522 results about "Graphic card" patented technology

The invention discloses an industrial personal computer and multi-graphics card collaborative parallel computation acceleration system, which relates to the technical field of industrial resource allocation and parallel computation, and comprises a resource monitoring and predicting module, a resource management module and a prediction type resource preparation module, the task splitting and collaborative execution module comprises a task splitting module, a cross-node collaborative module and a collaborative operation engine; the intelligent scheduling and dynamic resource allocation module comprises an intelligent scheduler, a dynamic resource allocation module and a conflict avoidance module. According to the method, the GPU video memory utilization rate, the core utilization rate, the temperature, the video memory fragment rate, the available video memory total amount, the CPU core total utilization rate, the load condition and the idle core number index are collected in real time through a resource monitoring module, and the video memory capacity, the GPU core occupancy rate and the CPU load requirement are predicted in advance before a task is submitted in combination with a gradient boosting decision tree and a neural network prediction model; and resources are reserved, so that the scheduling delay is remarkably reduced, and the scheduling hit rate is improved.

The invention discloses a processor, a graphics card, equipment and a resource allocation method and device, and belongs to the technical field of computer resource management. The processor comprises a thread group assembling unit, a thread group scheduling execution unit and at least two processing units, the thread group assembling unit is used for assembling the tasks into one or more thread groups based on the attribute information of the tasks in a task assembling stage; and allocating computing resources for one or more thread groups with the thread group granularity, wherein each thread group is allocated with a processing unit; the thread group scheduling execution unit is used for scheduling one or more thread groups to the processing unit corresponding to each thread group for execution according to a unified scheduling rule, and the unified scheduling rule is a scheduling rule shared by different types of tasks; and the at least two processing units are used for executing the scheduled thread groups. And the computing resources are allocated according to the thread group granularity, so that the execution efficiency of the processor is improved.

The invention discloses a real-time dynamic rendering method based on multi-layer ray tracing and cache collaboration, and relates to the technical field of three-dimensional rendering of an energy station, and the method comprises the steps: converting a scene grid of the energy station into a voxelized grid, generating a global distance field, and generating grid surface data at the same time; a mixed ray tracing mode including software ray tracing and hardware ray tracing is combined to process static and dynamic objects respectively. Through a mixed ray tracing mode, the advantages of software ray tracing and hardware ray tracing are combined, illumination changes in a dynamic scene can be processed in real time, the software ray tracing utilizes a global distance field to quickly respond to intersection query of rays and the scene, the method is suitable for complex static scenes, and the real-time performance of the scene is improved. According to hardware ray tracing, high-precision reflection and shadow of a dynamic object are processed through the hardware acceleration capacity of an RTX display card, the real-time performance and dynamic performance of rendering are improved, and the requirement of an energy field station scene for real-time dynamic rendering is met.

The invention discloses a multi-model dynamic image analysis system, and relates to the technical field of artificial intelligence. The system adopts a heterogeneous computing architecture and comprises a preprocessing model, a multi-modal analysis model, an anisotropic correction model, a large language model, a task knowledge base embedding model and a KV cache management system. An incongruous task reconstruction mechanism based on hardware isomerism is constructed, a large language reasoning model is nested for analysis, and efficient reuse of computing resources is achieved by using a cross-model KV cache optimization technology. The system is provided with multiple graphics cards and a double-channel NUMA, and a multi-mode large language model carries out unsupervised or weak supervised training on a target detection model in the operation of the system. According to the system, through a dynamic load scheduling strategy, a mechanism for reasoning by using a processor and a memory enhanced display card in a full-load mode is innovatively designed, and three-section real-time streaming enhanced output is achieved. According to the system, through a dynamic load scheduling strategy, a mechanism for reasoning by using a processor and a memory enhanced graphics card in a full-load mode is innovatively designed.

The invention relates to a data processing method, a processor, a chip, a display card and electronic equipment, and relates to the field of intelligent computing, and the method comprises the following steps: reading a part of a first matrix from a local memory or a register of a computing unit in response to M tensor computing engines in a tensor computing engine cluster, reading the second matrix from the tensor memory, and executing matrix operation by the M tensor calculation engines according to part of the first matrix and the second matrix respectively to obtain operation results corresponding to the M tensor calculation engines; and the M tensor calculation engines respectively write operation results corresponding to the M tensor calculation engines into registers of the M tensor calculation engines. According to the embodiment of the invention, the computing power can be increased under the condition that the sizes and the bandwidths of the local memory and the register in the computing unit are not increased.

The invention relates to the technical field of performance testing, and discloses a performance testing method, device and equipment for a graphics card, and the method comprises the steps: carrying out the quaternion stage decoupling of a rendering pipeline of the graphics card, and obtaining a vertex shader decoupling unit, a geometric shader decoupling unit, a rasterization unit decoupling unit and a pixel shader decoupling unit; stage isolation performance tests are respectively carried out to obtain first performance test data of the vertex shader, second performance test data of the geometric shader, third performance test data of the rasterization unit and fourth performance test data of the pixel shader; the first performance test data, the second performance test data, the third performance test data and the fourth performance test data are comprehensively analyzed to obtain performance bottleneck positioning results of all stages of the rendering pipeline, the coupling states of all the stages of the rendering pipeline can be effectively separated, and accurate adjustment and control over the running states of all the stages are achieved.

A graphics card lifting device comprises an elongated lifting member having a front end and a rear end. A groove track is provided between the two ends. A first portion and a second portion are provided at the front end and the rear end of the elongated lifting member respectively. The second portion is movable along the groove track. When one end of a graphics card is disposed between the front end and the rear end, a spacing between the front end and the rear end is adjusted, so that the one end of the graphics card is supported by the first portion and the second portion.

The invention discloses an automatic texture color mapping method for large-scale point cloud data. The automatic texture color mapping method comprises the following steps: firstly, realizing geometric alignment of geographic texture data and point cloud data; then realizing release of intra-core buffer by means of a mass point cloud space segmentation and retrieval management technology, and segmenting the mass point cloud into a plurality of regional point cloud blocks; carrying out filtering processing on the regional point cloud blocks to filter out discrete flying spots; secondly, considering correction constraints of different texture source information to realize seamless generation of geographic texture data; secondly, efficient point cloud preliminary color assignment is achieved by means of the spatial relation between geometric mapping and local aggregation of regional point cloud blocks and geographic texture data; secondly, eliminating the texture information (color) of the wrong coloring point cloud by using the self-shielding judgment result of the point cloud; and finally, realizing spatial merging of regional point cloud block data sets by using an efficient out-of-core file merging technology. According to the method, the dependence on hardware equipment (such as a large memory and a high graphics card) is avoided, and the block processing of massive point clouds is efficiently realized.

The invention provides a graph card-based hybrid scheduling rendering method and system, and the method comprises the steps: dividing a frame buffer area, binding the divided frame buffer area with a task, completing the rendering of each card through a hybrid task scheduling strategy, and finally synthesizing and outputting a complete graph; a frame buffer area of a rendering graph is divided into a plurality of graph cards according to display criticality, each graph card is bound with an independent rendering task and a video memory area, a unique task division and resource allocation mode is formed, and the mode is different from a traditional overall rendering mode; and in combination with a hybrid scheduling strategy of high-priority task preemptive scheduling and dynamic card task parallel rendering, the problems of rendering task priority conflict and resource utilization are effectively solved.

Disclosed in the present application are resource configuration methods, a resource configuration system, an electronic device and a storage medium. A resource configuration method comprises: acquiring configuration requirement information corresponding to a computing power service; on the basis of the configuration requirement information, performing resource configuration on a general-purpose server and a graphics card resource pool to obtain a configuration result, wherein the general-purpose server is obtained on the basis of processor resource configuration, and the graphics card resource pool comprises a plurality of graphics processing units that support a hot-swapping function; and on the basis of the configuration result, providing a first instance for the computing power service, wherein the first instance comprises a processor resource allocated by the general-purpose server and a processor resource allocated by the graphics card resource pool. The present application solves the technical problems in the related art of low resource utilization rate and poor flexibility of the entire unit caused by heterogeneous models being constrained by the fixed configuration of processor resources of the entire unit.

The invention relates to the technical field of material detection, and discloses a graphics card welding spot pseudo soldering automatic detection method based on image recognition, and the method comprises the steps: firstly comparing a graphics card visible light image after gray level normalization with an infrared thermal distribution diagram after noise suppression, and obtaining the surface texture and thermodynamic characteristics of a welding spot; and then splicing the two to obtain an associated feature weight matrix, extracting texture and thermodynamic feature vectors of a welding spot region from the associated feature weight matrix, and splicing the texture and thermodynamic feature vectors into a fusion feature matrix according to channel dimensions. And finally, positioning pseudo soldering spot coordinates in combination with the standard soldering spot feature library, and generating a graphics card soldering spot pseudo soldering defect report according to the coordinates and the texture fracture index. According to the process, through multi-feature fusion and comparison, pseudo soldering accurate detection and report generation are achieved; according to the method, the accuracy and the efficiency of insufficient solder detection of the graphics card welding spots based on image recognition can be improved, and a high-precision automatic solution is provided for quality detection of the graphics card welding spots.

The invention relates to the technical field of video card power management, and discloses a power management method, device and equipment for a video card and a storage medium. The method comprises the following steps: collecting time sequence data of SM unit frequency of a graphics card, GDDR video memory bandwidth and VRM output voltage in real time, and establishing a GPU power consumption topology model; based on the GPU power consumption topology model, extracting a time sequence feature vector of the load change of the rendering pipeline; constructing a sparse representation matrix based on the time sequence feature vector; performing power consumption gradient threshold judgment and delay type classification by using the sparse representation matrix, and identifying a delay fault type in the current graphics card power management system; and adjusting a switching parameter of the GPU, a VRM compensation current and a fan rotating speed according to the identified delay fault type, and updating a delay detection threshold value and a repair strategy strength parameter. According to the invention, three different delay fault types of frequency climbing, voltage regulation and temperature control current limiting can be accurately distinguished, and continuous optimization of power management performance is realized.

The invention discloses a video card information monitoring system, a server, a monitoring method and a storage medium. Comprising a graphics card and a substrate management controller, the display card comprises a command register, a data register and a processor; the baseboard management controller generates a request instruction containing a first type of operation codes and at least one parameter according to a monitoring demand, sends the request instruction to the command register, reads a status bit from the command register, and reads data from the data register or writes the data according to the request instruction; the command register receives a request instruction sent by the substrate management controller, stores an operation code, a parameter and a status bit, and feeds the status bit back to the substrate management controller; the processor analyzes and executes the request instruction in the command register, and updates the status bit in the command register; the data register stores data written by the baseboard management controller or the processor and allows the baseboard management controller or the processor to read the data, and the problem that the number of monitorable information is limited due to I2C address limitation is solved.

A computer case with a graphics card holder is provided, which includes a computer case body and a graphics card holder. The graphics card holder includes a first support member, a second support member, and a third support member. The first support member is slidably connected to a fixing member, the second support member is vertically provided at one end of the first support member, the second support member is provided with a graphics card adapter cable. One side of the third support member away from the first support member is fixedly connected to the computer case body. By setting the graphics card holder and fixing component, the computer case can stably fix the graphics card. The setting of the graphics card adapter cable allows the graphics card to be placed vertically, thereby enhancing the heat dissipation performance of the graphics card.

1. The name of this design product: server channel fan frame. 2. Purpose of this design product: It is used to be installed on the chassis to dissipate heat for the motherboard, graphics card and hard disk inside the chassis. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: Stereoscopic drawing 1.

The invention discloses a graphics card optimization method and system based on intelligent rendering acceleration, and relates to the technical field of graphics card intelligent rendering. Physical topology of an input scene is analyzed, and an acting force network and a causal event chain between objects are constructed; extracting a spatial-temporal characteristic matrix based on the physical topology of the input scene, dividing the input scene into a static region and a dynamic region, and binding cross-scale physical attributes based on the spatial-temporal characteristic matrix to generate layered scene fingerprints; performing historical fingerprint matching on the layered scene fingerprints, and performing static region multiplexing and dynamic region light path propagation prediction based on a matching result to generate a primary prediction rendering frame; analyzing the primary rendering frame based on a causal event chain to identify an abnormal frame and a compliance frame; performing grading processing on the abnormal frame and the predicted rendering frame to obtain a rendering result, and dynamically updating a physical rule base and a causal event chain according to the rendering result; by analyzing the scene physical topology and the causal event chain, intelligent acceleration of the graphics card rendering process is realized.

The invention relates to the technical field of graphics card resource scheduling, and discloses a graphics card resource load balancing control method and system. The method comprises the following steps: constructing a sample set containing actual GPU video memory occupation and utilization rate; constructing a GPU video memory prediction function and a GPU utilization rate prediction function; the schedulability of the current task is judged through a soft constraint matching mechanism; gPU target allocation for executing the task; and carrying out dynamic scheduling by adopting a multi-stage KV cache block recovery mechanism. In the prior art, only static configuration or a single index is adopted to carry out GPU load estimation, and especially in the scene of large Token length uncertainty and obvious KV cache dynamic expansion in an LLM class model reasoning stage, accurate video memory resource scheduling control is difficult to realize. Due to the fact that the multivariable prediction model and the hybrid priority scheduling mechanism are introduced, the load stability of the GPU in the large language model reasoning task is improved.

The invention provides a semi-aviation transient electromagnetic rapid inversion method and system based on multi-GPU parallel, and relates to the technical field of semi-aviation transient electromagnetic inversion. Comprising the following steps: determining a calculation task of a Jacobian matrix based on necessary initial information and an initial model; splitting a Jacobian matrix calculation task into a plurality of sub-tasks on a CPU memory, transmitting the plurality of sub-tasks to corresponding GPUs respectively, and executing calculation of the sub-tasks in parallel on the GPUs; results of all the subtasks are spliced into a complete Jacobian matrix in a CPU memory; obtaining an update model based on the complete Jacobian matrix; and performing forward modeling calculation on the updated model until the root-mean-square error meets a threshold value, thereby obtaining a final model which is a three-dimensional inversion result. According to the method, a Jacobian matrix calculation task is split into a plurality of sub-tasks on a CPU memory, the plurality of sub-tasks are allocated to a plurality of corresponding GPU graphics cards, and the process of solving an inversion model is accelerated through a multi-GPU parallel calculation scheme.

The invention relates to a computer graphics card flat-lying installation support and method and a computer mainframe, the computer graphics card flat-lying installation support comprises a supporting plate, the lower surface of one end of the supporting plate is fixedly connected with an installation base, the other end of the supporting plate is fixedly connected with a bayonet socket, and a concave groove for containing a fan of a graphics card is formed in the middle of the upper surface of the supporting plate; a heat dissipation open groove is formed in the bottom surface of the concave groove; the mounting seat is detachably connected with the computer mainboard; the lower end of the bayonet socket is provided with a golden finger matched and plugged with a graphics card slot on a computer mainboard, and the upper end of the bayonet socket is slidably connected with a slot seat; the overall height of the display card after the display card is assembled is low while the display card is positioned, the display card can be flexibly clamped and fixed and buffered, damped and protected in cooperation with the air bag damping unit, and a plurality of ejector pins are used for tensioning the position of a bayonet socket and locking the position before and after sliding while achieving the electrical adapter function of a connector. And moreover, the plugging operation of the display card and the bayonet socket is more reliable, and the mainboard is completely avoided, so that the condition of damaging the mainboard is avoided.

The invention relates to the technical field of vehicle-mounted equipment testing devices, and discloses a method and a device for testing the imaging quality of a vehicle-mounted camera in a salt-spray high-low temperature environment, and the method comprises the steps: installing a to-be-tested camera on an adjustable platform in a salt-spray environment cabin, maintaining an optimal angle, and forming a closed environment; adjustable sodium chloride salt mist is provided by the salt mist generation system, and environmental parameters are controlled by the temperature and humidity generation control system; the salt mist environment chamber is provided with high-low-temperature-resistant high-transmittance glass and a self-cleaning device, and the glass is cleaned before soaking is finished; the camera is lightened through the lightening driving system, and the camera is adjusted to be centered with the test graphic card; by adjusting working conditions such as temperature, humidity, light environment and attitude angle, the camera is driven to shoot an image card image and transmit the image card image to the image analysis module; the module analyzes the image in real time and quantifies the imaging quality of the camera; the technical problem that the composite environment working condition cannot be simulated in the prior art is solved.

The invention discloses a graphics card multi-task co-processing system based on dynamic video memory allocation, which belongs to the technical field of computer resource management and comprises a task grading module, a video memory state scanning module, an allocation strategy module and a resource recovery integration module. The task grading module is used for acquiring tasks, dividing the tasks into high-priority tasks and low-priority tasks, and establishing an independent resource pool according to initial priorities of the tasks; the video memory state scanning module is used for scanning a video memory use state in the independent resource pool and generating a video memory resource distribution map; the allocation strategy module is used for generating an allocation instruction based on the video memory resource distribution graph and the task priority; and the resource recycling and integrating module is used for recycling the continuous blocks released after the high-priority task is finished and updating the video memory resource distribution map. Through the task grading module, the video memory state scanning module, the allocation strategy module and the resource recovery integration module, the system response efficiency is improved.

The invention discloses a low-cost rapid three-dimensional Gaussian sputtering method based on an interactive heuristic mode, and relates to the technical field of three-dimensional scene modeling and image reconstruction. The method comprises the following steps: acquiring an initial three-dimensional point cloud and camera parameters; calculating a global budget upper limit for three-dimensional Gaussian modeling and a target budget upper limit for dense optimization according to the number of the initial three-dimensional point clouds and the parallel computing capability of the used graphics card; the method comprises the following steps: performing initial optimization training under global budget upper limit control, performing dense optimization under target budget upper limit control of dense optimization, eliminating gauss which do not meet a retention condition to obtain a dense three-dimensional Gaussian set, performing global fine adjustment optimization, and triggering an artificial auxiliary optimization process to perform active adjustment. According to the invention, a set of complete reconstruction optimization scheme oriented to the consumer-level graphics card environment is designed, the dependence on hardware resources is remarkably reduced on the premise of ensuring the three-dimensional reconstruction quality, and rapid, efficient and controllable three-dimensional scene modeling is realized.

The present invention discloses a GPU task queue management method, system, and device. The method comprises: dividing physical GPU graphics card resources into multiple GPU computing units according to GPU partitioning rules; constructing a GPU resource pool based on the GPU computing units; monitoring the operating status information of the GPU resource pool in real time, obtaining task parameters in the GPU resource pool according to the operating status information, and constructing a task queue with priority according to the task parameters; dynamically allocating to-be-scheduled tasks in the GPU task queue and the GPU computing units based on a resource scheduling strategy, and performing resource scheduling management on the GPU task queue based on the resource parameter information of the GPU computing units. The present invention avoids waste and idleness of resources, improves the management and scheduling efficiency of GPU resources, and realizes the maximum value utilization of the GPU resource pool.

The invention discloses electronic equipment and a display card frame rate and display screen refresh rate matching adjustment method thereof. The method comprises the following steps: when a graphics card receives a rendering task, extracting a picture complexity parameter of the rendering task and a current hardware parameter of the graphics card; inputting the picture complexity parameter of the rendering task and the current hardware parameter of the display card into a rendering time prediction model, so as to output the predicted rendering time of the rendering task through the rendering time prediction model, and transmitting the preset rendering time to a display screen; the display screen is controlled to adjust the refresh rate of the display screen according to the predicted rendering time, so that the refresh rate of the display screen is matched with the output frame rate of the display card. The prediction rendering time obtained according to the fusion rendering time prediction model and fusion of the picture complexity parameters and the current hardware parameters of the graphics card is high in accuracy, and the problems of picture tearing, jamming and delayed response caused by mismatching of the output frame rate of the graphics card and the refresh rate of a display screen can be effectively solved.

The invention relates to a surface water sanitation dynamic monitoring method and system based on an Internet of Things large model, and the method comprises the steps: collecting surface water parameters, the surface water parameters comprise dissolved oxygen, pH, ammonia nitrogen, chemical oxygen demand and total organic carbon; converting the surface water parameters into a water quality semantic vector; inputting the water quality semantic vector into an inference model deployed on a consumer server to obtain a surface water analysis result, the reasoning model is obtained by training a light-weight large model based on a preset data set, the light-weight large model adopts an LLaMA-7B model as a base model, and a LoRA adaptation layer is introduced behind each MLP layer of Transformer. According to the method, the surface water sanitation dynamic monitoring can be operated efficiently and in real time on edge computing equipment such as a consumer-level graphics card, so that the deployment cost is greatly reduced, and the response speed is increased.

This invention relates to the field of film and television rendering processing technology, specifically disclosing a rendering frame-stuttering detection method, electronic device, and computer storage medium. The method includes: firstly, acquiring first rendering data and second rendering data from a rendering task, wherein the first rendering data is the rendering data of completed frames in the rendering task, and the second rendering data is the rendering data of the current frame in the rendering task; then, based on the first and second rendering data, predicting the completion time of the current frame; if the actual rendering time of the current frame is greater than the completion time of the current frame, then it is determined that the rendering task has a frame-stuttering issue. In this way, the existence of frame-stuttering in a rendering task can be accurately detected, allowing relevant personnel to easily end the rendering task, as well as restart or cancel it, avoiding the task from remaining in a frame-stuttering state and wasting machine resources and user time.

This invention discloses a method, device, medium, and system for generating and using 3D character culling data in computer graphics, belonging to the field of computer graphics. The method includes the following steps: pre-generating frame-level cluster bounding box data corresponding to sampled animation frames; submitting the frame-level cluster bounding box data to the graphics processing unit of the graphics card during initialization; updating the current animation frame using an animation state machine during runtime; during the culling operation, searching for the bounding box data of the cluster in the current animation frame based on the current animation frame and the cluster index, and culling it; if the current animation frame does not match the sampled animation frame, interpolating and calculating the bounding box data corresponding to the current animation frame based on the pre-generated frame-level cluster bounding box data of the animation frames before and after the current animation frame. This invention has advantages such as low overhead, good dynamics, and high culling performance.

The present disclosure relates to a data processing method, a processor, a chip, a graphics card and an electronic device, and relates to the technical field of intelligent computing. The method comprises the following steps: in response to M tensor computing engines in a tensor computing engine cluster completing reading of a partial first matrix from a local memory or a register of a computing unit to which the M tensor computing engines belong and reading of a second matrix from a tensor memory, the M tensor computing engines respectively perform matrix operation according to the partial first matrix and the second matrix to obtain corresponding operation results of the M tensor computing engines; and the M tensor computing engines respectively write the corresponding operation results into the registers of the M tensor computing engines. The embodiment of the present disclosure can increase computing power without increasing the size and bandwidth of the local memory and the register inside the computing unit.

The invention relates to the technical field of material thermal performance testing, in particular to a thermal conductivity testing method for a thermal conductivity interface material, and develops a qualitative thermal conductivity testing method for the thermal conductivity interface material based on graphics card hardware and baking machine software. Extreme working conditions are simulated by utilizing baking machine software, the heat dissipation efficiency of different heat conduction materials is quantitatively analyzed by monitoring the temperature change of a display card chip, and the method is better to implement and easy to judge for companies or individuals without professional heat conduction testing equipment, and has better guiding significance for practical application.