module based on the first enable signal and transmit the test data to the hardware detection module.
H04N 19/423 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation characterised by memory arrangements
39.
CLOUD PLATFORM APPLICATION DEPLOYMENT METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
The cloud platform application deployment method and apparatus, the electronic device and the storage medium are provided in the disclosure. The method includes: acquiring the composition information of the application to be deployed in the current cloud platform, the composition information representing the attribute content and composition logic of the application to be deployed; determining the environmental attributes of the respective components included in the application to be deployed according to the composition information of the application to be deployed; calling the corresponding cloud environment plugins for the respective components according to the environmental attributes of the respective components based on the preset multi-cloud environment configurator; and deploying the application to be deployed to the current cloud platform based on the cloud environment plugins of the respective components.
Disclosed is a fan support free of assembly and disassembly tools. The fan support includes: left-right symmetrical slots, provided on a server case base and respectively located on both sides of a fan; an elastic arm assembly, including two symmetrical side arms and an elastic member, bottoms of the two side arms are snap-fitted in the two slots, and tops of the two side arms are connected by the elastic member; a fixing assembly, provided with a limiting structure that fits with a fan housing, and a sliding groove; a pressing assembly, provided with a deformable region, and a sliding structure that fits with the sliding groove, the deformable region is configured to drive the sliding structure to move outwards, the sliding structure pushes the elastic member to stretch and deform to drive the two side arms to disengage from the two slots.
A storage controller system updating method includes: performing a system updating operation on a storage controller, and obtaining a real-time speed value and a real-time operation volume value that are generated when the system updating operation is performed on the storage controller; obtaining a corresponding speed reference value and operation volume reference value from a database based on device information of the storage controller; determining a volume corresponding to an operation volume abnormity based on a relationship between the real-time speed value and the speed reference value and a relationship between the real-time operation volume value and the operation volume reference value, and adjusting a volume parameter; and continuing to perform the system updating operation based on an adjusted volume parameter.
Disclosed are an Ethernet device, and a bidirectional converter and a control method. The bidirectional converter is arranged in any Ethernet device, including: a first switch transistor, a second switch transistor, a third switch transistor, a fourth switch transistor, a first transformer, and a controller. The controller is configured to: enable the bidirectional converter to be in a forward mode or a flyback mode by controlling respective on/off states of the first switch transistor, the second switch transistor, the third switch transistor and the fourth switch transistor. The bidirectional converter is configured to: in response to being in the forward mode, receive power supplied from a network port and transmit electric energy to a load bus, or in response to being in the flyback mode, receive power supplied from the load bus and transmit electric energy to the network port.
H02M 3/335 - Conversion of DC power input into DC power output with intermediate conversion into AC by static converters using discharge tubes with control electrode or semiconductor devices with control electrode to produce the intermediate AC using devices of a triode or a transistor type requiring continuous application of a control signal using semiconductor devices only
Disclosed are a method, system and apparatus for data transmission, and a storage medium, which relate to the field of data transmission, and are used for transmitting data. Address mapping logic is provided in a storage array card, and a host maps a storage address space thereof to the storage array card by the address mapping logic of the storage array card; and after a data transmission instruction is sent to an NVMeSSD by a hard disk control mapping address in the storage array card, the NVMeSSD can directly perform data transmission on the basis of the data transmission instruction and a host storage mapping address in the storage array card, that is, the NVMeSSD can directly perform data transmission with the storage address space inside the host.
Provided is a direct memory access architecture, including: a direct memory access control component, a read data moving component, a write data moving component and a data storage component; wherein the direct memory access control component includes a control register, a read descriptor storage component, a write descriptor storage component, a read command transfer component and a write command transfer component; the control register is configured to obtain descriptor address information; the read descriptor storage component is configured to store a read descriptor obtained by using the control register; the write descriptor storage component is configured to store a write descriptor obtained by using the control register; the read command transfer component is configured to send, to the read data moving component, a read command; the write command transfer component is configured to send, to the write data moving component, a write command.
G06F 13/28 - Handling requests for interconnection or transfer for access to input/output bus using burst mode transfer, e.g. direct memory access, cycle steal
G06F 13/16 - Handling requests for interconnection or transfer for access to memory bus
G06F 13/24 - Handling requests for interconnection or transfer for access to input/output bus using interrupt
45.
Cache Management Method, Apparatus and System, Device and Medium
A cache management method, apparatus and system, a device, and a nonvolatile readable storage medium. The method includes: receiving, by a storage system cache manager, a target operation request sent by a target user; processing the target operation request in a pipeline manner, so as to execute a processing operation corresponding to the target operation request on a cache line using the target operation request; and feeding back a processing result of the target operation request to the target user, and executing a cache maintenance operation corresponding to the processing result according to the processing result by means of a software cache manager.
Disclosed in the present disclosure are an image-text mutual retrieval model training method and apparatus, an image-text mutual retrieval method, and a device, applied to the technical field of retrieval. The image-text mutual retrieval model training method includes: acquiring training data pairs; inputting the training data pair in an initial model, and extracting text coding features of text training data and image coding features of image training data by using a text coding module and an image coding module in the initial model, respectively; calculating a training loss based on the text coding features and the image coding features, and performing parameter adjustment on the initial model based on the training loss; and in response to the training loss meeting a convergence condition, determining the initial model after the parameter adjustment as an image-text mutual retrieval model.
G06F 16/583 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
The present application relates to the field of power electronics technology control, and discloses a temperature control method for a power supply conversion chip, a related assembly, and a multi-phase power supply apparatus. A real-time average value of current temperature accumulation values of power supply conversion chips is calculated, and the output current of the power supply conversion chip whose current temperature accumulation value is not equal to the real-time average value is increased or decreased. The temperature of a power supply conversion chip increases as the output current increases and decreases as the output current decreases, and the temperature of the power supply conversion chip changes under a condition that the output current of the power supply conversion chip is adjusted.
H02M 3/156 - Conversion of DC power input into DC power output without intermediate conversion into AC by static converters using discharge tubes with control electrode or semiconductor devices with control electrode using devices of a triode or transistor type requiring continuous application of a control signal using semiconductor devices only with automatic control of output voltage or current, e.g. switching regulators
G01K 7/01 - Measuring temperature based on the use of electric or magnetic elements directly sensitive to heat using semiconducting elements having PN junctions
G01R 19/00 - Arrangements for measuring currents or voltages or for indicating presence or sign thereof
48.
DATA PROCESSING METHOD AND APPARATUS, ELECTRONIC DEVICE, AND READABLE STORAGE MEDIUM
The present application discloses a data processing method and apparatus, an electronic device, and a computer-readable storage medium. The method is applied to a convolution adaptor, and the convolution adaptor is arranged between external storage and an internal cache of a computing unit. The method includes: acquiring register data, where the register data is determined according to data types of target data and/or convolution types of convolution processing applied to the target data, and is used for describing reading modes of the target data; and reading the target data from the external storage according to the register data, and storing the target data in the internal cache according to a data read sequence.
The present disclosure discloses a method and an apparatus for managing a storage system. The method includes: determining an original resource model of any target object in an original storage system, wherein the target object includes one or more application processes, one or more virtual machine kernels, and/or one or more file storage services in the original storage system; determining a front-end service type corresponding to the original storage system, and querying a target resource model with an attribute of the front-end service type and the greatest similarity with the original resource model in an available model library corresponding to the target object; and determining a software/hardware resource update strategy of the target object by comparing the original resource model with the target resource model, and updating the original storage system and/or deploying a new storage system including the target object based on the software/hardware resource update strategy.
The present application relates to the field of servers, and in particular to a blade server power control system and method, and a blade server. The system comprises: a plurality of blade nodes; a cold plate which exchanges heat with each blade node, there being a cooling liquid in the cold plate; a liquid cooling module used for circulating the cooling liquid in each cold plate; a plurality of power supply units used for supplying power to the plurality of blade nodes and the liquid cooling module; and a system management and control module communicationally connected to each blade node, the liquid cooling module and each power supply unit, and used for monitoring the power consumption of each blade node and of the liquid cooling module and uniformly distributing the power consumption to the plurality of power supply units. According to the solution of the present application, the power consumption balance of system power supply units is achieved, the stability and reliability of a blade server are improved, and cold plate liquid cooling and multi-node adaptability and regulation and control capability are improved.
The present application provides a radio frequency connector, a server testing device, and a server testing method. The radio frequency connector comprises: a housing; a shaft body disposed in the housing, the shaft body being provided with a coupling hole used for coupling with an external piece; a first connecting piece; and a second connecting piece, one of the first connecting piece and the second connecting piece electrically conducting with the shaft body, the other one of the first connecting piece and the second connecting piece electrically conducting with a load, and the second connecting piece being configured so as to be movable, and to have a conductive state when in contact with the first connecting piece and a separated state when separated from the first connecting piece. The second connecting piece is provided with a driving end located in the coupling hole; when no force is applied to the driving end, the second connecting piece is in the conductive state, and the shaft body is electrically connected to the load; when the external piece applies force to the driving end, the second connecting piece is in the separated state, and the shaft body is electrically disconnected from the load. The present application solves the problem in the related art of relatively high costs during signal testing.
G06F 11/22 - Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
H01R 13/629 - Additional means for facilitating engagement or disengagement of coupling parts, e.g. aligning or guiding means, levers, gas pressure
H01R 24/00 - Two-part coupling devices, or either of their cooperating parts, characterised by their overall structure
H01R 43/26 - Apparatus or processes specially adapted for manufacturing, assembling, maintaining, or repairing of line connectors or current collectors or for joining electric conductors for engaging or disengaging the two parts of a coupling device
52.
POWER-FAILURE HOLD CIRCUIT, POWER SUPPLY PROTECTION METHOD AND APPARATUS, AND POWER SUPPLY CONTROL CIRCUIT
The present application relates to the technical field of power supply protection, and discloses a power-failure hold circuit, a power supply protection method and apparatus, and a power supply control circuit. The power-failure hold circuit comprises: a first energy storage circuit comprising a plurality of capacitors connected in parallel, wherein the plurality of capacitors are used for storing energy on the basis of an input bus voltage of a server and reversely supplying power to the server; a second energy storage circuit comprising an inductor and a first switch transistor, wherein the inductor and the first switch transistor are sequentially connected in series between an input bus positive electrode and an input bus negative electrode, and the inductor is used for storing energy so as to boost the voltage to a target voltage; and a third energy storage circuit comprising a second switch transistor and an energy storage capacitor, wherein the second switch transistor and the energy storage capacitor are sequentially connected in series between the inductor and the input bus negative electrode, the inductor is used for charging the energy storage capacitor, and the energy storage capacitor reversely supplies power to the server.
H02J 9/06 - Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source with automatic change-over
H02J 7/34 - Parallel operation in networks using both storage and other DC sources, e.g. providing buffering
H02M 3/155 - Conversion of DC power input into DC power output without intermediate conversion into AC by static converters using discharge tubes with control electrode or semiconductor devices with control electrode using devices of a triode or transistor type requiring continuous application of a control signal using semiconductor devices only
53.
CLOUD COMPUTING-ORIENTED MEMORY ALLOCATION METHOD AND APPARATUS, CLOUD COMPUTING-ORIENTED MEMORY ACQUISITION METHOD AND APPARATUS, AND DEVICE
Disclosed in the present application are a cloud computing-oriented memory allocation method and apparatus, a cloud computing-oriented memory acquisition method and apparatus, and a device. The memory allocation method comprises: receiving request messages from different nodes within a preset time; according to identifiers of the requester nodes and the sizes of requested remote memory resources, separately screening nodes in a cluster on the basis of communication performances and memory resource sizes, so as to determine a contribution node set for each requester node; establishing matching relationships between different requester nodes and contributor nodes in different contribution node sets, and generating at least two effective matching combinations; calculating an evaluation index value of each effective matching combination in the sets; and determining a target effective matching combination and, according to the target effective matching combination, providing a remote memory resource for each requester node. The method finds out optimal memory resource allocation combinations for remote memory contribution nodes and requester nodes, thereby avoiding fragmented remote memories and achieving efficient utilization of remote memory spaces and good system synthesis effects.
H04L 67/60 - Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
54.
METHOD, APPARATUS AND SYSTEM FOR CONTROLLING SIGNAL TRANSMISSION, STORAGE MEDIUM, AND ELECTRONIC DEVICE
Embodiments of the present application provide a method, apparatus and system for controlling signal transmission, a nonvolatile readable storage medium, and an electronic device. The method comprises: receiving, by means of a first link, a first signal sent by a first device, wherein the first link is connected to the first device and a relay control device, the relay control device is a device supporting an open standard interconnect CXL protocol, and the first signal is an electrical signal; using the first signal to determine a link state of the first link; and on the basis of the link state of the first link, sending a control instruction to a microcontroller unit (MCU) device, so as to control transmission of the first signal by means of the MCU device, wherein the MCU is connected to the relay control device. The present application solves the problem in the related art that a data signal defined by a CXL protocol cannot be transmitted between devices by means of an optical fiber link, thereby achieving the effect of transmitting, between devices by means of an optical fiber link, a data signal defined by a CXL protocol.
Embodiments of the present application provide a route flapping positioning method and apparatus, a non-volatile readable storage medium, and an electronic device. The method comprises: acquiring dynamic information of a routing network when route flapping occurs in the routing network, the dynamic information of the routing network being used for representing routing line transformation among a plurality of autonomous domains in the routing network within a preset period in which the route flapping occurs; converting the dynamic information of the routing network into a matching first data matrix; acquiring a second data matrix matching static information of the routing network, the static information of the routing network being used for representing a topological relationship among the plurality of autonomous domains; and using a preset neural network model to perform data fitting on the first data matrix and the second data matrix, so as to obtain a prediction result corresponding to each autonomous domain, and according to the prediction result corresponding to each autonomous domain, determining an abnormal autonomous domain from among the plurality of autonomous domains, the prediction result corresponding to each autonomous domain being used for representing the probability of an abnormality occurring in each autonomous domain.
Provided in the embodiments of the present application is an image information enhancement method. The method comprises: acquiring image information sequences which are collected by a plurality of cameras, and point cloud information; selecting an alternative target sample from a target sample set; adding the alternative target sample to image information at the current moment, so as to obtain enhanced image information at the current moment, and adding the point cloud information corresponding to the alternative target sample; and adding the alternative target sample to image information at other moments, so as to obtain enhanced image information at the other moments, and adding the point cloud information corresponding to the alternative target sample, such that the positions of the alternative target sample in the image information at the other moments and the image information at the current moment meet timing training requirements. In this way, by means of performing extraction, screening and mapping processing on target samples, the diversity of the target samples in image information is greatly increased, the number of parameters of a model is prevented from being too large, and the number distribution of the target samples is more balanced, thereby improving the generalization performance and the detection precision of the model, and also improving the detection performance for a relatively small number of target sample categories.
Disclosed are a correction method and a related assembly. According to a solution, loading is performed on an electronic load, and during each loading, a digital multimeter collects the output voltage of a VR inverter; after loading is ended, it is determined whether the average voltage value of the output voltage collected by the digital multimeter is within a preset voltage range, so as to determine whether the VR inverter stably performs output; and when the average voltage value is not within the preset voltage range, it can be determined that the output of the VR inverter is unstable, and it is needed to correct the VR inverter, i.e., the correction of the VR inverter is realized by adjusting the impedance of a digital potentiometer arranged between the output end and the feedback end of the VR inverter.
A journal storage acceleration method, applied to a distributed storage system and the method comprising: dividing a to-be-written file into a plurality of to-be-written objects, respectively storing the plurality of to-be-written objects in object placement groups, and then constructing corresponding small-block write operations based on the plurality of to-be-written objects and the object placement groups (S11); committing the small-block write operations to a journal file system by using a journal queue, writing the small-block write operations into a hash-based multi-linked list data structure through the journal file system, so as to merge the small-block write operations into a large-block sequential write operation, and flushing of the large-block sequential write operation to a write-back queue (S12); and writing back the large-block sequential write operation in the write-back queue into an extended file system for storage (S13). By virtue of the solution, the small-block write operations are merged into the large-block sequential write operation by using the hash-based multi-linked list data structure, and flushing of the small-block write operations is changed to flushing of the large-block sequential write operation, such that journal storage is accelerated, thereby improving the storage performance.
The present application discloses a person re-identification method, system and device, and a computer-readable storage medium. The method includes: obtaining a first type of person image without a label; making label information for the first type of person image; training a target person re-identification network on the basis of the first type of person image and the label information to obtain a first trained target person re-identification network; extracting a region of interest in the first type of person image; and training, on the basis of the first type of person image and the region of interest, the first trained target person re-identification network to obtain a second trained target person re-identification network, and performing person re-identification on the basis of the target person re-identification network.
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
G06V 10/771 - Feature selection, e.g. selecting representative features from a multi-dimensional feature space
G06V 20/70 - Labelling scene content, e.g. deriving syntactic or semantic representations
60.
FILE SHARING METHODS, FILE SHARING SYSTEM, ELECTRONIC DEVICE AND READABLE STORAGE MEDIUM
The present disclosure discloses a file sharing method and system. The method includes: obtaining a target file and determining a first dynamic key corresponding to the target file; generating a first private key based on the first dynamic key and double private keys; selecting unpaired public and private keys, and generating a first public key based on the first dynamic key, the selected public and private keys; encrypting a symmetric key using the first public key to obtain a key ciphertext; encrypting the target file using the symmetric key to obtain a file ciphertext; signing the first dynamic key, the first public key, the key ciphertext and the file ciphertext using the first private key to obtain signature information; and uploading the first dynamic key, the first public key, the key ciphertext, the file ciphertext and the signature information to a cloud sharing end to share the target file.
H04L 9/06 - Arrangements for secret or secure communicationsNetwork security protocols the encryption apparatus using shift registers or memories for blockwise coding, e.g. D.E.S. systems
A deployment method for a booting sequence of multiple operating systems and related apparatus, related to the technical field of computers and applied to a baseboard management controller (BMC), include: establishing a connection to a disk array (S101); receiving first target logical disk information, wherein the first target logical disk information is information of logical disks provided with to-be-booted operating systems (S102); sending the first target logical disk information to the disk array (S103); and receiving booting flag setting information of the disk array, wherein the booting flag setting information is completion information sent after the disk array sets booting flags for corresponding logical disks based on the first target logical disk information (S104).
Disclosed in the present disclosure are a data recovery method and apparatus for a dual-machine hot standby system, and a medium, which are applicable to the field of data processing. In the method, a main service running time period and a start time period are determined by means of a backed-up start-stop operation record file, and when the start time period is in the main service running time period, it indicates that a split-brain phenomenon possibly occurs in a dual-machine hot standby; and record information of a database backup record file within an initial split-brain time is further read, so as to determine the possibility of split-brain data, a final split-brain time is automatically determined, an Application Programming Interface (API) calling information file is read according to the final split-brain time, so as to recover data, and operation information of a system during brain splitting is automatically restored.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
63.
PEDESTRIAN RE-IDENTIFICATION METHOD, SYSTEM AND DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM
Provided in the present application are a disk processing method and system, and an electronic device. The method comprises: when disk alarm information is detected, marking a corresponding alarm disk as a faulty disk; detecting the state of a disk group corresponding to the faulty disk; if the state of the disk group is degraded, marking the faulty disk as an isolation disk, and generating alarm information; if the state of the disk group is healthy, determining whether there is a redundant disk group; if there is no redundant disk group, operating the faulty disk according to a first preset rule, and generating alarm information; and if there is a redundant disk group, detecting the state of the redundant disk group, if the state of the redundant disk group is healthy, marking the faulty disk as the isolation disk, and generating alarm information, otherwise, operating the faulty disk according to a second preset rule, and generating alarm information.
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
64.
DISK PROCESSING METHOD AND SYSTEM, AND ELECTRONIC DEVICE
Provided are a disk processing method and system, an electronic device. The method comprises: when disk alarm information is detected, marking a corresponding alarm disk as a faulty disk; detecting the state of a disk group corresponding to the faulty disk; if the state of the disk group is degraded, marking the faulty disk as an isolation disk, and generating alarm information; if the state of the disk group is healthy, determining whether there is a redundant disk group; if there is no redundant disk group, operating the faulty disk according to a first preset rule, and generating alarm information; if there is a redundant disk group, detecting the state of the redundant disk group, if the state of the redundant disk group is healthy, marking the faulty disk as the isolation disk, generating alarm information, otherwise, operating the faulty disk according to a second preset rule, generating alarm information.
Disclosed are a disk array redundancy method and system. The method includes: monitoring a running state of a disk array, and sending abnormal information to a state machine in response to a monitored abnormal running state of the disk array to start a timer according to a preset redundancy duration; sending a silent request to an agent to execute silent processing to suspend input and output operations of the disk array, and switching from a normal running mode to a temporary running mode; sending a silent recovery request to the agent to execute silent recovery processing to recover the input and output operations; and after the silent recovery processing is completed, switching a running mode to the normal running mode in response to the fact that timing time of a timer does not exceed a present redundancy duration and the running state is recovered to be normal.
A controlling circuit includes a plurality of analogue switches and a controlling module. The controlling module is configured for, when the current master device of the serial bus is the I3C master device, controlling the analogue switches corresponding to I3C slave devices that are selected by the user to be switched on, whereby the serial bus ensures the data interaction between the I3C master device and the I3C slave devices, and when the current master device of the serial bus is the SMBUS master device, controlling the analogue switches corresponding to SMBUS slave devices that are selected by the user to be switched on, whereby the serial bus ensures the data interaction between the SMBUS master device and the SMBUS slave devices.
The present application relates to the technical field of computers. Disclosed are a firmware upgrading method and apparatus, a BMC chip, a server and a medium. The method comprises: powering on a coprocessor, loading same with a coprocessor system, and initializing inter-core communication with a main processor; powering on the main processor and loading same with a main processor system, and releasing a bus control right by means of loading a bus driver; the main processor sending a bus control right release message to the coprocessor; in response to the bus control right release message, the coprocessor taking over the bus control right; the main processor sending new firmware and a firmware upgrading message to the coprocessor; and, in response to the firmware upgrading message, the coprocessor writing the new firmware into a corresponding server hardware module by means of a bus, so as to upgrade firmware of the server hardware module.
OOIOII) of a primary control module (4); a primary low-voltage power supply module (2) is coupled with a secondary low-voltage power supply module (3) by means of a low-voltage transformer; in response to the primary control module (4) receiving a power supply fault signal sent by a rectification module (0), a circuit starting signal is sent to a thermoelectric standby module (1), so that the thermoelectric standby module (1) generates electric energy and then inputs the electric energy to the primary low-voltage power supply module (2) so that the primary control module (4) maintains working; and the primary control module (4) and a secondary control module (5) bidirectionally transmit signals.
H02J 9/06 - Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source with automatic change-over
H02J 7/32 - Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries for charging batteries from a charging set comprising a non-electric prime mover
H02N 11/00 - Generators or motors not provided for elsewhereAlleged perpetua mobilia obtained by electric or magnetic means
A data access method, a switch and a storage medium, which relate to the technical field of switches. The method is applied to a switch. The switch comprises a central processing unit, a substrate management controller, a main controller and at least one device, wherein the central processing unit and the substrate management controller are each connected to the main controller, and the main controller is connected to the at least one device. The method comprises: by means of a main controller, receiving an interface state corresponding to a target interface, and by means of the main controller, allowing, according to the interface state, a central processing unit or a substrate management controller to access at least one device.
A heterogeneous acceleration method, including the following steps: analyzing a received target data packet to obtain data source end identification information; when the data source end identification information does not exist in a configuration information table, customizing a data message format according to the target data packet to obtain a target data message format, or when the data source end identification information exists in the configuration information table, reading the target data message format from the configuration information table; and according to the target data message format, performing acceleration processing on the target data packet to obtain processed data, and returning the processed data to a data source end.
An internet small computer system interface (iSCSI) service load balancing method is provided by the present application, which includes: uniformly distributing volumes onto different target objects; acquiring information of a plurality of racks where available storage nodes are located and information of available volumes in the available storage nodes, and according to the acquired information of the racks where the available storage nodes are located and the acquired information of the available volumes in the available storage nodes, determining to-be-accessed storage nodes corresponding to current storage tasks, so that the current storage tasks are uniformly allocated to the available volumes of different available storage nodes in the racks; returning the determined to-be-accessed storage nodes to a client for use by the user. An iSCSI service load balancing apparatus, a device and a medium are further provided by the present application.
Embodiments of the present application provide a fault detection method and apparatus for an external device. The method comprises: when target information comprises first error information, injecting the first error information into an external device, and when the target information comprises first register data, sending the first register data to a basic input/output system (BIOS), wherein the first register data is register data generated by a register, which simulates the external device, responding to second error information; acquiring a first log and/or a second log reported by the BIOS, wherein the second register data is register data generated by the register responding to the first error information; and according to the first log and standard register data corresponding to the first error information, determining a running state of the external device, and/or determining a running state of the BIOS according to the second log and a standard log corresponding to the first register data, wherein the running state is a fault state or a normal state.
The present application relates to a dynamic self-adaptive virtual channel mapping method and apparatus, and a storage medium. The method includes: monitoring equivalent data flows of transaction layer packets of different transmit classes, and obtaining the sum of the equivalent data flows of all the transmit classes, the equivalent data flow being the product of a data length of the transaction layer packet and a coefficient; obtaining a pre-calculation value of the number of virtual channels corresponding to each transmit class base on the sum of the equivalent data flows of the transmit classes; and adjusting mapping from the transmit classes to the virtual channels according to the pre-calculation value to obtain a mapping relationship table from the transmit classes to the virtual channels.
Disclosed are a method and system for setting options of a basic input output system (BIOS), a device and a storage medium. The method includes: numbering different option combination modes; creating a first combination structure of the options configured to store numbers of the different option combination modes; sending a default option combination mode value from the BIOS to a baseboard management controller, and forming a second combination structure in the baseboard management controller; and reading configure values from the second combination structure, and executing different operations for option setting according to different configure values. According to the method, the options occupy a small storage space of the baseboard management controller, such that cost of a memory is saved. Logical processing is carried out by means of flag bits, such that the options are synchronized and set between the different combination modes.
Embodiments of the present disclosure relate to a cache method and apparatus applied to all-flash storage, a device, and a medium. The method includes the following steps: acquiring and storing, by a multi-path node, write request information, and sending the write request information to storage nodes; generating, by the storage nodes, confirmation information corresponding to the write request information, and returning the confirmation information to the multi-path node; and determining the number of the confirmation information returned to the multi-path node, and in the case that the number of the confirmation information returned to the multi-path node is not less than one half of the number of the storage nodes, deleting the write request information stored to the multi-path node. According to the cache method and apparatus applied to the all flash storage, the device, and the medium in the embodiments of the present disclosure, in the case that data security is not reduced, the defect of write request delay caused by consistency of distributed cache can be greatly overcome, write request information write and read capabilities of an all flash disk array can be effectively improved, and overall performance of the cache apparatus applied to the all flash storage can be enhanced.
G06F 12/0802 - Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
G06F 12/123 - Replacement control using replacement algorithms with age lists, e.g. queue, most recently used [MRU] list or least recently used [LRU] list
Provided are a server and a tool-free locking mechanism. The tool-free locking mechanism includes: a module tray and a limiting member, wherein mounting grooves for insertion of the module bodies are formed in the limiting member, and at least two mounting grooves are provided in parallel; and at least one movement locking member movably connected to the module tray, where the movement locking member is provided at an outer side between notches of the adjacent mounting grooves, the movement locking member includes a locking portion, and locking structures matching each other are provided between the module tray and an end of the movement locking member close to the module tray; and the locking structures lock the module tray and the movement locking member when the at least one-movement locking member moves towards the module tray and the locking portion abuts against outer sides of module bodies in the adjacent mounting grooves.
The embodiments of the present application provide a program starting method and apparatus, and a server and a non-volatile readable storage medium. The method comprises: a substrate management controller sending starting instruction information to a processor, wherein the substrate management controller stores a mirror image file of a target program, and the starting instruction information is used for instructing the processor to start the target program according to the mirror image file; in a starting process of the processor starting the target program, receiving first verification information sent by the processor, wherein the first verification information is used for determining whether there is a fault in the starting process of the target program; and when it is determined that there is no fault in the starting process, sending the mirror image file to the processor, until the processor completes the starting process. The present application solves the problem in the related art whereby due to the independent operation of a starting process of a BIOS program, a faulty stage cannot be quickly and accurately located when the starting of the BIOS program has a fault, thereby achieving the effect of quickly locating a faulty stage when the starting of a BIOS program has a fault.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
78.
HOLD-UP CIRCUIT OF POWER SUPPLY UNIT, CONTROL METHOD THEREFOR AND CONTROL APPARATUS THEREOF
A hold-up circuit of a power supply unit, a control method therefor and control apparatus thereof. There are multiple power supply units, a power supply unit comprising an input circuit and an output circuit. The hold-up circuit comprises: an input energy storage unit, electrically connected to output ends of the input circuits of the multiple power supply units; an output energy storage unit, comprising multiple output energy storage modules, a first end of an output energy storage modules being electrically connected to an input end of an output circuit, and a second end of the output energy storage module being grounded; an intermediate energy storage unit, comprising an intermediate energy storage module and a first switch module, a first end of the intermediate energy storage module being separately electrically connected to output ends of the multiple input circuits, a second end of the intermediate energy storage module being electrically connected to a first end of the first switch module and the first ends of the output energy storage modules, and a second end of the first switch module being grounded. The described hold-up circuit solves the problem of occupying a large amount of space and power consumption.
The present application provides an inter-node communication method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring a list of a field-programmable gate array; virtualizing the field-programmable gate array according to the list to obtain a first source node and a first target node; acquiring an application descriptor between the first source node and the first target node, wherein the application descriptor comprises a memory address of the first source node and a memory address of the first target node; acquiring identity information of the first source node according to the memory address of the first source node, and acquiring identity information of the first target node according to the memory address of the first target node; and executing a communication action on the first source node and the first target node by means of a remote direct memory access (RDMA) module according to the identity information of the first source node and the identity information of the first target node. The inter-node communication method provided by the present application depends on the RDMA module to execute the communication action between the first source node and the first target node, and a CPU does not need to participate, thereby improving the inter-node communication efficiency.
G06F 15/173 - Interprocessor communication using an interconnection network, e.g. matrix, shuffle, pyramid, star or snowflake
G06F 9/455 - EmulationInterpretationSoftware simulation, e.g. virtualisation or emulation of application or operating system execution engines
H04L 67/10 - Protocols in which an application is distributed across nodes in the network
H04L 67/1097 - Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
80.
METHOD AND APPARATUS FOR ACQUIRING STARTUP LOG, AND METHOD FOR TRANSMITTING STARTUP LOG
A method for acquiring a startup log. The method comprises: determining an operation state of a target device, wherein the operation state indicates normal operation or abnormal operation; if the operation state indicates normal operation, acquiring a startup log from a first target memory device in a baseboard management control system of the target device, wherein the first target memory device is a volatile memory device, and the startup log comprises all logs of the target device in a startup process; and if the operation state indicates abnormal operation, acquiring the startup log from a second target memory device in the target device, wherein the second target memory device is a memory device in the target device. In this way, the technical problems of the efficiency of startup log collection being low and the startup log collection taking a long time due to the fact that a startup log is collected by means of operations of restarting a server, updating firmware, reproducing an abnormal phenomenon, etc., in the related art are solved. Further provided are an apparatus for acquiring a startup log, and a method for transmitting a startup log.
Embodiments of the present application provide a data writing method and a device for a solid-state disk, and a solid-state disk. The method comprises: acquiring logic block addresses of a plurality of pieces of write data stored in a target cache module, the target cache module being located in a buffer of a solid-state disk; storing the plurality of pieces of write data in the buffer into a solid-state storage unit of the solid-state disk; determining whether the logical block addresses of the plurality of pieces of write data are consecutive or not; when the determination result indicates that the logical block addresses of the plurality of pieces of write data are consecutive, acquiring physical block addresses of the plurality of pieces of write data in the solid-state storage unit; and generating a target mapping table according to the logic block addresses of the plurality of pieces of write data and the physical block addresses of the plurality of pieces of write data in the solid-state storage unit, the target mapping table being used for mapping the logic block addresses of the plurality of pieces of write data to the physical block addresses in the solid-state storage unit. The present application solves the problem in the related art of poor write operation performance of a solid-state disk.
Provided are a method and apparatus for initializing a smart network interface card by a server, a device, and a readable medium. The method includes: establishing communication between a baseboard management controller (BMC) of the server and a BMC of the smart network interface card; configuring an integrated I/O module (IIO) of a central processing unit (CPU) by a server host, and initializing the smart network interface card in response to starting up the server; determining in response to configuration of the IIO of CPU by the server host is completed, by the BMC of the server through the communication with the BMC of the smart network interface card, whether the smart network interface card is completely initialized; connecting the IIO of CPU to the smart network interface card by the server host, and continuing executing startup process in response to initialization of the smart network interface card is completed.
The present disclosure provides a configuration method for virtual network interface card resource, including: integrating a plurality of virtual network interface cards in a node where a container group is located, so as to obtain a virtual network interface card set including a plurality of virtual network interface card groups; assigning a target virtual network interface card group for the container group from the virtual network interface card set; analyzing the target virtual network interface card group to obtain address information of target virtual network interface cards in the target virtual network interface card group; and configuring a virtual network interface card resource for the container group according to the address information.
H04L 41/40 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
H04L 41/0895 - Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
84.
METHOD FOR RECOGNIZING EMOTION, TRAINING METHOD, APPARATUSES, DEVICE, STORAGE MEDIUM AND PRODUCT
A method for recognizing emotion, a training method, apparatuses, a device, a storage medium and a product. The method for recognizing emotion includes: acquiring to-be-recognized spiking sequences corresponding to video information; and recognizing the to-be-recognized spiking sequences by using a spiking neural network emotion recognition model, so as to obtain a corresponding emotion category.
A data stream processing method, a storage control node, and a nonvolatile readable storage medium are provided. The storage control node includes a first Data Processing Unit (DPU) and a second DPU. The method includes: the first DPU receives an Input/Output interface (I/O) request, performs protocol offloading on the I/O request to obtain a data message, and stores the data message in a memory; and the second DPU acquires the data message from the memory and performs data processing on the acquired data message.
Provided in the embodiments of the present application are a wave soldering device and a manufacturing method therefor, and a printed circuit board. The wave soldering device comprises: a substrate, which comprises a front face and a back face arranged opposite each other; a target hole group, which comprises a plurality of pad through-holes distributed at intervals in a first direction and running through the front face of the substrate and the back face of the substrate; a virtual hole group, which comprises a plurality of virtual holes running through the back face of the substrate, the virtual holes being correspondingly located on the same side of the pad through-holes on a one-to-one basis and each having a smaller diameter than the pad through-hole, the direction pointing from the pad through-holes to the corresponding virtual holes being a second direction, the direction opposite to the direction in which the wave soldering device enters a wave soldering apparatus being a third direction, the included angle between the second direction and the third direction being smaller than or equal to 90°, and the third direction being perpendicular to the first direction; and a plurality of connecting wires, which are located on the back face of the substrate, wherein the virtual holes are correspondingly connected to the pad through-holes on a one-to-one basis by means of the connecting wires. The present application solves the problem of bridging between pins by tin during a wave soldering process.
Embodiments of the present application provide a mounting ear apparatus for a server, and a server. The mounting ear apparatus comprises: a mounting mechanism (10), the mounting mechanism (10) being connected to a chassis and/or a rack; a mounting ear (20), the mounting ear (20) being movably connected to the mounting mechanism (10) and having a working state in which the mounting ear (20) is mounted on the mounting mechanism (10) and a detached state in which the mounting ear (20) is separated from the mounting mechanism (10), and the mounting ear (20) being internally provided with a control board (21) electrically connected to a device in the chassis; and a locking mechanism, the locking mechanism being provided between the mounting ear (20) and the mounting mechanism (10) and capable of locking the mounting ear (20) in the working state, the locking mechanism being provided with an operating end for unlocking, and the operating end being located on the front surface or the side surface of the mounting ear (20). The present application solves the problem in the related art that a server mounting ear is inconvenient to repair.
Provided in the present disclosure are a memory and apparatus for managing a memory snapshot, a device, and a medium. The method includes: when a memory snapshot generation command is acquired, a virtual machine is suspended; a two-level page table of the virtual machine is copied to obtain a first snapshot page table, and a read-only identifier is set for each of page table entries of the two-level page table; and memory pages corresponding to page table entries of the first snapshot page table are acquired by means of the page table entries of the first snapshot page table, a reference count of each of the memory pages is increased, and the virtual machine is restored from a suspended state to a running state.
G06F 9/455 - EmulationInterpretationSoftware simulation, e.g. virtualisation or emulation of application or operating system execution engines
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
89.
NETWORK TELEMETRY METHOD AND APPARATUS, SWITCH, NETWORK, ELECTRONIC DEVICE AND MEDIUM
The present application relates to the technical field of network communications. Disclosed are a network telemetry method and apparatus, a switch, a network, an electronic device and a medium. The method comprises: receiving a first message sent by an end point switch among first switches in a network under telemetry; receiving a second message sent by a second switch in said network; and, on the basis of the first message and the second message, determining a traffic telemetry result of said network, a data part of the first message comprising telemetry information collected by the first switches, a data part of the second message comprising telemetry information collected by the second switch, the first switches supporting in-band network telemetry, and the second switch not supporting in-band network telemetry. The method and apparatus provided by the present application implement network telemetry without upgrading devices of existing networks, reducing the operation costs of the networks.
The present application discloses an interconnect apparatus for a bus, including at least one decoder, configured to determine, according to at least one read instruction sent by at least one master device, at least one slave device corresponding to the at least one read instruction; a read instruction ID state recording component, Configured to determine the slave device corresponding to the read instruction in response to the decoder, and query, on the basis of a second port of the memory, whether an interconnect apparatus contains a read instruction having the same ID as that of a current read instruction, and configured to route, on the basis of a query result, the current read instruction to a slave device buffer component or a same-ID sorting buffer component corresponding to the read instruction, and write a value into the memory on the basis of a first port of the memory.
The present application relates to an immersed liquid-cooling system and a control method therefor, and a server. The immersed liquid-cooling system comprises a liquid-cooling chassis and a mainboard; the mainboard is fixed in the liquid-cooling chassis in a vertical direction, and a liquid-state cooling working medium is filled in the liquid-cooling chassis, so that the mainboard is immersed in the liquid-state cooling working medium; the mainboard is provided with at least one high-power component and at least one low-power component; the liquid-cooling chassis comprises a body, fluid main flow guide covers, fluid secondary flow guide covers, and flow adjustment plates; the fluid main flow guide covers extend in the vertical direction to form a main flow channel, and the main flow channel contains all high-power components; the fluid secondary flow guide covers are arranged opposite to the fluid main flow guide covers to form secondary flow channels, and the secondary flow channels contain the low-power components; the secondary flow channels are connected to the main flow channel by means of the flow adjustment plates. The present application can coordinate and distribute the flow of the fluid according to the heat dissipation requirements of different areas, thereby achieving directional conveying of a cooling liquid.
The embodiments of the present application relate to the technical field of computers. Provided are a message processing method and apparatus, and a device and a storage medium. The method comprises: acquiring a priority order of a plurality of types of protocol messages, which are sent to a CPU; during the process of sending the protocol messages to the CPU, detecting a resource utilization rate of the CPU; if the resource utilization rate of the CPU is greater than a first threshold value, decreasing the sending rate of at least one type of protocol messages among the plurality of types of protocol messages according to the priority order, such that the total packet receiving rate of the CPU is decreased to a first target packet receiving rate; and if the resource utilization rate of the CPU is less than a second threshold value, increasing the sending rate of at least one type of protocol messages among the plurality of types of protocol messages according to the priority order, such that the total packet receiving rate of the CPU is increased to a second target packet receiving rate. By means of the present application, the capability of a CPU to process a protocol message in an idle state is improved, thereby avoiding a network fault caused by a system being unstable due to the CPU being excessively busy.
A server case latch structure and a server are disclosed. The structure includes: an upper-layer case including an L-shaped groove; lower-layer case having a locking snapping portion and an unlocking snapping portion; a sliding block having an elastic arm provided with a hook, wherein the hook can be snapped with the locking snapping portion or the unlocking snapping portion in the sliding stroke of the sliding block, and the sliding block has an operation portion; and a stopping member. When the sliding block moves to snap with the locking snapping portion, the stopping member is snapped with the L-shaped groove, so that the upper-layer case and the lower-layer case are locked; and when the sliding block moves to disengage the hook from the locking snapping portion, the stopping member is un-snapped locked from the L-shaped groove, and the upper-layer case and the lower-layer case are unlocked.
The present application relates to the technical field of power supply for communication devices. Provided are a power supply backup power system and method. The power supply backup power system comprises a plurality of high-voltage direct-current buses, a centralized energy storage backup power system and a power distribution system, wherein the plurality of high-voltage direct-current buses are connected to the power distribution system; the power distribution system is used for connecting to a communication device, and the power distribution system is used for distributing the high-voltage direct current transmitted on the plurality of high-voltage direct-current buses to the communication device; the centralized energy storage backup power system is bypassed on the plurality of high-voltage direct-current buses; the plurality of high-voltage direct-current buses are used for charging the centralized energy storage backup power system under a normal power supply condition; and the centralized energy storage backup power system is used for discharging a high-voltage direct-current bus having a power supply abnormality. The power supply backup power system provided in the present application has relatively low redundancy, thereby reducing the networking difficulty and cost of the power supply backup power system.
A computing task scheduling method and apparatus, an electronic device, and a computer readable storage medium are disclosed. The method includes: acquiring network description data; determining a dependency relationship between network layer tasks on the basis of the network description data; detecting an idle register group on an artificial intelligence accelerated computing component; generating a target register configuration on the basis of the dependency relationship, the network description data, and a type of the idle register group, and writing the target register configuration into the idle register group; and if a target network layer task completion notification is detected, determining, on the basis of the dependency relationship, a next task of a target network layer task corresponding to the target network layer task completion notification, and starting the next task on a corresponding first function module on the artificial intelligence accelerated computing component so as to execute the next task.
The embodiments of the present application provide a job scheduling method, system and apparatus, and a communication device and a non-volatile readable storage medium. The method comprises: receiving a preset job program sent by a user, wherein the preset job program comprises a preset independent task manager mark; generating an execution plan according to the preset job program, wherein the execution plan comprises execution steps; determining operation positions of the execution steps according to the types of the execution steps, wherein the types of the execution steps are generated according to the independent task manager mark; acquiring resource consumption corresponding to the execution steps; and determining target nodes corresponding to the execution steps according to the resource consumption and the operation positions of the execution steps, and starting the execution steps. In the present application, by combining a Yarn cluster and an independent task manager node, and determining an operation position of an execution step according to the type of the execution step, a flexible resource sharing characteristic of Yarn cluster scheduling is retained, and a resource-sensitive-type calculation step can use sufficient resources of the independent task manager node.
A server internal temperature control method and system, a device, a non-volatile readable storage medium, and a server, relating to the technical field of servers. The method is applied to a server internal temperature control system. The method comprises: acquiring the element temperatures of heating elements in a heating element group by means of a controller; acquiring the fluid temperatures of a fluid between the heating elements in the heating element group by means of the controller and fluid temperature sensors; determining the motor rotating speed of a motor corresponding to the heating element group by means of the controller according to the element temperatures and the fluid temperatures; controlling the motor rotating speed by means of the controller, to control the fluid rate of the fluid between the heating elements in the heating element group, thereby cooling the interior of a server. According to the method, the fluid state in the server is controlled by continuously monitoring the temperature of the fluid between the heating elements, so that the cooling effect on the interior of the server is enhanced.
The air guide hood includes: an air guide hood body arranged with slideways, each slideway including a first and a second operation position; left and right side plates, where each of the left and right side plates has a side slidably provided in a corresponding slideway and rotates to the body; when fixed in the first operation positions, the left and right side plates are provided opposite to each other and are both perpendicular to the body; when detached from the first operation positions and rotated to the second operation positions, the left and right side plates are both attached to the body; and top plates, where two sides of the top plate are rotatably connected to the top of the left and the right side plates so that the top plate is supported by the left and right side plates and is higher than the body.
The present disclosure relates to the technical field of Printed Circuit Board (PCB) routing. Disclosed are a method and apparatus for routing signal line, and a device and a readable storage medium. The method includes: acquiring a signal line of a PCB and an original segmentation region corresponding to a reference plane; determining whether the signal line crosses the original segmentation region; when the signal line crosses the original segmentation region, expanding the original segmentation region to obtain a target segmentation region; and routing the signal line to the target segmentation region.
Provided in the embodiments of the present application are a memory system, a memory resource adjustment method and apparatus, and an electronic device and a non-volatile readable storage medium. The memory system comprises: a first motherboard; a processor and a high-speed interconnection path interface, which are integrated on the first motherboard; a first adapter board; a high-speed interconnection path interface, a chip and a memory module, which are integrated on the first adapter board; and at least one connecting cable, wherein the connecting cable is used for establishing a physical link between the high-speed interconnection path interface of the first motherboard and the high-speed interconnection path interface of the first adapter board, and is used for converting a high-speed path interconnection signal into an intra-processor dedicated bus signal which is transmitted over a physical link based on a peripheral component interconnect express, and the chip of the first adapter board is used for acquiring the converted intra-processor dedicated bus signal and converting the converted intra-processor dedicated bus signal into a double-rate memory signal. High-speed path interconnection signals are converted into IPB resources by means of connecting cables, thereby expanding DRAM resources.
patents
