Resource occupation processing method and device suitable for GPU and storage medium

Abstract

The invention provides a resource occupation processing method and device suitable for a GPU (Graphics Processing Unit) and a storage medium, a monitoring strategy of resources at the GPU is pre-configured, and resource processing paths of the monitoring strategy are resource creation, resource calling and resource deletion in sequence; monitoring a control channel between the user and the GPU in real time to generate monitoring data; if it is judged that the processing path of any resource in the monitoring data is different from the resource processing path of the monitoring strategy, a target task corresponding to the resource is selected; and performing release processing on the GPU resources occupied by the target task. According to the technical scheme provided by the invention, whether inefficient and meaningless occupancy occurs in resource occupancy of the GPU or not can be judged according to the operation of the user on the GPU, the resource occupancy rate of the GPU is reduced, and the processing efficiency of the processing flow realized based on the GPU is improved.

Description

technical field [0001] The present invention relates to the technical field of data analysis, in particular to a resource occupation processing method, device and storage medium suitable for GPU. Background technique [0002] Graphics processing unit (English: graphics processing unit, abbreviation: GPU), also known as display core, visual processor, display chip, is a special graphics processing unit in personal computers, workstations, game consoles and some mobile devices (such as tablet computers, smart phones) etc.) to do image and graphics-related operations on the microprocessor. [0003] When the GPU is working, the more tasks it processes, the higher its resource occupancy rate, and the higher the resource occupancy rate of the GPU, the slower its task processing speed, so it needs to be adjusted in time according to the working conditions of the GPU. The resource usage of the GPU enables the GPU to work normally and quickly. [0004] When the GPU is working, ther...

AI Technical Summary

Problems solved by technology

[0004] When the GPU is working, there are two situations in which its resources are occupied. One is normal occupation, that is, when it is performing task processing because of a large amount of task processing, the resource occupancy rate of the GPU will be high. The other is The situation is that when the GPU is working, some tasks cannot be processed normally due to task processing errors, but the tasks that cannot be processed normally still occupy the resources of the GPU, which makes the resource occupancy rate of the GPU falsely high, that is, the resources of the GPU are not fully used. At the correct task processing level, the overall processing efficiency of the GPU is reduced

Images