Abstract: A register reading method and apparatus, a device and a medium. After a server is crashed, a CPU-register collecting request is triggered. Different types of CPUs correspond to different types and quantities of registers that require data collection. Therefore, by firstly determining the register required to be read corresponding to the CPU type, and determining the reading mode of the register, the disadvantage that the reading mode that may merely use a single instruction may not satisfy the demand on field crashing analysis is prevented. Subsequently, by using a PECI bus, the register data of a plurality of registers are read. By collecting the registers of the CPU directly by using the PECI bus, the problem that the performance excessively relies on the stability of the ME due to the intermediate transfer via the ME is prevented, which greatly increases the reading success rate of the registers.

Abstract: A method and apparatus for performing a power stress test on an FPGA acceleration card and a computer-readable storage medium. The method includes: dividing, according to a partial reconfiguration method, a hardware resource of an FPGA acceleration card into a static region serving as a hardware logic implementation region for performing a normal function test, and a dynamic PR region including a blank mode occupying no hardware resource and a power test mode for performing a power stress test, and burning FPGA firmware having a partial reconfiguration function to a flash memory; upon receiving a request for power stress test, configuring an operation mode of the dynamic PR region to be the power test mode, loading, to the dynamic PR region, a dynamic PR configuration file burned in the flash memory; and calling a power stress test module to execute the power stress test in the dynamic PR region.

Abstract: A service orchestration method, apparatus and device for a physical machine, and a computer-readable storage medium. The method includes: creating a physical machine resource that inherits all attributes of a cloud host, and modifying the physical machine resource according to characteristics of a target physical machine to obtain a target physical machine resource; configuring an underlying driver of Ironic according to the characteristics of a target physical machine; and invoking the Ironic by means of nova, such that the target physical machine resource is used to perform service orchestration on the target physical machine when the Ironic is running. On the basis of implementing service orchestration on a physical machine, the target physical machine resource in the method is obtained by inheriting all attributes of a cloud host and performing modification according to the characteristics of a target physical machine.

Abstract: Provided is a control circuit of a buck converter, comprising three transistors, seven resistors and a comparator. Also provided is a server. In this solution, when a phase voltage of a buck converter changes, a controller in the buck converter is controlled to output a signal for turning off a lower MOS transistor, so that after the signal is transmitted through the line, the lower MOS transistor can be controlled to be exactly turned off just when the current is reversed. Such an accurate reverse current detection function can reduce the voltage loss of the buck converter, thereby improving the efficiency of a system in standby or having a light load.

Abstract: A method, system, and related component for detecting properness of a PG pin power-on timing sequence are provided. The method comprises: obtaining a pull-up level of a PG pin of a VR chip (S101); determining a value of a pull-up resistor of the PG pin, as a first resistance, when a current injected into the VR chip by using the pull-up level is equal to a maximum withstand current of the VR chip (S102); obtaining an equivalent resistance to ground when the PG pin is at a low level, and calculating, based on the equivalent resistance to ground, a value of the pull-up resistor of the PG pin, as a second resistance, when an output voltage of the PG pin is equal to a preset interference voltage limit value (S103); and outputting first prompt information when it is determined that an actual resistance of the pull-up resistor is lower than the first resistance or the second resistance (S104).

Abstract: A heat dissipation control method is disclosed, wherein the heat generation speed of a heat dissipation channel may be calculated according to a power consumption value of each component in the heat dissipation channel, and a radiator is then controlled on the basis of the heat generation speed, whereby the heat dissipation speed of the heat dissipation channel is comparable to the heat generation speed. A heat dissipation control apparatus and device are further disclosed, which have the same beneficial effects as the heat dissipation control method.

Abstract: A method and device for detecting a memory downgrade error. The method comprises: capturing and analyzing a memory error by means of an operating system (OS); sending a memory downgrade error log to a management chip BMC on a server motherboard according to the analysis result; and after the BMC receives log information, detecting and locating an uncorrectable memory inspection error on the basis of an algorithm.

Abstract: A method and device for avoiding abnormal signal oscillation in UVLO test, applied to a power supply module, includes: a voltage detection module (301) detecting a voltage of an enable terminal of the power supply module during an under voltage lock out UVLO test; a difference calculation module (302) calculating a difference value between a detected voltage and a voltage trigger threshold of the enable terminal; upon a control module (303) determining that the difference value is below a preset first threshold, the control module increasing the voltage of the enable terminal during UVLO test via a voltage adjustment module. The application of the above solution of the present application can avoid abnormal signal oscillation in UVLO test.

Abstract: A method for clearing a register, including: causing the PLD to set preset bits of a first register and a second register as an invalid state, detect whether a command is received from a MCU; when the command being received, parsing the command and determining whether a reading or writing event is triggered; when the reading event being triggered, setting the preset bit of the first register as a valid state, reading data of the preset bit of the first register, postponing clearing, by the PLD, the preset bit of the first register for a preset time; when the writing event being triggered, setting the preset bit of the second register as the valid state, writing, by the MCU, data into the preset bit of the second register, causing the PLD to acquire the data, postpone clearing the preset bit of the second register for a second preset time.

Abstract: A method and an apparatus for monitoring a Battery Backup Unit (BBU) (312), a server (301), and a readable storage medium (330) are provided. The method includes following steps: monitoring a voltage and a ampere-hour of the BBU (312) (S101); when the voltage is static and the variation of the ampere-hour is greater than a variation threshold value, determining a current moving window point by a remaining power percentage curve corresponding to the BBU (312) (S102); determining a current moving window by a previous moving window point and the current moving window point (S103); and calculating a remaining capacity of the BBU (312) by the current moving window (S104).

Abstract: The present disclosure discloses a cloud platform resource cross-project transfer method and system, and a computer storage medium. The method includes: generating a slot position and an authentication key for a resource to be transferred based on a transfer request; generating a transfer Identity (ID) of the resource to be transferred, acquiring a project ID where the resource to be transferred is located based on a resource ID, constructing a transfer structure body, and writing the transfer structure body into a database; generating a transfer record of the transfer structure body in the database, and setting a resource status of the resource to be transferred as waiting for transfer in the transfer record; and returning the transfer ID, the authentication key, a transfer description, and the resource ID to a transfer user based on the transfer request.

Abstract: Provided is a dynamic Huffman encoding method based on a sorting network. Compared with traditional dynamic Huffman coding solutions, the method implements sorting on the basis of the sorting network, therefore the sorting process is not only stable, but also may ensure a stable sorting result; and moreover, sorting steps and related operations are simpler, thereby greatly simplifying the sorting and iteration processes, and thus the sorting efficiency is higher. In addition, the sorting process better facilitates program implementation and transplantation, and implementation of hardware and software may achieve good effects. In addition, the present disclosure further provides a dynamic Huffman coding apparatus and device based on a sorting network, and a readable storage medium, and the technical effects thereof correspond to the technical effects of the above method.

Abstract: The present application discloses a method for calculating equal lengths of wound differential wires, wherein the method includes: calculating total lengths of a P differential wire and an N differential wire of a to-be-wound-with-equal-lengths target differential-wire pair; according to the total lengths of the P differential wire and the N differential wire, calculating a differential-wire length difference between the P and N differential wires, and determining the one having a lower total length as a target differential wire; acquiring a distance between the P differential wire and the N differential wire, and using the distance as a protruding height; acquiring a preset protruding angle, and calculating the protruding height and the protruding angle according to a first calculating relation, to obtain a length added by one protruding; and according to the differential-wire length difference and the length added by one protruding, calculating a total quantity of protrudings.

Abstract: A device verification method, a UVM verification platform, an electronic apparatus, and a storage medium are provided. The method includes: determining a transaction class corresponding to a device under test, and instantiating a first interface in a callback function; sending input data to the device under test based on a bus protocol, and sequentially adding the input data to an array of the first interface according to addresses of the input data; instantiating a second interface in a monitor device, and sequentially adding output data to an array of the second interface according to addresses of the output data; and comparing the input data and the output data that have same addresses in the array of the first interface and the array of the second interface, and outputting a verification result of the device under test according to a comparison result.

Abstract: Disclosed are a cluster quorum method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: acquiring a historical election set, and obtaining a first node quantity and a power condition by using the historical election set; generating a quorum parameter by using the first node quantity according to the power condition; acquiring a current network topology, and judging whether the current network topology satisfies the quorum parameter; and if the current network topology satisfies the quorum parameter, providing a cluster service. According to the method, a new network topology after a failure is not required to include the majority of nodes in an original cluster, whereby the network topology can continue to work no matter a quantity of nodes in the network topology while data consistency is ensured, improving viability of the cluster.

Abstract: A method and apparatus for expanding cloud volume, and a device and a readable medium are provided. The method includes: determining whether there is an request of a host in a cloud volume and confirming a snapshot started during cloud backup (S1); in response to there being no IO request, expanding a snapshot volume of the snapshot started during the cloud backup and the cloud volume (S2); expanding a bitmap of the snapshot started during the cloud backup, and setting a bitmap obtained by expanding as a first preset value (S3); after completion of a cloud backup task, expanding a snapshot volume of an another snapshot that is not started in the cloud backup (S4); and expanding a bitmap of the another snapshot that is not started in the cloud backup, and setting a bitmap obtained by expanding as a second preset value (S5).

Abstract: Provided is an image processing method, which includes: determining whether the number of written rows of source image data in a DDR is a preset number of rows or a stop write number of rows, the preset number of rows being an integer multiple of the number of rows of an image block determined according to a compression condition, and the image block being any image block in an image block matrix determined on the basis of an entire frame of image; if yes, reading the source image data of the current image block from the DDR on the basis of a first read address of the current image block, the number of rows, and the number of columns; and performing compression on the source image data of the current image block to obtain compressed data, and writing the compressed data to the DDR.

Abstract: Disclosed is an IO request pipeline processing device. The device mainly includes: an IO state buffer and a pipeline controller, wherein the IO state buffer includes multiple elements, for storing context information including a module calling sequence generated by a CPU; and the pipeline controller is configured to perform pipeline control on an IO request according to the context information. The device performs pipeline management on an IO processing state by arranging hardware modules, which shares the huge workload during an original CPU software control process, and also reduces the requirements for CPU design. At the same time, processing logic of the pipeline controller is triggered by the module calling sequence recorded in the IO state buffer, which may reduce the implementation power consumption and improve the implementation efficiency.

Abstract: A capacity expansion method for a storage cluster has the following steps: receiving an expansion instruction and determining a new expansion node corresponding to the instruction; traversing all placement groups to determine reference counts of OSDs corresponding to each of the groups, wherein the reference count of each OSD is the same as the number of groups; setting the OSD with the largest reference count associated with each group as an OSD to be determined; calling a data distribution interface to select an optimal OSD from the new node to replace the OSD to be determined. The OSD with the largest reference count associated with each group can only be replaced by an OSD in the new node, so that the data migration between the old nodes is eliminated, thereby improving expansion and reconstruction efficiency, reducing the resource utilization rate when the system is being expanded, and improving system performance.

Abstract: A node synchronization method and apparatus, an electronic device, and a computer-readable storage medium, include: acquiring node data sent by each slave node; obtaining a target cluster parameter from each piece of node data, and obtaining a standard cluster parameter by using the target cluster parameter based on an event queue length; determining an authorized slave node according to the standard cluster parameter, and judging whether a quantity of authorized slave nodes is greater than a quantity threshold; and if the quantity is greater than the quantity threshold, performing event playback on the authorized slave node by using a cluster event based on the standard cluster parameter; or if the quantity is not greater than the quantity threshold, controlling the authorized slave node to perform status synchronization on an unauthorized slave node, and performing event playback on the authorized slave node by using a cluster event after status synchronization.